anthropics/knowledge-work-plugins
180 skills424k installs4M starsGitHub
Install
npx skills add https://github.com/anthropics/knowledge-work-pluginsSkills in this repo
1Data VisualizationCreate effective data visualizations with Python matplotlib seaborn plotly Use when building charts choosing the right chart type for a dataset creating publication-quality figures or applying design principles like accessibility and color theory name data-visualization description Create effective data visualizations with Python matplotlib seaborn plotly Use when building charts choosing the right chart type for a dataset creating publication-quality figures or applying design principles like accessibility and color theory user-invocable false Data Visualization Skill Chart selection guidance Python visualization code patterns design principles and accessibility considerations for creating effective data visualizations Chart Selection Guide Choose by Data Relationship What You're Showing Best Chart Alternatives Trend over time Line chart Area chart if showing cumulative or composition Comparison across categories Vertical bar chart Horizontal bar many categories lollipop chart Ranking Horizontal bar chart Dot plot slope chart comparing two periods Part-to-whole composition Stacked bar chart Treemap hierarchical waffle chart Composition over time Stacked area chart 100 stacked bar.10.3kinstalls2DocumentationWrite and maintain technical documentation Trigger with write docs for document this create a README write a runbook onboarding guide or when the user needs help with any form of technical writing API docs architecture docs or operational runbooks name documentation description Write and maintain technical documentation Trigger with write docs for document this create a README write a runbook onboarding guide or when the user needs help with any form of technical writing API docs architecture docs or operational runbooks Technical Documentation Write clear maintainable technical documentation for different audiences and purposes Document Types README What this is and why it exists Quick start 5 minutes to first success Configuration and usage Contributing guide API Documentation Endpoint reference with request response examples Authentication and error codes Rate limits and pagination SDK examples Runbook When to use this runbook Prerequisites and access needed Step-by-step procedure Rollback steps Escalation path Architecture Doc Context and goals High-level design with diagrams Key decisions and trade-offs Data flow and integration points Onboarding Guide Environment7.7kinstalls3Code ReviewReview code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps. --- name: code-review description: Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps. argument-hint: "<PR URL, diff, or file path>" --- # /code-review > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). Review code changes with a structured lens on security, performance, correctness, and maintainability. ## Usage ``` /code-review <PR URL or file path> ``` Review the provided code changes: @$1 If no specific file or URL is provided, ask what to review.7.5kinstalls4Build DashboardBuild an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file. --- name: build-dashboard description: Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file. argument-hint: "<description> [data source]" --- # /build-dashboard - Build Interactive Dashboards > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). Build a self-contained interactive HTML dashboard with charts, filters, tables, and professional styling. Opens directly in a browser -- no server or dependencies required. ## Usage ``` /build-dashboard <description of dashboard> [data source] ``` ## Workflow ### 1.6.8kinstalls5Task ManagementSimple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments. --- name: task-management description: Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments. user-invocable: false --- # Task Management Tasks are tracked in a simple `TASKS.md` file that both you and the user can edit. ## File Location **Always use `TASKS.md` in the current working directory.** - If it exists, read/write to it - If it doesn't exist, create it with the template below ## Dashboard Setup (First Run) A visual dashboard is available for managing tasks and memory. **On first interaction with tasks:** 1. Check if `dashboard.html` exists in the current working directory 2. If not, copy it from `${CLAUDE_PLUGIN_ROOT}/skills/dashboard.html` to the current working directory 3.6.1kinstalls6Memory ManagementTwo-tier memory system that makes Claude a true workplace collaborator Decodes shorthand acronyms nicknames and internal language so Claude understands requests like a colleague would CLAUDE md for working memory memory directory for the full knowledge base name memory-management description Two-tier memory system that makes Claude a true workplace collaborator Decodes shorthand acronyms nicknames and internal language so Claude understands requests like a colleague would CLAUDE md for working memory memory directory for the full knowledge base user-invocable false Memory Management Memory makes Claude your workplace collaborator someone who speaks your internal language The Goal Transform shorthand into understanding User ask todd to do the PSR for oracle Claude decodes Ask Todd Martinez Finance lead to prepare the Pipeline Status Report for the Oracle Systems deal 2 3M closing Q2 Without memory that request is meaningless With memory Claude knows todd Todd Martinez Finance lead prefers Slack PSR Pipeline Status Report weekly sales doc oracle Oracle Systems deal not the company Architecture CLAUDE md Hot cache 30 people common terms6.1kinstalls7System DesignSystem Design guides architects and backend engineers through structured system design workflows covering requirements gathering, high-level component design, deep dives into data models and API contracts, scale/reliability patterns, and explicit trade-off analysis. Developers use it when designing new services, evaluating architectural decisions, or tackling API design and data modeling questions. Key workflows include building component diagrams, defining storage and caching strategies, estimating load, planning failover mechanisms, and documenting assumptions for growing systems. --- name: system-design description: Design systems, services, and architectures. Trigger with "design a system for", "how should we architect", "system design for", "what's the right architecture for", or when the user needs help with API design, data modeling, or service boundaries. --- # System Design Help design systems and evaluate architectural decisions. Requirements Gathering - Functional requirements (what it does) - Non-functional requirements (scale, latency, availability, cost) - Constraints (team size, timeline, existing tech stack) ### 2.6kinstalls8View PdfThe view-pdf skill opens PDFs in a local interactive viewer for visual collaboration rather than text ingestion. Use it when users want to show contracts, highlight key terms, fill forms, place signature images, stamp labels like CONFIDENTIAL, or walk through a document with annotations. A local PDF server renders documents while list_pdfs, display_pdf, and interact list files, open a viewUUID-bound session, and batch follow-up commands sequentially. Annotation types include highlight, underline, note, stamp, and image placements for signatures and initials. Workflows cover collaborative markup using get_text to orient annotations before add_annotations, visual form filling with fill_form and get_screenshot verification, and visual signing with image annotations that are not certified digital signatures. display_pdf accepts local paths or HTTPS URLs including arXiv auto-conversion to PDF. Do not use for summarization or pure text extraction; native Read handles ingestion. Out of scope: PDF creation and cryptographic signing.5.3kinstalls9Knowledge SynthesisKnowledge synthesis is the last mile of enterprise search inside Anthropic knowledge work plugins. It takes raw results from chat, email, cloud storage, wikis, and project trackers and produces one coherent trustworthy answer with full source attribution. The workflow deduplicates cross-source duplicates by merging same-day signals from the same author or entity, clusters related themes, ranks by query relevance, assesses confidence from freshness and authority tiers, and formats detail level for small medium or large result sets. Citation rules require inline attribution plus a source list with channel, folder, thread title, sender, and date. Confidence expression distinguishes high agreement across authoritative fresh sources from single dated chat references and surfaces conflicting conclusions explicitly rather than silently picking a winner. Anti-patterns block source-by-source dumps, buried answers, and over-aggressive summarization that strips nuance. The skill is user-invocable false, so agents invoke it after federated search returns heterogeneous snippets needing merge, rank, and cite treatment.5.2kinstalls10Tech DebtThe tech-debt skill identify, categorize, and prioritize technical debt. Trigger with "tech debt", "technical debt audit", "what should we refactor", "code health", or when the user asks about code quality, refactoring priorities, or maintenance backlog.. Tech Debt Management Systematically identify, categorize, and prioritize technical debt. Categories Type Examples Risk ------ ---------- ------ Code debt Duplicated logic, poor abstractions, magic numbers Bugs, slow development Architecture debt Monolith that should be split, wrong data store Scaling limits Test debt Low coverage, flaky tests, missing integration tests Regressions ship Dependency debt Outdated libraries, unmaintained dependencies Security vulns Documentation debt Missing runbooks, outdated READMEs, tribal knowledge Onboarding pain Infrastructure debt Manual deploys, no monitoring, no IaC Incidents, slow recovery Prioritization Framework Score each item on: - Impact : How much does it slow the team down? (1-5) - Risk : What happens if we don't fix it? (1-5) - Effort : How hard is the fix? (1-5, inverted - lower effort = higher priority) Priority = (Impact + Risk) x (6 - Effort) Output5kinstalls11ArchitectureThe architecture skill creates Architecture Decision Records or evaluates system designs from the knowledge-work-plugins collection. Modes include Create an ADR for technology choices like Kafka versus SQS, Evaluate a design such as reviewing a microservices proposal, and System design for new components from requirements and constraints. Output follows ADR format with status, date, deciders, context, decision, options considered with complexity cost scalability and team familiarity tables, trade-off analysis, consequences, and action items. It references the system-design skill for detailed requirements gathering, scalability analysis, and trade-off frameworks. When connectors are available, it searches knowledge bases for prior ADRs and links project tracker epics. Tips urge stating constraints upfront like ship timelines or throughput targets, naming explicit alternatives for balanced analysis, and including non-functional requirements such as latency, cost, expertise, and maintenance burden alongside functional needs.5kinstalls12Testing StrategyThe testing-strategy skill helps agents design effective testing approaches that balance coverage, speed, and maintenance cost. It applies the testing pyramid with many fast unit tests, some integration tests, and few slow E2E tests. Strategy guidance varies by component type: API endpoints need business-logic unit tests plus HTTP integration and consumer contract tests; data pipelines need validation, transformation correctness, and idempotency checks; frontend work covers component, interaction, visual regression, and accessibility tests; infrastructure targets smoke, chaos, and load tests. Focus areas include business-critical paths, error handling, edge cases, security boundaries, and data integrity while skipping trivial getters, framework code, and one-off scripts. Output is a structured test plan listing what to test, test types per area, coverage targets, and example cases plus gaps in existing coverage. Trigger when users ask how to test, request a test plan, or need test architecture guidance.5kinstalls13Incident ResponseThis workflow automates incident management across four phases: triage (assess severity, identify affected systems, assign roles), communicate (draft internal and customer updates, set war room cadence), mitigate (document steps, track timeline, confirm resolution), and postmortem (generate blameless analysis with 5-whys, action items, and lessons learned). Developers trigger it when production fails, alerts fire, or post-incident review is needed. The tool classifies incidents as SEV1-4 based on user impact and response urgency, generates structured status updates at regular intervals, and produces postmortem documents that separate systems-level root causes from individual actions. It integrates with monitoring, incident management, and chat platforms when available to pull metrics, page responders, and broadcast updates automatically. Severity classification (SEV1-4) with response time SLAs from immediate all-hands to next business day Structured status updates with impact, actions taken, next steps, and timestamped timeline Blameless postmortem generation including 5-whys root cause analysis and action items with owners Three modes - new incident, status update mid-incident, p.4.6kinstalls14Explore Dataexplore-data generates a comprehensive data profile for tables or uploaded files, revealing row/column counts, data types, grain, and quality metrics. Developers use it when encountering unfamiliar datasets to classify columns (identifier, dimension, metric, temporal, text, boolean, structural), detect issues (high nulls, duplicates, suspicious values), and discover patterns. The tool runs profiling queries against live warehouse tables or infers types from uploaded CSV/Excel/Parquet/JSON files, then surfaces null rates, cardinality ratios, value distributions, and flagged anomalies. Follow-up recommendations suggest specific trend analyses, distribution deep-dives, and correlation studies. Essential for data exploration workflows before building dashboards, reports, or analytics pipelines. Profiles table structure: row count, column types, primary keys, date range coverage, and data grain Classifies all columns by role - identifier, dimension, metric, temporal, text, boolean, structural Detects data quality issues: null4.6kinstalls15DebugDebug is a structured troubleshooting workflow for engineers facing production issues, staging-to-prod discrepancies, post-deploy failures, or behavior divergence with unclear root causes. It guides users through four phases: reproduce (map expected vs. actual behavior and scope), isolate (narrow to affected component and recent changes), diagnose (form and test hypotheses, trace code paths), and fix (propose solutions with side-effect analysis and regression tests). When monitoring, source control, or project tracking tools are connected, the skill pulls correlated logs, deploys, config changes, and related tickets to accelerate diagnosis and ticket creation. Four-phase structured workflow: reproduce, isolate, diagnose, fix Integrates with monitoring, source control, and project tracker connectors for log pulls and change correlation Generates Debug Reports with expected vs. actual behavior, root cause analysis, and prevention steps Accepts error messages, stack traces, reproduction steps, logs, or behavioral descriptions as input Emphasizes exact error text, recent changes, and contextual constraints to narrow scope fast Structured error reproduction and scope mapping Root cause.4.5kinstalls16AnalyzeThe /analyze skill transforms natural language questions into actionable data insights across three complexity levels: quick answers for single metrics, full analyses for trend investigation and comparisons, and formal reports for stakeholder reviews. It parses user intent, gathers data from connected warehouse MCPs or manual sources, executes SQL queries, validates results against row counts and aggregation logic, then presents findings with methodology and caveats. Developers use this for exploratory data work, business metric reporting, and data quality assessments. The workflow includes schema exploration, multi-dimensional analysis, pattern detection, and visualization recommendations via the data-visualization skill. Three complexity levels: quick answers, full analyses with trend investigation, formal stakeholder reports Connects to data warehouse MCP servers for schema exploration and SQL query execution Validates results before presenting - checks row counts, nulls, magnitudes, and aggregation logic Supports manual data input via CSV, Excel, or user-provided query results if no warehouse connected Outputs direct answers, data tables, charts, or narratives depending on que.4.5kinstalls17Search StrategyThe search-strategy skill Query decomposition and multi-source search orchestration. Breaks natural language questions into targeted searches per source, translates queries into source-specific syntax, ranks results by relevance, and handles ambiguity and fallback strategies. If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md. The core intelligence behind enterprise search. Transforms a single natural language question into parallel, source-specific searches and produces ranked, deduplicated results. Turn this: `` "What did we decide about the API migration timeline?" `` Into targeted searches across every connected source: `` ~~chat: "API migration timeline decision" (semantic) + "API migration" in: engineering after:2025-01-01 ~~knowledge base: semantic search "API migration timeline decision" ~~project tracker: text search "API migration" in relevant workspace `` Into targeted searches across every connected source: ~~chat: "API migration timeline decision" (semantic) + "API migration" in: engineering after:2025-01-01 ~~knowledge base: semantic search "API migration timeline decision" ~~project tracker: text search "API migration" i.4.4kinstalls18Deploy Checklistdeploy-checklist generates a structured pre-deployment verification document organized into Pre-Deploy, Deploy, and Post-Deploy phases, plus explicit Rollback Triggers. Developers invoke it before shipping any release, especially those involving database migrations, feature flags, or breaking API changes. The skill accepts a service or release name as an argument and customizes checklist items based on deployment context described in natural language. When source control, CI/CD, or monitoring connectors are available, it can pull live PR approval status, pipeline results, and current metric baselines to pre-fill thresholds. Core outputs include task items for CI gate verification, staging smoke tests, canary rollout monitoring, stakeholder notification, changelog updates, and ticket closure. Generates three-phase checklist: Pre-Deploy, Deploy, and Post-Deploy with discrete checkboxes for each step Rollback Triggers section lets teams define error rate and latency thresholds before the deploy begins4.3kinstalls19Source ManagementSource Management handles detection and orchestration of connected MCP data sources (chat, email, cloud storage, project tracker, CRM, knowledge base) for enterprise search. Developers use it to query multiple sources intelligently, applying query-type-specific prioritization (decision/status/document/people/policy queries each have ranked source orders) and gracefully handling rate limits without blocking results. Key workflows include checking available sources, guiding users to connect new MCP servers via .mcp.json configuration, tracking source health across sessions, and respecting API quotas by batching requests, avoiding unnecessary calls, and continuing searches across remaining sources when rate limits hit. Automatically detects newly added MCP servers and includes them in subsequent searches. Detects available MCP sources by checking tool prefixes; maps chat, email, cloud storage, project tracker, CRM, knowledge base capabilities. Routes queries using five source-priority strategies (decision, status, document, people, policy) instead of uniform ordering.4.2kinstalls20Create Vizcreate-viz generates publication-quality data visualizations from Python DataFrames or query results using matplotlib, seaborn, or plotly. Developers use it to convert raw data into charts for reports, dashboards, and presentations. The workflow handles data source selection (query, paste, CSV, or existing DataFrame), chart type recommendation based on data relationships (line for trends, bar for comparisons, scatter for correlation, heatmap for matrices), and code generation with design best practices. It applies colorblind-friendly palettes, removes chart junk, formats numbers appropriately (percentages, currency, large numbers), and ensures readable typography. Output is saved as PNG and code is provided for modification. Supports static charts via matplotlib/seaborn or interactive charts via plotly with hover and zoom. Recommends chart type automatically based on data relationship (trend, comparison, distribution, correlation, composition, ranking, flow, geographic, matrix). Generates publication-quality code with design best practices: colorblind palettes, proper number formatting, readable typography, whitespace management.4.2kinstalls21StandupStandup generates structured daily standup updates by aggregating recent work activity across source control, project trackers, chat, and CI/CD systems. Developers use it to prepare for team standups without manual note-taking, pulling commits and PRs from git, ticket status changes from project management tools, relevant discussions from chat, and build status from CI/CD pipelines. The tool formats output into yesterday/today/blockers sections. It works standalone when developers provide a brief summary of their work, or supercharged when tools are connected via Skillselion connectors. Key workflow: run each morning to automatically gather activity, add context about blockers, and optionally reformat for Slack or email before sharing with the team. Pulls recent commits, PRs, and code reviews from source control automatically. Aggregates ticket moves and status changes from connected project trackers. Scans chat systems for relevant discussions and decisions affecting work.4.2kinstalls22SearchThe search skill Search across all connected sources in one query. Trigger with "find that doc about...", "what did we decide on...", "where was the conversation about...", or when looking for a decision, document, or discussion that could live in chat, email, cloud storage, or a project tracker. If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md. Search across all connected MCP sources in a single query. Decompose the user's question, run parallel searches, and synthesize results. Before searching, determine which MCP sources are available. Attempt to identify connected tools from the available tool list. Common sources: - ~~chat chat platform tools - ~~email email tools - ~~cloud storage cloud storage tools - ~~project tracker project tracking tools - ~~CRM CRM tools - ~~knowledge base knowledge base tools Follow SKILL.md reference sections for detailed command examples and edge-case handling.4.1kinstalls23UpdateThe update skill Sync tasks and refresh memory from your current activity. Use when pulling new assignments from your project tracker into TASKS.md, triaging stale or overdue tasks, filling memory gaps for unknown people or projects, or running a comprehensive scan to catch todos buried in chat and email. If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md. Keep your task list and memory current. Two modes: - Default: Sync tasks from external tools, triage stale items, check memory for gaps - --comprehensive: Deep scan chat, email, calendar, docs flag missed todos and suggest new memories ``bash /productivity:update /productivity:update --comprehensive `` bash /productivity:update /productivity:update --comprehensive Read TASKS.md and memory/ directory. If they don't exist, suggest /productivity:start first. Check for available task sources: - Project tracker (e.g. Asana, Linear, Jira) (if MCP available) - GitHub Issues (if in a repo): gh issue list --assignee=@me If no sources are available, skip to Step 3. Fetch tasks assigned to the user4kinstalls24Product BrainstormingProduct Brainstorming is a thinking partner skill that helps PMs explore problem spaces deeply, generate divergent solution ideas, and stress-test assumptions before committing to a direction. It operates in four modes: Problem Exploration (mapping the problem ecosystem and root causes), Solution Ideation (generating 5-7+ distinct approaches with constraint removal and analogies), Assumption Testing (identifying and validating the riskiest dependencies), and Strategy Exploration (mapping competitive dynamics and second-order effects). The skill structures sessions through five phases - Frame, Diverge, Provoke, Converge, and Capture - using frameworks like How Might We, JTBD, Opportunity Solution Trees, SCAMPER, OODA Loop, and Reverse Brainstorming. It emphasizes being opinionated, challenging constructively, and avoiding anti-patterns like solutioning before framing or feature parity copying. Four brainstorming modes: Problem Exploration, Solution Ideation, Assumption Testing, and Strategy Exploration with distinct questions and techniques for each.4kinstalls25StartThe start skill Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project. If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md. You are helping a biological researcher get oriented with the bio-research plugin. Walk through the following steps in order. Your AI-powered research assistant for the life sciences. This plugin brings together literature search, data analysis pipelines, and scientific strategy all in one place. ``` Test which MCP servers are connected by listing available tools. Group the results: Test which MCP servers are connected by listing available tools. Group the results: Literature & Data Sources: - ~~literature database — biomedical literature search - ~~literature database — preprint access (biology and medicine) - ~~journal access — academic publications - ~~data repository — collaborative research data (Sage Bionetworks) Drug Discovery & Clinical: - ~~chemical database — bioactive compound4kinstalls26Content CreationContent Creation provides templates and frameworks for drafting marketing content across six channels: blog posts, social media, email newsletters, landing pages, press releases, and case studies. Developers use this skill when building content workflows, CMS integrations, or AI-powered writing assistants that need to produce channel-specific copy. Key workflows include structuring blog posts with SEO headlines and meta descriptions, composing email subject lines under 50 characters with preview text, formatting social media hooks for LinkedIn/Twitter/Instagram/Facebook, designing landing pages with value propositions and CTAs, and building case study layouts with snapshots and metrics. The skill covers writing best practices (8th-grade reading level, active voice, scannable formatting), SEO fundamentals (keyword placement, title tags, H1-H3 structure, image alt text), headline formulas (how-to, numbered lists, contrarian), hook formulas (statistics, scenarios, questions), and CTA principles with placement strategy.3.9kinstalls27Legal Risk AssessmentThe legal-risk-assessment skill Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review. You are a legal risk assessment assistant for an in-house legal team. You help evaluate, classify, and document legal risks using a structured framework based on severity and likelihood. Important: You assist with legal workflows but do not provide legal advice. Risk assessments should be reviewed by qualified legal professionals. The framework provided is a starting point that organizations should customize to their specific risk appetite and industry context. Legal risks are assessed on two dimensions: Severity (impact if the risk materializes): Severity (impact if the risk materializes): Level Label Description --- --- --- 1 Negligible Minor inconvenience; no material financial, operational, or reputational impact. Can be handled within normal operations. 2 Low Limited impact; minor financial exposure (< 1% of relevant contract/deal value); minor operational disruption; no public at.3.8kinstalls28Competitive IntelligenceThe competitive-intelligence skill researches competitors extensively and generates an interactive HTML battlecard for deal positioning. Developers and sales engineers use it when asked for competitive intel, battlecards, head-to-head comparisons, or what is new with a named competitor. Standalone mode relies on web research across product pages, pricing, blogs, release notes, reviews, job postings, and public comparisons for up to five competitors. Optional connectors can add CRM win and loss data, existing battlecard docs, internal chat intel, and customer call transcripts when available. Execution flows through seller context gathering, company research, per-competitor deep dives, connected source pulls, and HTML artifact assembly. The output is a self-contained dark-themed file with a comparison matrix landing view, clickable competitor tabs, differentiation grids, pricing intelligence, objection handling, and landmine questions. Data structures capture profile, recent 90-day releases, where each side wins, talk tracks for early, displacement, and late-eval scenarios, and refresh cadence guidance for monthly or deal-driven updates.3.6kinstalls29Design CritiqueDesign Critique is an Anthropic knowledge-work plugin skill that delivers structured UX and visual design feedback from Figma links, screenshots, or written descriptions. It walks reviewers through a five-part framework: first impression within two seconds, usability, visual hierarchy, consistency against the design system, and accessibility checks for contrast, touch targets, and readability. Feedback must be specific with severity tables, explain why issues matter, propose alternatives, acknowledge what works, and match critique depth to the stated design stage from exploration through final polish. Optional connectors can pull Figma components and tokens or cross-reference user feedback data when available. Output follows a markdown template with overall impression, usability findings with severity, hierarchy notes, consistency table, accessibility checklist, positives, and three prioritized recommendations. Users supply the design asset, context such as audience and flow purpose, and optional focus areas like mobile or onboarding.3.4kinstalls30Sql QueriesThe sql-queries skill helps developers write correct, performant, readable SQL across major data warehouse dialects including PostgreSQL, Snowflake, BigQuery, Databricks, and related platforms. It activates when users need queries, slow SQL optimization, dialect translation, or complex analytical SQL with CTEs, window functions, and aggregations. Each dialect section documents date and time helpers, string functions, semi-structured JSON or VARIANT access, array handling, and performance tips such as EXPLAIN ANALYZE on PostgreSQL, clustering keys on Snowflake, and partition pruning guidance on BigQuery. The reference contrasts syntax differences like ILIKE versus LOWER LIKE, DATEADD versus DATE_ADD, and JSON path operators so translated queries stay faithful. Performance sections call out indexing, EXISTS over IN, warehouse sizing, RESULT_SCAN reuse, and flatten patterns for nested data. Developers reach for it when they must ship warehouse-specific SQL without guessing function names or when migrating analytics queries between engines.3.4kinstalls31Statistical Analysisstatistical-analysis teaches descriptive statistics, trend analysis, outlier detection, hypothesis testing, and cautionary guidance for business data interpretation. Central tendency guidance picks mean for symmetric data, median for skewed distributions, and mode for categorical fields, always reporting mean and median together for business metrics. Spread covers standard deviation, IQR, coefficient of variation, and range with percentile narratives from p1 through p99. Trend analysis documents seven-day and twenty-eight-day moving averages, WoW MoM YoY comparisons, simple CAGR and log growth formulas, seasonality checks, and naive through moving-average forecasts with uncertainty ranges instead of false precision. Outlier methods include z-score above three, IQR 1.5 bounds, and p1/p99 percentile cuts with investigate-don't-delete handling for data errors versus genuine extremes. Hypothesis testing framework covers null and alternative hypotheses, alpha 0.05, t-tests, z-tests for proportions, paired t-test, ANOVA, Mann-Whitney U, and chi-squared with practical versus statistical significance and effect sizes. Caution sections warn on correlation not causation, multiple comparison.3.4kinstalls32Financial StatementsFinancial Statements is a knowledge-work plugin command that generates income statements, balance sheets, and cash flow statements with period-over-period comparison and variance analysis. Usage accepts period-type monthly, quarterly, annual, or ytd plus a period such as 2024-12 or 2024-Q4. Phase 1 gathers trial balance data from connected ERP or warehouse sources or prompts for pasted spreadsheet figures with comparison periods. Phase 2 formats a multi-column income statement with current, prior, variance, and budget columns across revenue, COGS, operating expenses, and net income with margins. Phase 3 calculates variances, applies scaled materiality thresholds, decomposes drivers into volume, rate, mix, and timing effects, and writes investigation narratives. Phase 4 summarizes key metrics and Phase 5 lists material variances. Reference sections cover ASC 220, 210, and 230 GAAP presentation plus balance sheet and indirect cash flow formats and common period-end adjustments. Output assists workflows but requires qualified financial professional review.3.3kinstalls33Slack MessagingSlack Messaging Best Practices teaches agents to compose effective Slack messages using mrkdwn, which differs from standard Markdown. Formatting rules cover bold with single asterisks, italic with underscores, strikethrough with tildes, inline and block code with backticks, quotes with angle brackets, and links as url|display text in angle brackets. Common mistakes to avoid include double-asterisk bold, Markdown headers, bracket-paren links, and horizontal rules that Slack does not render. Message structure guidance says lead with the point in the first line, keep messages to one to three short paragraphs, use line breaks generously, convert three or more items into bullet lists, and bold names, dates, deadlines, and action items. Thread etiquette recommends replying in threads for specific messages, using reply_broadcast only when everyone needs the reply, posting new topics in the channel, and continuing existing conversations in the original thread. Tone should match the channel, with emoji reactions suggested for simple acknowledgments when MCP tools cannot add reactions directly.3.2kinstalls34Ux Copyux-copy is a slash-command skill for writing or reviewing interface copy across CTAs, error messages, empty states, confirmation dialogs, tooltips, loading states, and onboarding text. It asks for screen context, user goal, emotional state, tone, and character limits before producing recommendations. Principles enforce clarity without jargon, concise wording, consistent terminology, usefulness toward the user goal, and human tone rather than robotic phrasing. Pattern tables define verb-first specific CTAs, error structure of what happened plus why plus fix steps, empty states explaining what the area is and how to start, and confirmation dialogs that name the action and consequences with action-labeled buttons instead of OK or Cancel. Output format returns recommended copy, alternatives table with tone notes, rationale tied to user context, and localization cautions about idioms or expansion. Optional connectors can pull brand voice from a knowledge base or layout constraints from a design tool when available. Triggers include write copy for, button label questions, error message review, and onboarding wording tasks.3kinstalls35User ResearchUser Research is an Anthropic knowledge-work skill for planning, conducting, and synthesizing user research studies. It compares methods including interviews, usability testing, surveys, card sorting, diary studies, and A/B testing with sample sizes and timelines. The interview guide structure covers warm-up, context, deep dive, reaction to concepts, and wrap-up timing. Analysis frameworks include affinity mapping, impact-effort prioritization, journey mapping, and jobs-to-be-done framing. Deliverables span research plans, interview guides, synthesis reports, and highlight reels of key quotes. Developers and product teams invoke it when users ask for user research plans, interview guides, usability tests, survey design, research questions, or help understanding users through structured studies. The skill stays method-focused without prescribing specific survey tools, making it a lightweight planning assistant for early validation and design critique workflows rather than statistical analysis platforms.2.9kinstalls36Design Systemdesign-system is an Anthropic knowledge-work plugin skill for managing design systems through audit, document, and extend modes invoked as /design-system audit, document, or extend. It frames design tokens for colors, typography, spacing, borders, shadows, and motion, plus components with variants, states, sizes, behavior, and accessibility, and composite patterns for forms, navigation, data display, and feedback. Principles emphasize consistency over creativity, flexibility within constraints, documenting everything, and versioning with migration paths. Audit output templates score naming consistency, token coverage with hardcoded value counts, component completeness, and priority actions. Document mode produces variant tables, props, states, accessibility notes, do and don't guidance, and code examples. Extend mode captures problem statements, related components, proposed API props, tokens used, and open questions for design review. Optional connector hooks pull Figma component properties when a design tool is connected and publish docs to a knowledge base when available. Tips recommend starting with audit, documenting while building, and prioritizing broad coverage over perfect.2.8kinstalls37Interview PrepThe interview-prep skill produces structured hiring interview kits to evaluate candidates consistently and fairly across a full panel loop. Design principles require structured same-question interviews, competency-based mapping, behavioral and situational evidence, diverse panel perspectives, and rubric scoring instead of gut feel. Components include four to six role competencies, a per-competency question bank with behavioral tell-me-about-a-time prompts, situational how-would-you-handle questions, follow-up probes, a one-to-four scorecard with level descriptions, and a debrief template for panel decisions. Triggers include interview plan for, interview questions for, how should we interview, and scorecard for phrasing when users prepare to interview candidates. Output is a complete kit covering who interviews which competency, the shared question bank, scoring rubric, and debrief format. It focuses on planning and fairness artifacts rather than executing live interviews, ATS configuration, or offer negotiation workflows.2.8kinstalls38Research SynthesisThe research-synthesis skill distills user research inputs into actionable insights through a structured markdown report template. Accepted inputs include interview transcripts, survey CSVs, usability test notes, support tickets, NPS or CSAT responses, and app store reviews. Output sections cover executive summary, themed findings with prevalence counts and verbatim quotes, insights mapped to opportunities with impact and effort, identified user segments, prioritized recommendations, further research questions, and methodology notes separating observations from interpretations. Tips stress credible quotes, quantified prevalence like seven of ten instead of most users, and explicit limitations. When connectors are available it can pull supplemental user feedback, validate themes with product analytics, and publish to a knowledge base, referencing the user-research skill for methods and interview guides. The slash command format is /research-synthesis with arguments for pasted research data or file references.2.8kinstalls39Accessibility Reviewaccessibility-review runs WCAG 2.1 AA audits on designs or pages triggered by audit accessibility, check a11y, or pre-handoff review requests. Quick reference covers Perceivable rules including alt text, semantic structure, contrast ratios four point five to one for normal text and three to one for large text and UI components. Operable criteria include keyboard access, logical focus order, visible focus indicators, and forty-four pixel touch targets. Understandable checks cover predictable focus behavior, error identification, and input labels. Robust requirements demand name, role, and value for UI components. Testing approach combines automated scans, keyboard-only navigation, screen reader testing, contrast verification, and two hundred percent zoom layout checks. Output templates summarize critical, major, and minor findings by WCAG category with color contrast tables, keyboard navigation matrices, and prioritized fixes. Optional Figma connector integration inspects color values and touch targets directly from design files.2.8kinstalls40Brand Voice Enforcementbrand-voice-enforcement applies saved brand guidelines to sales and marketing content generation requests such as emails, proposals, pitch decks, LinkedIn posts, presentations, and Slack messages. It loads guidelines from session context first, then .claude/brand-voice-guidelines.md resolved relative to the user working folder, otherwise prompts users to run discover-brand or generate-guidelines or paste rules directly. Enforcement reads .claude/brand-voice.local.md for strictness and always-explain settings, analyzes content type, audience, and message pillars, applies constant voice attributes and approved terminology, then flexes tone using the guidelines matrix for formality, energy, and technical depth. Generated copy mirrors guideline examples, validates choices afterward, and explains tradeoffs when user requests conflict with brand rules. Open questions flagged during guideline generation surface when content touches unresolved positioning decisions, with delegation hooks to content-generation and quality-assurance agents for long-form or high-stakes pieces.2.7kinstalls41Review ContractThe review-contract skill analyzes agreements against an organization negotiation playbook, flagging deviations, suggesting redlines, and summarizing business impact. Workflow accepts PDF, DOCX, URL, or pasted text, gathers side, deadline, focus areas, and deal context, then loads legal.local.md playbook positions or falls back to generic commercial standards with clear disclosure. Clause-by-clause review covers limitation of liability, indemnification, IP, data protection, confidentiality, warranties, term, governing law, insurance, assignment, force majeure, and payment terms with detailed sub-guidance on caps, carveouts, DPA needs, and work-for-hire risks. Analysis reads the full contract first because clauses interact, then assesses holistic risk balance. Output is assistance not legal advice and must be reviewed by qualified counsel. If no playbook exists, the skill offers setup help or generic baseline review. Teams invoke it when preparing vendor negotiations, customer paper reviews, or prioritizing redlines before escalation to senior or outside counsel.2.6kinstalls42Seo AuditThe seo-audit skill produces actionable SEO health reports across keyword research, on-page analysis, content gaps, technical foundations, and competitor benchmarking. Inputs require a URL or topic plus audit type defaulting to full site audit, with optional target keywords and competitors discovered via web search when omitted. Process sections define primary and long-tail keyword opportunity scoring, page-level title meta heading and internal link checks, thin content and funnel gap identification, technical crawlability speed schema and Core Web Vitals signals, and head-to-head competitor keyword and SERP feature comparisons. Connected SEO or analytics tools auto-populate data when available; otherwise web search is used with a note to connect Ahrefs or Semrush MCP for precision. Output includes executive summary, keyword opportunity table with fifteen to twenty-five rows, on-page issues by severity, content gap recommendations, and prioritized quick wins versus strategic investments. Marketers invoke it via /seo-audit when assessing site health, finding keyword opportunities, or comparing competitor organic visibility.2.6kinstalls43Write SpecThe write-spec skill turns vague feature ideas into structured PRDs via /write-spec with conversational context gathering before generation. Inputs accept feature names, problem statements, user requests, or rough ideas. Context questions cover user problem, target segments, success metrics, constraints, and prior art without dumping all questions at once. Optional connected project tracker, knowledge base, and design tools pull related tickets, research, and mockups when available; otherwise the skill proceeds from user input only. Generated PRDs include problem statement, measurable goals, explicit non-goals, prioritized user stories by persona, Must Have Nice Have and Future requirements with acceptance criteria, leading and lagging success metrics, open questions tagged by owner, and timeline considerations. Review step offers section expansion and follow-up artifacts like design briefs or ticket breakdowns. Guidance embeds MoSCoW categorization and common user story mistake warnings. Product managers invoke it when scoping features, preventing scope creep, or translating customer asks into engineering-ready documents.2.6kinstalls44Legal ResponseThe legal-response skill drafts replies to common legal inquiries using configured templates in legal.local.md with mandatory escalation screening before any templated output. Supported types include data subject requests, discovery holds, vendor questions, NDA requests, privacy inquiries, subpoenas, insurance claims, and custom templates identified by aliases like dsr or hold. Universal escalation triggers block templated replies for litigation risk, regulator contact, binding commitments, criminal liability, media attention, unprecedented matters, or multi-jurisdiction conflicts. Category-specific triggers add rules for minors data, litigation holds on DSR data, competitor NDAs, and subpoenas that always require counsel review. Workflow loads templates, gathers recipient-specific details, customizes tone by audience and sensitivity, and presents drafts for human review before sending. Template creation guidance helps teams bootstrap missing categories. The skill assists workflows but is not legal advice; regulated communications need qualified professional review especially for subpoenas and government requests.2.6kinstalls45Validate DataThe validate-data skill reviews analyses for accuracy, methodology, and bias before stakeholder delivery via /validate-data. It accepts documents, notebooks, SQL with results, charts, or methodology descriptions. The workflow examines question framing, data selection, population definition, metric consistency, and fair baselines, then runs a pre-delivery QA checklist covering data quality, calculations, reasonableness, and presentation. It systematically checks join explosion, survivorship bias, incomplete period comparisons, denominator shifting, average-of-averages traps, timezone mismatches, and selection bias. Spot-checks recalculate key numbers, verify subtotals, and cross-validate against known benchmarks. Visualization review flags truncated axes, inconsistent scales, and misleading chart choices. Output rates overall assessment as Ready to share, Share with caveats, or Needs revision with severity-tagged issues, required caveats, and actionable improvements. Teams invoke it before executive presentations, quarterly reviews, or any high-stakes data narrative.2.5kinstalls46ReconciliationThe reconciliation skill assists account reconciliation workflows for finance teams comparing GL balances to subledgers, bank statements, or intercompany entries. It explicitly disclaims financial advice and requires qualified professional review before sign-off. GL to subledger reconciliation matches control accounts like AR, AP, fixed assets, inventory, prepaid, and accruals to detailed subledger balances, investigating manual journals, interface timing, and failed postings. Bank reconciliation walks from statement and GL cash balances through deposits in transit, outstanding checks, and unrecorded fees or interest to adjusted balances that must tie. Intercompany reconciliation compares entity pair receivables and payables, addressing FX differences, cut-off mismatches, and elimination entries. Reconciling items categorize into timing differences, adjustments required, or investigation needed with aging buckets at 0-30, 31-60, 61-90, and 90 plus days. Escalation thresholds examples cover amount and age triggers for supervisor and controller review. Best practices stress timeliness, documentation, segregation of duties, and root cause fixes for recurring items.2.5kinstalls47Daily BriefingDaily Sales Briefing produces a scannable two-minute prioritized action plan for sales days. Standalone mode works when users paste meetings, key deals, and priorities without any connectors. Supercharged mode auto-pulls calendar events with attendees, CRM pipeline alerts, priority emails, and enrichment signals when integrations exist. Output sections include number one priority, today's numbers table, meeting prep with context and suggested call-prep commands, pipeline alerts for stale or closing deals, email needs-response and waiting-on-reply tables, and three suggested actions. Priority ranking places urgent closing deals first, then high-value meetings, decision-maker emails, weekly closes, stale deals, and weekly tasks. Quick mode compresses to priority, meeting count, alerts, and do-now action. End-of-day mode summarizes completed meetings, pipeline changes, tomorrow focus, and open loops. Without connectors the skill asks for meetings, focused deals, and urgent context then works with whatever is provided. Related skills call-prep, call-follow-up, and account-research extend meeting depth.2.5kinstalls48Account ResearchThe account-research skill retrieves and synthesizes company intelligence from Common Room for sales and GTM workflows. Step zero loads the Me object to default queries to the user's own segments unless broader scope is requested. Four interaction patterns cover full overviews with structured briefings, targeted field questions with concise answers, sparse data honesty without speculation, and combined MCP data plus ICP reasoning. Account lookup searches by domain or name with exact match first and partial match confirmation. Field selection scales from all groups for overviews to targeted groups for specific questions like ownership, scores, contacts, or RoomieAI research. Sparse Pattern 3 triggers targeted thirty-day web search for funding, launches, or executive news only when Common Room data is thin. Output omits empty sections, returns scores as raw values or percentiles never labels, and requires every fact to trace to a tool call. Full briefings include snapshot, CRM, signals, top contacts, RoomieAI research, and signal-backed next steps readable in two to three minutes.2.5kinstalls49Draft OutreachThe draft-outreach skill always researches before drafting personalized outreach via web search by default, plus optional enrichment, CRM, and email connectors. Step one parses person, role, company, or email inputs. Step two runs research-prospect internally to find title, company context, recent news, and a personalization hook before any message text. Hook priority ranks trigger events, mutual connections, their content, company initiatives, then role-based pain points. Email drafts follow AIDA with plain text only, no markdown bold or asterisks, short paragraphs, and subjects under fifty characters. LinkedIn provides sub-three-hundred-character connection requests and value-first follow-ups. Optional connectors add verified emails, CRM relationship history, and inbox draft creation. Output includes research summary, email body, subject alternatives, LinkedIn backup, rationale table, draft status, and optional day three, seven, and fourteen follow-up sequence. Channel selection prefers verified email, falls back to LinkedIn, and suggests warm intros when possible.2.5kinstalls50Slack SearchThe slack-search skill guides effective Slack search for messages, files, channels, and people. Apply whenever locating Slack information or gathering context before answering questions about workspace activity. Tools include slack_search_public for public channels without consent, slack_search_public_and_private for private channels DMs and group DMs with user consent, slack_search_channels by name or description, and slack_search_users by name email or role. Strategy: start broad then narrow with in, from, and date filters; use natural language for fuzzy conceptual queries and keywords for exact content; break complex questions into multiple searches. Modifiers cover in channel, from user, is thread, has pin link file, before after on during dates, exact phrase quotes, minus exclusion, and wildcards. File search uses content_types files with type images documents pdfs spreadsheets or canvases. Follow up with slack_read_thread, slack_read_channel timestamps, and slack_read_user_profile. Pitfalls: boolean AND OR NOT unsupported, not real-time for last seconds, private search needs consent.2.5kinstalls51Risk AssessmentThe risk-assessment skill guides systematic identification, assessment, and mitigation planning for operational risks tied to projects, vendors, processes, or decisions. It opens with a likelihood-by-impact matrix that maps High, Medium, and Low combinations to Critical, High, Medium, or Low risk levels. Six risk categories cover operational, financial, compliance, strategic, reputational, and security concerns such as process failures, budget overruns, audit findings, market shifts, customer impact, and data breaches. For each risk the register captures description, likelihood, impact, derived risk level, mitigation actions, owner, and status values Open, Mitigated, Accepted, or Closed. Output is a prioritized risk register with specific, actionable mitigations focused on controllable and material risks. Triggers include phrases like risk assessment, risk register, what could go wrong, or when evaluating risks before a major decision. The workflow emphasizes structured documentation rather than ad hoc worry lists so teams can track ownership and mitigation progress over time.2.5kinstalls52Design HandoffThe design-handoff skill produces developer handoff documentation when a design is ready for engineering implementation. It accepts a Figma URL, screenshot, or written description and emits a structured spec with overview, layout, token tables, component variants and props, interaction states, responsive breakpoints, edge cases, motion details, and accessibility notes. Visual specs call for measurements, design token references instead of raw pixel values, and all component states including hover, loading, error, and empty. Interaction specs cover click behavior, transitions with duration and easing, and gestures. Principles stress specifying everything developers might otherwise guess, referencing tokens like spacing-md rather than fixed pixels, and explaining rationale for responsive choices. Optional connectors can pull exact Figma measurements or link tickets in a project tracker. Output follows a markdown template with tables for tokens, components, states, breakpoints, animations, and accessibility requirements for each screen.2.4kinstalls53Audit SupportThe audit-support skill guides SOX Section 404 internal controls over financial reporting work with scoping, risk assessment, design and operating effectiveness testing, and deficiency classification. It documents six-phase methodology from scoping significant accounts through reporting material weaknesses, including assertion mapping by account type and walkthrough versus sample-based operating tests. Sample selection covers random, targeted, haphazard, and systematic methods with frequency-based size tables for annual through per-transaction controls. Workpaper standards require control identification, test design, execution evidence, conclusions, and reviewer sign-off with explicit sufficient versus insufficient evidence rules. Deficiency guidance distinguishes deficiency, significant deficiency, and material weakness with aggregation analysis and remediation plans covering root cause, owner, timeline, and re-test validation. ITGC, manual, automated, IT-dependent manual, and entity-level control sections explain testing approaches including IPE validation for report-based reviews.2.4kinstalls54Competitive BriefThe competitive-brief skill researches competitors and delivers structured positioning and messaging comparisons with content gaps, opportunities, and threats for sales battlecards or rapid response analysis. Inputs include required competitor names plus optional company context and focus areas such as messaging, product comparison, content strategy, news, pricing, or market presence. Research spans competitor websites, blogs, social profiles, demos, webinars, press releases, job postings, review sites, analyst reports, news coverage, SEO signals, filings, and community sentiment with quarterly deep dives and monthly monitoring cadence guidance. Each competitor profile covers overview, messaging analysis, product positioning, content footprint, recent moves, and strengths versus weaknesses relative to your product. Synthesis sections highlight whitespace messaging angles, content gaps, threat assessment when rivals launch features, and recommended responses. Output templates support executive summaries, battlecard bullets, and follow-up research queues. CONNECTORS.md is referenced when tool availability is unclear for automated research steps.2.4kinstalls55Process OptimizationThe process-optimization skill improves inefficient business workflows using a four-step analysis framework triggered by phrases like slow process, too many steps, or bottleneck complaints. Step one maps the current state with every step, decision point, handoff, owner, and duration including manual work and approval waits. Step two identifies waste categories: waiting queues, rework loops, failure-prone handoffs, over-processing, and automatable manual tasks. Step three designs a future state that eliminates unnecessary steps, automates where practical, reduces handoffs, parallelizes independent work, and replaces heavy gates with checkpoints. Step four estimates impact via time saved per cycle, error rate reduction, cost savings, and employee satisfaction gains. Output is a before-and-after process comparison with specific recommendations, estimated impact, and an implementation plan. The skill targets operational workflows rather than code architecture, making it suitable for internal ops, support, and cross-team handoff improvements.2.4kinstalls56Campaign PlanThe campaign-plan skill produces comprehensive marketing campaign briefs from user inputs on goal, audience, timeline, optional budget, and additional product context. Output sections include campaign overview with SMART objectives, target audience segments and pain points, key messages with proof points, channel strategy across owned earned and paid media, week-by-week content calendar table, content asset list with priorities, success metrics with tracking methods, optional budget allocation, risks and mitigations, and next steps with approvals. Planning reference embeds the Objective Audience Message Channel Measure framework with SMART examples, audience profile templates, message hierarchy, and channel selection tables for owned and earned media. It gathers missing inputs before proceeding and can reference product analytics when connected for benchmark-informed targets. Triggered by /campaign-plan or requests to plan launches, lead-gen pushes, or awareness campaigns. Optional budget input shapes channel allocation recommendations when provided.2.4kinstalls57Compliance CheckThe compliance-check skill assesses proposed actions, product features, marketing campaigns, or business initiatives for regulatory implications. It disclaims legal advice and recommends professional review. Output includes summary verdict Proceed, Proceed with conditions, or Requires further review, plus tables for applicable regulations, requirement status, risk areas with severity and mitigation, recommended actions, approvals needed, and areas needing outside counsel. Embedded privacy overviews cover GDPR lawful basis, data subject rights, DPIAs, breach notification, and international transfers, plus CCPA and CPRA consumer rights and response timelines. A DPA review checklist walks Article 28 processor obligations, sub-processor rules, audit rights, and breach notification clauses. Additional regulation monitor table spans LGPD, POPIA, PIPEDA, PDPA, Privacy Act, PIPL, and UK GDPR. Users describe initiatives such as referral programs, biometric auth, cross-border data moves, or testimonial ads to trigger structured review.2.4kinstalls58Data Context ExtractorThe data-context-extractor meta-skill generates tailored data analysis skills from company-specific warehouse knowledge. Bootstrap mode connects to BigQuery, Snowflake, PostgreSQL, Redshift, or Databricks, explores schemas, asks analysts about entity disambiguation, primary identifiers, key metrics, standard filters, and common gotchas, then packages SKILL.md plus reference files for entities, metrics, and domain tables. Iteration mode loads an existing skill, identifies gaps such as new domains or failing queries, runs targeted discovery, and appends reference files before repackaging. It enforces reference standards covering table location, keys, relationships, sample queries, metric formulas, and entity definitions. A quality checklist verifies frontmatter, terminology, exclusions, dialect-correct SQL, and navigation links. The skill uses warehouse MCP tools for schema discovery and produces zip-deliverable skills analysts can reuse so Claude understands their metrics and query patterns. Analysts receive a zip-deliverable skill reusable across sessions.2.3kinstalls59Performance ReviewIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Generate performance review templates and help structure feedback performance review self assessment Generate self assessment template performance review manager employee Manager review template for a specific person performance review calibration Calibration prep document If no mode is specified ask what type of review they need The performance review skill documents workflows prerequisites and usage patterns grounded in its repository SKILL md Agents should follow the documented steps respect safety and permission notes and cite only capabilities described in the source It triggers on phrases matching the skill description and integrates with the agent toolchain for the tasks outlined in the documentation2.3kinstalls60Customer ResearchThe customer-research skill performs multi-source research on customer questions, issue investigations, account context, or support topics with attribution and confidence scoring. Workflow parses request type, searches tiered sources from official internal docs and knowledge base through CRM, support tickets, chat, email, web, and inferred analogies, then synthesizes a brief with answer, confidence level, key findings by source, context and nuance, gaps, and recommended next steps. Insufficient sources trigger transparent web research and user prompts for internal docs or SMEs. Customer-facing work flags roadmap, pricing, legal, or security topics for review and offers to draft responses. Knowledge capture suggests saving findings to knowledge base or FAQ after completion. Confidence tiers rank official docs highest and inference lowest, with explicit handling when sources contradict. Escalation guidance distinguishes answer directly, answer with caveats, and escalate to SMEs.2.3kinstalls61Variance AnalysisImportant This skill assists with variance analysis workflows but does not provide financial advice All analyses should be reviewed by qualified financial professionals before use in reporting Techniques for decomposing variances materiality thresholds narrative generation waterfall chart methodology and budget vs actual vs forecast comparisons The most fundamental variance decomposition Used for revenue cost of goods and any metric that can be expressed as Price x Volume Formula Total Variance Actual Budget or Prior Volume Effect Actual Volume Budget Volume x Budget Price Price Effect Actual Price Budget Price x Actual Volume Mix Effect Residual interaction term or allocated proportionally The variance analysis agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.3kinstalls62Brand ReviewIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Review marketing content against brand voice style guidelines and messaging standards Flag deviations and provide specific improvement suggestions User runs brand review or asks to review check or audit content against brand guidelines 1 Content to review accept content in any of these forms Pasted directly into the conversation A file path or knowledge base reference e g Notion page shared doc A URL to a published page Multiple pieces for batch review 2 Brand guidelines source determined automatically If a brand style guide is configured in local settings use it automatically If not configured ask Do you have a brand style guide or voice guidelines I should review against You can paste them share a file or describe your brand voice Otherwise I ll do a general review for clarity consistency and professionalism2.3kinstalls63Roadmap UpdateIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Update create or reprioritize a product roadmap If project tracker is connected Pull current roadmap items with their statuses assignees and dates Identify items that are overdue at risk or recently completed Surface any items without clear owners or dates If no project management tool is connected Ask the user to describe their current roadmap or paste upload it Accept any format list table spreadsheet screenshot or prose description Add item New feature initiative or work item to the roadmap Gather name description priority estimated effort target timeframe owner dependencies Suggest where it fits based on current priorities and capacity The roadmap update agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in2.3kinstalls64Ticket TriageIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Categorize prioritize and route an incoming support ticket or customer issue Produces a structured triage assessment with a suggested initial response ticket triage ticket text customer message or issue description Examples ticket triage Customer says their dashboard has been showing a blank page since this morning ticket triage I was charged twice for my subscription this month ticket triage User can t connect their SSO getting a 403 error on the callback URL ticket triage Feature request they want to export reports as PDF Core problem What is the customer actually experiencing Symptoms What specific behavior or error are they seeing Customer context Who is this Any account details plan level or history available Urgency signals Are they blocked Is this production How many users affected Emotional state Frustrated confused matter of fact escalating2.3kinstalls65Call PrepProduce a complete scannable call prep brief by combining account research contact research and signal synthesis from Common Room Step 1 Identify the Account and Attendees Parse what the user has provided Company name required look up the account in Common Room Attendee names optional if provided research each one Calendar lookup If a calendar connector is available search for upcoming meetings with the named company to automatically surface attendee names meeting time and any meeting notes or agenda Use this to fill gaps the user didn t provide If neither attendees nor a calendar match can be found ask Who will be on the call from Company I can research each attendee to make your prep more useful The call prep agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described2.2kinstalls66Meeting BriefingYou are a meeting preparation assistant for an in house legal team You gather context from connected sources prepare structured briefings for meetings with legal relevance and help track action items that arise from meetings Important You assist with legal workflows but do not provide legal advice Meeting briefings should be reviewed for accuracy and completeness before use Determine the meeting context from the user s request or calendar Meeting title and type What kind of meeting is this deal review board meeting vendor call team sync client meeting regulatory discussion Participants Who will be attending What are their roles and interests Agenda Is there a formal agenda What topics will be covered Your role What is the legal team member s role in this meeting advisor presenter observer negotiator Preparation time How much time is available to prepare Based on the meeting type determine what preparation is needed Meeting Type Key Prep Needs Deal Review Contract status open issues counterparty history negotiation strategy approval requirements Board Committee Legal updates2.2kinstalls67Sprint PlanningIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Plan a sprint by scoping work estimating capacity and setting clear goals SPRINT PLANNING STANDALONE always works Define sprint goals and success criteria Estimate team capacity accounting for PTO meetings Scope and prioritize backlog items Identify dependencies and risks Generate sprint plan document SUPERCHARGED when you connect your tools Project tracker Pull backlog create sprint assign items Calendar Account for PTO and meetings in capacity Chat Share sprint plan with the team Team Who s on the team and their availability this sprint Sprint length How many days weeks Backlog What s prioritized Pull from tracker paste or describe Carryover Anything unfinished from last sprint Dependencies Anything blocked on other teams markdown Sprint Plan Sprint Name Dates Start End Team X engineers Sprint Goal One clear sentence about what success looks like2.2kinstalls68RunbookIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Create a step by step operational runbook for a recurring task or procedure markdown Runbook Task Name Owner Team Person Frequency Daily Weekly Monthly As Needed Last Updated Date Last Run Date Purpose What this runbook accomplishes and when to use it Prerequisites Access or permission needed Tool or system required Data or input needed The runbook agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.2kinstalls69Synthesize ResearchIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Synthesize user research from multiple sources into structured insights and recommendations Accept research from any combination of Pasted text Interview notes transcripts survey responses feedback Uploaded files Research documents spreadsheets recordings summaries knowledge base if connected Search for research documents interview notes survey results user feedback if connected Pull recent support tickets feature requests bug reports product analytics if connected Pull usage data funnel metrics behavioral data meeting transcription if connected Pull interview recordings meeting summaries and discussion notes Ask the user what they have What type of research interviews surveys usability tests analytics support tickets sales call notes How many sources participants Is there a specific question or hypothesis they are investigating What decisions will this research inform For each source extract Key observations What did users say do or experience Quotes Verbatim quotes that illustrate important points Behaviors What users actually did vs what they said they do Pain points2.2kinstalls70Close ManagementImportant This skill assists with close management workflows but does not provide financial advice All close activities should be reviewed by qualified financial professionals Month end close checklist task sequencing and dependencies status tracking and common close activities organized by day Pre Close Last 2 3 Business Days of the Month Send close calendar and deadline reminders to all contributors Confirm cut off procedures with AP AR payroll and treasury Verify all sub systems are processing normally ERP payroll banking Complete preliminary bank reconciliation all but last day activity Review open purchase orders for potential accrual needs Confirm payroll processing schedule aligns with close timeline Collect information for any known unusual transactions Close Day 1 T 1 First Business Day After Month End The close management agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs2.2kinstalls71Create An AssetGenerate custom sales assets tailored to your prospect audience and goals Supports interactive landing pages presentation decks executive one pagers and workflow architecture demos Invoke this skill when User says create an asset or create an asset CompanyName User asks to create an asset build a demo make a landing page mock up a workflow User needs a customer facing deliverable for a sales conversation This skill creates professional sales assets by gathering context about a The Prospect company contacts conversations pain points b The Audience who s viewing what they care about c The Purpose goal of the asset desired next action d The Format landing page deck one pager or workflow demo The skill then researches structures and builds a polished branded asset ready to share with customers Phase 0 Context Detection Input Collection2.2kinstalls72Compliance TrackingHelp track compliance requirements prepare for audits and maintain regulatory readiness Framework Focus Key Requirements SOC 2 Service organizations Security availability processing integrity confidentiality privacy ISO 27001 Information security Risk assessment security controls continuous improvement GDPR Data privacy EU Consent data rights breach notification DPO HIPAA Healthcare data US PHI protection access controls audit trails PCI DSS Payment card data Encryption access control vulnerability management Control Inventory Map controls to framework requirements Document control owners and evidence Track control effectiveness Audit Calendar Upcoming audit dates and deadlines Evidence collection timelines Remediation deadlines Evidence Management What evidence is needed for each control Where evidence is stored When evidence was last collected The compliance tracking agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure.2.2kinstalls73Write QueryIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Write a SQL query from a natural language description optimized for your specific SQL dialect and following best practices write query description of what data you need Parse the user s description to identify Output columns What fields should the result include Filters What conditions limit the data time ranges segments statuses Aggregations Are there GROUP BY operations counts sums averages Joins Does this require combining multiple tables Ordering How should results be sorted Limits Is there a top N or sample requirement The write query agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.2kinstalls74Journal Entry PrepImportant This skill assists with journal entry workflows but does not provide financial advice All entries should be reviewed by qualified financial professionals before posting Best practices standard entry types documentation requirements and review workflows for journal entry preparation Standard Accrual Types and Their Entries Accrue for goods or services received but not yet invoiced at period end Typical entry Debit Expense account or capitalize if asset qualifying Credit Accrued liabilities The journal entry prep agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.2kinstalls75Discover BrandOrchestrate autonomous discovery of brand materials across enterprise platforms This skill coordinates the discover brand agent to search connected platforms Notion Confluence Google Drive Box Microsoft 365 Figma Gong Granola Slack triage sources and produce a structured discovery report with open questions Before starting briefly explain what s about to happen so the user knows what to expect 1 Search I ll search your connected platforms Notion Google Drive Slack etc for brand related materials style guides pitch decks templates transcripts and more 2 Analyze I ll categorize and rank what I find pull the best sources and produce a discovery report with what I found any conflicts and open questions 3 Generate guidelines Once you ve reviewed the report I can generate a structured brand voice guideline document from the results 4 Save Guidelines are saved to claude brand voice guidelines md in your working folder once you approve them Nothing is written until that step The search usually takes a few minutes depending on how many platforms are2.2kinstalls76Guideline GenerationGenerate comprehensive LLM ready brand voice guidelines from any combination of sources brand documents sales call transcripts discovery reports or direct user input Transform raw materials into structured enforceable guidelines with confidence scoring and open questions Accept any combination of Discovery report from the discover brand skill structured pre triaged Brand documents uploaded or from connected platforms PDF PPTX DOCX MD TXT Conversation transcripts from Gong Granola manual uploads or Notion meeting notes Direct user input about their brand voice and values When a discovery report is provided use it as the primary input sources are already triaged and ranked Supplement with additional analysis as needed Determine what the user has provided If no sources are available Check if a discovery report exists from a previous brand voice discover brand run Check claude brand voice local md for known brand material locations Suggest running discovery first brand voice discover brand For documents Delegate to the document analysis agent for heavy parsing Extract voice attributes messaging themes terminology tone guidance and2.2kinstalls77Recruiting PipelineHelp manage the recruiting pipeline from sourcing through offer acceptance Stage Description Key Actions Sourced Identified and reached out Personalized outreach Screen Phone video screen Evaluate basic fit Interview On site or panel interviews Structured evaluation Debrief Team decision Calibrate feedback Offer Extending offer Comp package negotiation Accepted Offer accepted Transition to onboarding Pipeline velocity Days per stage Conversion rates Stage to stage drop off Source effectiveness Which channels produce hires Offer acceptance rate Offers extended vs accepted Time to fill Days from req open to offer accepted Pull candidate data automatically update statuses and track pipeline metrics in real time The recruiting pipeline agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.2kinstalls78ForecastIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Generate a weighted sales forecast with risk analysis and commit recommendations FORECAST STANDALONE always works Upload CSV export from your CRM Or paste describe your pipeline deals Set your quota and timeline Get weighted forecast with stage probabilities Risk adjusted projections best likely worst case Commit vs upside breakdown Gap analysis and recommendations SUPERCHARGED when you connect your tools CRM Pull pipeline automatically real time data Historical win rates by stage segment deal size Activity signals for risk scoring Automatic refresh and tracking over time Option A Upload a CSV Export your pipeline from your CRM e g Salesforce HubSpot I need at minimum Deal Opportunity name Amount Stage Close date Helpful if you have Owner if team forecast Last activity date Created date Account name2.2kinstalls79Create Cowork PluginBuild a new plugin from scratch through guided conversation Walk the user through discovery planning design implementation and packaging delivering a ready to install plugin file at the end A plugin is a self contained directory that extends Claude s capabilities with skills agents hooks and MCP server integrations This skill encodes the full plugin architecture and a five phase workflow for creating one conversationally 1 Discovery understand what the user wants to build 2 Component Planning determine which component types are needed 3 Design Clarifying Questions specify each component in detail 4 Implementation create all plugin files 5 Review Package deliver the plugin file Nontechnical output Keep all user facing conversation in plain language Do not expose implementation details like file paths directory structures or schema fields unless the user asks Frame everything in terms of what the plugin will do plugin name claude plugin plugin json Required plugin manifest skills Skills subdirectories with SKILL md skill name SKILL md references agents Subagent definitions md files mcp json MCP2.2kinstalls80Status ReportIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Generate a polished status report for leadership or stakeholders See the risk assessment skill for risk matrix frameworks and severity definitions markdown Status Report Project Team Period Author Name Date Date Executive Summary 3 4 sentence overview what s on track what needs attention key wins Overall Status On Track At Risk Off Track The status report agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.2kinstalls81Compose OutreachGenerate three personalized outreach formats email call script and LinkedIn message grounded in Common Room signals for a specific company or contact Use Common Room MCP tools to find and retrieve data for the target company and or specific contact Pull Recent product activity and engagement signals Community activity posts questions reactions 3rd party intent signals job postings news funding Relationship history prior contact meetings email opens If the user specified a person run contact level research If only a company was given identify the best contact to target based on title engagement and role Step 2 Web Search for External Hooks If CR Signals Are Thin If CR returned strong signals recent activity engagement product usage those should drive personalization skip web search If CR signals are thin or the prospect has little CR activity run a web search for external hooks2.2kinstalls82Contact ResearchRetrieve a comprehensive contact profile from Common Room Supports lookup by email social handle or name company Returns enriched data including activity history Spark scores website visits and CRM fields Common Room supports multiple lookup methods use whichever the user has provided What the user gives Lookup method Email address Look up by email most reliable LinkedIn Twitter X or GitHub handle Look up by social handle specify handle type explicitly Name company Identity resolution by name org domain present matches if ambiguous Name only Search by name if multiple matches show a brief list and ask the user to confirm If no match is found respond Common Room doesn t have a record for this person Do not speculate or fabricate profile data Use the Common Room object catalog to see available field groups and their contents For full profiles request all groups For targeted questions request only what s relevant2.2kinstalls83Enrich LeadTurn any identifier into a full contact dossier The user provides identifying info via ARGUMENTS apollo enrich lead Tim Zheng at Apollo apollo enrich lead https www linkedin com in timzheng apollo enrich lead sarah stripe com apollo enrich lead Jane Smith VP Engineering Notion apollo enrich lead CEO of Figma From ARGUMENTS extract every identifier available First name last name Company name or domain LinkedIn URL Email address Job title use as a matching hint If the input is ambiguous e g just CEO of Figma first use mcp__claude_ai_Apollo_MCP__apollo_mixed_people_api_search with relevant title and domain filters to identify the person then proceed to enrichment Credit warning Tell the user enrichment consumes 1 Apollo credit before calling The enrich lead agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository2.2kinstalls84Org PlanningHelp plan organizational structure headcount and team design Headcount How many people do we need in what roles by when Structure Reporting lines span of control team boundaries Sequencing Which hires are most critical What s the right order Budget Headcount cost modeling and trade offs Metric Healthy Range Warning Sign Span of control 5 8 direct reports 3 or 12 Management layers 4 6 for 500 people Too many slow decisions IC to manager ratio 6 1 to 10 1 4 1 top heavy Team size 5 9 people 4 lonely 12 hard to manage Produce org charts text based headcount plans with cost modeling and sequenced hiring roadmaps Flag structural issues like single points of failure or excessive management overhead The org planning agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and2.2kinstalls85Cowork Plugin CustomizerCustomize a plugin for a specific organization either by setting up a generic plugin template for the first time or by tweaking and refining an already configured plugin Finding the plugin To find the plugin s source files run find mnt local plugins mnt plugins type d name plugin name to locate the plugin directory then read its files to understand its structure before making changes If you cannot find the plugin directory the user is likely running this conversation in a remote container Abort and let them know Customizing plugins is currently only available in the desktop app s Cowork mode After locating the plugin check for prefixed placeholders grep rn w path to plugin include md include json Default rule If placeholders exist default to Generic plugin setup unless the user explicitly asks to customize a specific part of the plugin 1 Generic plugin setup The plugin contains prefixed placeholders These are customization points in a template that need to be replaced with real values e g Jira2.2kinstalls86Performance ReportIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Generate a marketing performance report with key metrics trend analysis insights and optimization recommendations User runs performance report or asks for a marketing report performance analysis campaign results or metrics summary 1 Report type determine which type of report the user needs Campaign report performance of a specific campaign Channel report performance across a specific channel email social paid SEO etc Content performance how content pieces are performing Overall marketing report cross channel summary weekly monthly quarterly Custom user defined scope 2 Time period the reporting window last week last month last quarter custom date range The performance report agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.2kinstalls87Email SequenceIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Design and draft complete email sequences with full copy timing branching logic and performance benchmarks for any lifecycle or campaign use case User runs email sequence or asks to create design build or draft an email sequence drip campaign nurture flow or onboarding series Gather the following from the user If not provided ask before proceeding 1 Sequence type one of Onboarding Lead nurture Re engagement Product launch Event follow up Upgrade upsell Win back Educational drip The email sequence agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.2kinstalls88ProspectGo from an ICP description to a ranked enriched lead list in one shot The user describes their ideal customer via ARGUMENTS apollo prospect VP of Engineering at Series B SaaS companies in the US 200 1000 employees apollo prospect heads of marketing at e commerce companies in Europe apollo prospect CTOs at fintech startups 50 500 employees New York apollo prospect procurement managers at manufacturing companies with 1000 employees apollo prospect SDR leaders at companies using Salesforce and Outreach Extract structured filters from the natural language description in ARGUMENTS Company filters Industry vertical keywords q_organization_keyword_tags Employee count ranges organization_num_employees_ranges Company locations organization_locations Specific domains q_organization_domains_list Person filters Job titles person_titles Seniority levels person_seniorities Person locations person_locations The prospect agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for.2.1kinstalls89Metrics ReviewIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Review and analyze product metrics identify trends and surface actionable insights If product analytics is connected Pull key product metrics for the relevant time period Get comparison data previous period same period last year targets Pull segment breakdowns if available If no analytics tool is connected ask the user to provide The metrics and their values paste a table screenshot or describe Comparison data previous period targets Any context on recent changes launches incidents seasonality Ask the user What time period to review last week last month last quarter What metrics to focus on Or should we review the full product metrics suite Are there specific targets or goals to compare against Any known events that might explain changes launches outages marketing campaigns seasonality2.1kinstalls90Comp AnalysisIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Analyze compensation data for benchmarking band placement and planning Helps benchmark compensation against market data for hiring retention and equity planning Option A Single role analysis What should we pay a Senior Software Engineer in SF Option B Upload comp data Upload a CSV or paste your comp bands I ll analyze placement identify outliers and compare to market Option C Equity modeling Model a refresh grant of 10K shares over 4 years at a 50 stock price The comp analysis agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.1kinstalls91Customer EscalationIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Package a support issue into a structured escalation brief for engineering product or leadership Gathers context structures reproduction steps assesses business impact and identifies the right escalation target customer escalation issue description customer name or account Examples customer escalation API returning 500 errors intermittently for Acme Corp customer escalation Data export is missing rows 3 customers reported this week customer escalation SSO login loop affecting all Enterprise customers customer escalation Customer threatening to churn over missing audit log feature What s broken or needed The core technical or product issue Who s affected Specific customer s segment or all users How long When did this start How long has the customer been waiting What s been tried Any troubleshooting or workarounds attempted Why escalate now What makes this need attention beyond normal support2.1kinstalls92Draft ContentIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Generate marketing content drafts tailored to a specific content type audience and brand voice User runs draft content or asks to draft write or create marketing content Gather the following from the user If not provided ask before proceeding 1 Content type one of Blog post Social media post specify platform LinkedIn Twitter X Instagram Facebook Email newsletter Landing page copy Press release Case study The draft content agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.1kinstalls93Stakeholder UpdateIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Generate a stakeholder update tailored to the audience and cadence Ask the user what kind of update Weekly Regular cadence update on progress blockers and next steps Monthly Higher level summary with trends milestones and strategic alignment Launch Announcement of a feature or product launch with details and impact Ad hoc One off update for a specific situation escalation pivot major decision Ask who the update is for Executives leadership High level outcome focused strategic framing brief Engineering team Technical detail implementation context blockers decisions needed Cross functional partners Context appropriate detail focus on shared goals and dependencies Customers external Benefits focused clear timelines no internal jargon Board Metrics driven strategic risk focused very concise If project tracker is connected Pull status of roadmap items and milestones Identify completed items since last update Surface items that are at risk or blocked Pull sprint or iteration progress2.1kinstalls94Change RequestIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Create a structured change request with impact analysis risk assessment and rollback plan Apply the assess plan execute sustain framework when building the request 1 Assess What is changing Who is affected How significant is the change Low Medium High What resistance should we expect 2 Plan Communication plan who what when how Training plan what skills are needed how to deliver Support plan help desk champions FAQs Timeline with milestones The change request agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.1kinstalls95Policy LookupIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Look up and explain company policies in plain language Answer employee questions about policies benefits and procedures by searching connected knowledge bases or using provided handbook content POLICY LOOKUP STANDALONE always works Ask any policy question in plain language Paste your employee handbook and I ll search it Get clear jargon free answers SUPERCHARGED when you connect your tools Knowledge base Search handbook and policy docs automatically HRIS Pull employee specific details PTO balance benefits PTO and Leave Vacation sick leave parental leave bereavement sabbatical Benefits Health insurance dental vision 401k HSA FSA wellness Compensation Pay schedule bonus timing equity vesting expense reimbursement Remote Work WFH policy remote locations equipment stipend coworking Travel Booking policy per diem expense reporting approval process Conduct Code of conduct harassment policy conflicts of interest Growth Professional development budget conference policy tuition reimbursement 1 Search knowledge base for the relevant policy document 2 Provide a clear plain2.1kinstalls96Process DocIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Document a business process as a complete standard operating procedure SOP Walk me through the process describe it paste existing docs or just tell me the name and I ll ask the right questions I ll produce a complete SOP markdown Process Document Process Name Owner Person Team Last Updated Date Review Cadence Quarterly Annually Purpose Why this process exists and what it accomplishes The process doc agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.1kinstalls97Call SummaryIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Process call notes or a transcript to extract action items draft follow up communications and update records call summary notes or transcript CALL SUMMARY STANDALONE always works Paste call notes or transcript Extract key discussion points and decisions Identify action items with owners and due dates Surface objections concerns and open questions Draft customer facing follow up email Generate internal summary for your team SUPERCHARGED when you connect your tools Transcripts Pull recording automatically e g Gong Fireflies CRM Update opportunity log activity create tasks Email Send follow up directly from draft Calendar Link to meeting pull attendee context Option 1 Paste your notes Just paste whatever you have bullet points rough notes stream of consciousness I ll structure it2.1kinstalls98Vendor Checkvendor check Vendor Agreement Status If you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Check the status of existing agreements with a vendor across all connected systems Provides a consolidated view of the legal relationship Important This command assists with legal workflows but does not provide legal advice Agreement status reports should be verified against original documents by qualified legal professionals If no vendor name is provided prompt the user to specify which vendor to check The vendor check agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.1kinstalls99BriefIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Generate contextual briefings for legal work Supports three modes daily brief topic brief and incident brief Important This command assists with legal workflows but does not provide legal advice Briefings should be reviewed by qualified legal professionals before being relied upon brief daily Morning brief of legal relevant items brief topic query Research brief on a specific legal question brief incident topic Rapid brief on a developing situation If no mode is specified ask the user which type of brief they need The brief agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.1kinstalls100Kb ArticleIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Draft a publish ready knowledge base article from a resolved support issue common question or documented workaround Structures the content for searchability and self service kb article resolved issue ticket reference or topic description Examples kb article How to configure SSO with Okta resolved this for 3 customers last month kb article Ticket 4521 customer couldn t export data over 10k rows kb article Common question how to set up webhook notifications kb article Known issue dashboard charts not loading on Safari 16 What was the problem The original issue question or error What was the solution The resolution workaround or answer Who does this affect User type plan level or configuration How common is this One off or recurring issue What article type fits best How to troubleshooting FAQ known issue or reference see article types below2.1kinstalls101Vendor ReviewIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Evaluate a vendor with structured analysis covering cost risk performance and fit Vendor name Who are you evaluating Context New vendor evaluation renewal decision or comparison Details Contract terms pricing proposal document or current performance data Cost Analysis Total Cost of Ownership Total cost of ownership not just license fees Implementation and migration costs Training and onboarding costs Ongoing support and maintenance Exit costs data migration contract termination Risk Assessment Vendor financial stability Security and compliance posture Concentration risk single vendor dependency Contract lock in and exit terms Business continuity and disaster recovery The vendor review agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.1kinstalls102Capacity PlanIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Analyze team capacity and plan resource allocation Team size and roles Who do you have Current workload What are they working on Upload from project tracker or describe Upcoming work What s coming next quarter Constraints Budget hiring timeline skill requirements People Available headcount and skills Current allocation and utilization Planned hires and timeline Contractor and vendor capacity Budget Operating budget by category Project specific budgets Variance tracking Forecast vs actual The capacity plan agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.1kinstalls103Weekly Prep BriefGenerate a single comprehensive weekly briefing that covers every external customer or prospect call in the next 7 days with per meeting account and contact research from Common Room Step 1 Get the Week s External Meetings Option A Calendar connected Use the calendar connector to fetch all meetings scheduled in the next 7 days or a user specified range Filter to keep only external meetings those with attendees from outside your organization Discard internal only meetings one on ones with colleagues and recurring internal syncs Identify for each external meeting Company name Meeting date and time External attendee names and email addresses Option B No calendar connected Ask the user To build your weekly prep brief I ll need your upcoming external calls Please list them company name date time and attendee names2.1kinstalls104OnboardingIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Generate a comprehensive onboarding plan for a new team member New hire name Who s starting Role What position Team Which team are they joining Start date When do they start Manager Who s their manager markdown Onboarding Plan Name Role Start Date Date Team Team Manager Manager Pre Start Before Day 1 Send welcome email with start date time and logistics Set up accounts email Slack tools for role Order equipment laptop monitor peripherals Add to team calendar and recurring meetings Assign onboarding buddy Suggested person Prepare desk remote setup instructions The onboarding agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.1kinstalls105DigestIf you see unfamiliar placeholders or need to check which tools are connected see CONNECTORS md CONNECTORS md Scan recent activity across all connected sources and generate a structured digest highlighting what matters Determine the time window from the user s input daily Last 24 hours default if no flag specified weekly Last 7 days The user may also specify a custom range since yesterday since Monday since 2025 01 20 The digest agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the tasks inputs outputs and failure modes described in the repository documentation2.1kinstalls106Pipeline ReviewThe pipeline-review skill analyzes sales pipeline health for weekly deal prioritization and risk flagging. It works standalone with CSV uploads, pasted deal lists, or natural-language pipeline descriptions, then supercharges when CRM and calendar connectors pull live data. Health checks identify stale, stuck, and at-risk opportunities while hygiene audits catch bad close dates, missing fields, and single-threaded deals. Prioritization ranks deals by impact and closability to produce a weekly action plan developers and revenue teams can execute. Expected inputs include deal name, amount, stage, close date, last activity, and owner fields from Salesforce or HubSpot exports. Output sections cover pipeline summary, top priorities, deals needing attention, hygiene issues, and recommended next actions. The skill accepts an optional segment or rep argument for team reviews. Use when running a weekly pipeline review, deciding which deals to focus on, spotting stuck opportunities, or auditing CRM hygiene before quarter close.2kinstalls107Sequence LoadFind enrich and load contacts into an outreach sequence end to end The user provides targeting criteria and a sequence name via ARGUMENTS apollo sequence load add 20 VP Sales at SaaS companies to my Q1 Outbound sequence apollo sequence load SDR managers at fintech startups Cold Outreach v2 apollo sequence load list sequences shows all available sequences apollo sequence load directors of engineering 500 employees US Demo Follow up apollo sequence load reload 15 more leads into Enterprise Pipeline Targeting criteria Job titles person_titles Seniority levels person_seniorities Industry keywords q_organization_keyword_tags Company size organization_num_employees_ranges Locations person_locations or organization_locations Sequence info Sequence name text after to into or Volume how many contacts to add default 10 if not specified If the user just says list sequences skip to Step 2 and show all available sequences2kinstalls108Journal EntryThe journal-entry skill assists with month-end and period-close journal entry workflows for ap-accrual, fixed-assets, prepaid, payroll, and revenue types with proper debits, credits, supporting detail, and review documentation. Usage is slash je type period such as ap-accrual 2024-12. Workflow gathers trial balance and subledger data from connected ERP or pasted spreadsheets, calculates entries by type with account coding and department splits, presents standard formatted journal tables with memo lines, and runs an eleven-point review checklist covering balance, period, valid accounts, reversals, and approval authority. AP accrual debits expense and credits accrued liabilities for uninvoiced receipts. Fixed assets pulls depreciation schedules debiting expense and crediting accumulated depreciation. Prepaid amortizes insurance software and rent. Payroll accrues salaries benefits and taxes. Revenue recognizes performance obligations and adjusts deferred revenue. Disclaimer notes assistance only, not financial advice, requiring qualified professional review before posting.2kinstalls109Triage NdaThe triage-nda skill. Rapidly triage an incoming NDA and classify it as GREEN (standard approval), YELLOW (counsel review), or RED (full legal review). Use when a new NDA arrives from sales or business development, when screening for embedded non-solicits, non-competes, or missing carveouts, or when deciding whether an NDA can be signed under standard delegation. Triage the NDA: @$1 Rapidly triage incoming NDAs against standard screening criteria. Classify the NDA for routing: standard approval, counsel review, or full legal review. **Important**: You assist with legal workflows but do not provide legal advice. All analysis should be reviewed by qualified legal professionals before being relied upon. The NDA playbook should define: - Mutual vs. Agreement Structure - [ ] **Type identified**: Mutual NDA, Unilateral (disclosing party), or Unilateral (receiving party) - [ ] **Appropriate for context**: Is the NDA type appropriate for the business relationship?.2kinstalls110People ReportThe people-report skill. Generate headcount, attrition, diversity, or org health reports. Use when pulling a headcount snapshot for leadership, analyzing turnover trends by team, preparing diversity representation metrics, or assessing span of control and flight risk across the org. Generate people analytics reports from your HR data. Analyze workforce data to surface trends, risks, and opportunities. Understand what question they're trying to answer 2. Identify the right data (upload, paste, or pull from ~~HRIS) 3. Analyze with appropriate statistical methods 4. Present findings with context and caveats 5. The workflow follows the source SKILL.md contract with progressive reference loading, clear trigger phrases, and practical steps developers can apply directly in agent sessions. The workflow follows the source SKILL.md contract with progressive reference loading, clear trigger phrases, and practical steps developers can apply directly in agent sessions.2kinstalls111Draft ResponseThe draft-response skill. Draft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or outage, delivering bad news like a delay or won't-fix, declining a feature request, or replying to a billing issue. Draft a professional, customer-facing response tailored to the situation, customer relationship, and communication context. Understand the Context Parse the user's input to determine: - **Customer**: Who is the communication for?. Look up account context if available. - **Situation type**: Question, issue, escalation, announcement, negotiation, bad news, good news, follow-up - **Urgency**: Is this time-sensitive?. How long has the customer been waiting?. - **Channel**: Email, support ticket, chat, or other (adjust formality accordingly) - **Relationship stage**: New customer, established, frustrated/escalated - **Stakeholder level**: End user, manager, executive, technical, business ### 2. The workflow follows the source SKILL.md contract with progressive reference loading, clear trigger phrases, and practical steps developers can apply directly in agent sessions.2kinstalls112Draft OfferThe draft-offer skill. Draft an offer letter with comp details and terms. Use when a candidate is ready for an offer, assembling a total comp package (base, equity, signing bonus), writing the offer letter text itself, or prepping negotiation guidance for the hiring manager. Draft a complete offer letter for a new hire. - **Level**: Junior, Mid, Senior, Staff, etc. - **Location**: Where will they be based?. (affects comp and benefits) - **Compensation**: Base salary, equity, signing bonus (if applicable) - **Start date**: When should they start?. - **Hiring manager**: Who will they report to?. If you don't have all details, I'll help you think through them. The workflow follows the source SKILL.md contract with progressive reference loading, clear trigger phrases, and practical steps developers can apply directly in agent sessions. The workflow follows the source SKILL.md contract with progressive reference loading, clear trigger phrases, and practical steps developers can apply directly in agent sessions.2kinstalls113Signature RequestPrepare and route a document for e-signature - run a pre-signature checklist, configure signing order, and send for execution. Use when a contract is finalized and ready to sign, when verifying entity names, exhibits, and signature blocks before sending, or when setting up an envelope with sequential or parallel signers. --- name: signature-request description: Prepare and route a document for e-signature - run a pre-signature checklist, configure signing order, and send for execution. Use when a contract is finalized and ready to sign, when verifying entity names, exhibits, and signature blocks before sending, or when setting up an envelope with sequential or parallel signers. argument-hint: "<document or contract to send>" --- # /signature-request -- E-Signature Routing > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). Prepare a document for electronic signature - verify completeness, set signing order, and route for execution.2kinstalls114Sox TestingThe sox-testing skill. Generate SOX sample selections, testing workpapers, and control assessments. Use when planning quarterly or annual SOX 404 testing, pulling a sample for a control (revenue, P2P, ITGC, close), building a testing workpaper template, or evaluating and classifying a control deficiency. **Important**: This command assists with SOX compliance workflows but does not provide audit or legal advice. All testing workpapers and assessments should be reviewed by qualified financial professionals before use in audit documentation. Generate sample selections, create testing workpapers, document control assessments, and provide testing templates for SOX 404 internal controls over financial reporting. Identify Controls to Test Based on the control area, identify the key controls. Create Testing Workpaper Generate a testing template for each control: ### 5. Document Control Assessment Classify any identified deficiencies: **Deficiency:** A control does not allow management or employees to prevent or detect misstatements on a timely basis.2kinstalls115Scientific Problem SelectionPorts Fischbach and Walsh's 'Problem choice and decision trees in science and engineering' (Cell, 2024, 187, 1828-1833) and Stanford's BIOE 395 course into a conversational Claude workflow for scientists deciding what to work on next. It opens with three entry points - pitch a new project idea, troubleshoot a stuck project, or ask a strategic question - then routes through nine sub-skills (intuition pumps, risk assessment, optimization function, parameter strategy, decision-tree navigation, adversity planning, problem inversion, integration, and a meta-framework), each backed by its own reference file and each producing a concrete 1-2 page document such as a Risk Assessment Matrix or Decision Tree Map. Built for graduate students choosing thesis projects, postdocs planning independent work, PIs setting lab direction, and startup founders at inception; its core bet is that problem choice matters more than execution quality, since scientists spend days choosing a problem and years solving it.1.8kinstalls116Single Cell Rna QcThe single-cell-rna-qc knowledge-work skill performs quality control on single-cell RNA-seq datasets in h5ad or h5 formats using scverse best practices. Workflows include MAD-based cell filtering, mitochondrial and gene count thresholds, doublet awareness, and comprehensive QC plots. Agents document filtering decisions and reproducible parameters. Use when users request scRNA QC, low-quality cell removal, or scanpy-aligned filtering pipelines. QC for h5ad and h5 single-cell RNA-seq inputs. MAD-based filtering with scverse best practices. Mitochondrial and gene count threshold guidance. Comprehensive QC visualizations. Reproducible scanpy-aligned parameters. Run single-cell RNA-seq QC on h5ad or h5 files with scverse MAD filtering and scanpy visualizations.1.7kinstalls117Nextflow DevelopmentThe nextflow development skill Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data - either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation. Documentation covers workflows, commands, and guardrails agents should follow when users invoke this capability. Key documented areas include [ ] Step 0: Acquire data (if from GEO/SRA); [ ] Step 1: Environment check (MUST pass); [ ] Step 2: Select pipeline (confirm with user); [ ] Step 3: Run test profile (MUST pass). Reference commands include - [ ] Step 0: Acquire data (if from GEO/SRA); - [ ] Step 1: Environment check (MUST pass). Use when developers or agents need structured guidance for nextflow development tasks with evidence grounded in the bundled SKILL.md rather than generic advice.1.7kinstalls118Scvi ToolsThe scvi tools skill Deep learning for single-cell analysis using scvi-tools. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome RNA+ATAC analysis with MultiVI, (5) spatial transcriptomics deconvolution with DestVI, (6) label transfer and reference mapping with scANVI/scArches, (7) RNA velocity with veloVI, or (8) any deep learning-based single-cell method. Triggers include mentions of scVI, scANVI, totalVI, PeakVI, MultiVI, DestVI, veloVI, sysVI, scArches, variational autoencoder, VAE, batch correction, data integration, multi-modal, CITE-seq, multiome, reference mapping, latent space. Documentation covers workflows, commands, and guardrails agents should follow when users invoke this capability. Key documented areas include Identify the appropriate workflow from the model/workflow tables below; Read the corresponding reference file for detailed steps and code; Use scripts in `scripts/` to avoid rewriting common code; For installation or GPU issues, consult `references/environment_setup.md`. Reference commands include python scripts/va.1.7kinstalls119Instrument Data To AllotropeThe instrument data to allotrope skill Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full ASM JSON, flattened CSV for easy import, and exportable Python code for data engineers. Common triggers include converting instrument files, standardizing lab data, preparing data for upload to LIMS/ELN systems, or generating parser code for production pipelines. Documentation covers workflows, commands, and guardrails agents should follow when users invoke this capability. Key documented areas include **Detect instrument type** from file contents (auto-detect or user-specified); **Parse file** using allotropy library (native) or flexible fallback parser; **Generate outputs**:; ASM JSON (full semantic structure). Reference commands include pip install allotropy pandas openpyxl pdfplumber --break-system-packages; from allotropy.parser_factory import Vendor. Use when developers or agents need structured guidance for instrument data.1.7kinstalls120Contract Reviewcontract-review is an agent skill from anthropics/knowledge-work-plugins that apply contract-review agent skill workflows from documented skill.md guidance. # Contract Review ## Quick start Attach a contract file, forward the email containing it, or paste the text directly. ``` User: "Review this MSA and flag anything I should push back on." → Skill reads the document, identifies parties and contract type, analyzes 8 risk categories, returns a severity-tiered summary with a negotiation playbook, Developers invoke contract-review during operate/infra work for cloud & infrastructure tasks. The skill documents triggers, prerequisites, and step-by-step workflows grounded in SKILL.md. Compatible with Claude Code, Cursor, and Codex agent runtimes that load marketplace skills. Review the Security Audits panel on this listing before installing in production environments. Category Cloud & Infrastructure with operations vertical focus supports repeatable agent-guided delivery.1.6kinstalls121Zoom McpThe zoom-mcp skill is designed for plan and troubleshoot Zoom MCP connectors for meetings, recordings, and transcripts. Zoom MCP Guidance for the bundled Zoom MCP connector in this Claude plugin. Prefer design-mcp-workflow or setup-zoom-mcp first, then route here for tool-surface details, auth expectations, and MCP-specific constraints. Invoke when the user plans Zoom MCP access to meetings, recordings, assets, or transcripts.1.5kinstalls122Design Mcp WorkflowThe design-mcp-workflow skill is designed for design Zoom MCP workflows separating MCP tool responsibilities from REST APIs. Design MCP Workflow Use this skill when the user wants Claude or another MCP-capable client to interact with Zoom via tool calls instead of only deterministic API code. Covers MCP fit assessment REST API vs MCP boundaries Hybrid architectures Connector expectations Whiteboard-specific MCP routing Workflow 1. Invoke when the user designs Zoom MCP workflows or separates MCP from REST responsibilities.1.5kinstalls123Build Zoom Rest Api AppThe build-zoom-rest-api-app skill is designed for reference skill for Zoom REST API. Use after choosing an API-based workflow when you need endpoint selection, resource-management patterns, OAuth requirements, rate-limit. /build-zoom-rest-api-app Background reference for deterministic server-side Zoom automation and resource management. Prefer plan-zoom-product, plan-zoom-integration, or debug-zoom first, then route here for endpoint-level detail. Invoke when the user asks about build zoom rest api app or related SKILL.md workflows.1.4kinstalls124ScribeThe scribe skill is designed for reference skill for Zoom AI Services Scribe. Use after routing to a transcription workflow when handling uploaded or stored media, Build-platform JWT auth, fast mode. If the user needs live meeting media without file-based upload/batch jobs, route to ../rtms/SKILL.md. If the user needs Zoom REST API inventory for AI Services paths, chain ../rest-api/SKILL.md. Invoke when the user asks about scribe or related SKILL.md workflows.1.4kinstalls125Plan Zoom ProductThe plan-zoom-product skill is designed for choose the right Zoom building surface for a use case and explain the tradeoffs clearly. Use when deciding between REST API, Webhooks, WebSockets, Meeting SDK, Video SDK, Zoom. /plan-zoom-product > If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md. Choose between Zoom REST API, Webhooks, WebSockets, Meeting SDK, Video SDK, Zoom Apps SDK, Phone, Contact Center, or MCP for a specific use case. Invoke when the user deciding between REST API, Webhooks, WebSockets, Meeting SDK, Video SDK, Zoom Apps SDK, Phone, Contact Center, or MCP for a specific product idea or integration goal.1.4kinstalls126Setup Zoom OauthThe setup-zoom-oauth skill is designed for implement Zoom authentication correctly. Use when setting up app credentials, choosing an OAuth grant, requesting scopes, handling token refresh, or debugging auth failures. /setup-zoom-oauth Use this skill when auth is the blocker or when auth choices will shape the entire integration. Scope App type selection OAuth grant selection Scope planning Token exchange and refresh Auth debugging and environment assumptions Workflow 1. Invoke when the user setting up app credentials, choosing an OAuth grant, requesting scopes, handling token refresh, or debugging auth failures.1.4kinstalls127Build Zoom Meeting Sdk AppThe build-zoom-meeting-sdk-app skill is designed for reference skill for Zoom Meeting SDK. Use after routing to a meeting-embed workflow when implementing real Zoom meeting joins, platform-specific SDK behavior, auth and join. /build-zoom-meeting-sdk-app Background reference for embedded Zoom meetings across web, mobile, desktop, and Linux bot environments. Prefer build-zoom-meeting-app or build-zoom-bot first, then route here for platform detail. Invoke when the user asks about build zoom meeting sdk app or related SKILL.md workflows.1.4kinstalls128Build Zoom Phone IntegrationThe build-zoom-phone-integration skill is designed for reference skill for Zoom Phone. Use after routing to a phone workflow when implementing OAuth, Phone APIs, webhooks, Smart Embed events, URI schemes, CRM or CTI dialers, or. /build-zoom-phone-integration Background reference for Zoom Phone integrations across API, webhook, Smart Embed, and URI-launch workflows. Implementation guidance for Zoom Phone integrations across API, webhook/event, Smart Embed, and URI-launch workflows. Invoke when the user asks about build zoom phone integration or related SKILL.md workflows.1.4kinstalls129Probe SdkThe probe-sdk skill is designed for reference skill for Zoom Probe SDK. Use after routing to a preflight workflow when testing browser compatibility, media permissions, audio or video diagnostics, and network. Zoom Probe SDK Background reference for preflight diagnostics on user devices and networks before meeting or session workflows. If user needs embedded meeting flows, route to ../meeting-sdk/SKILL.md. Invoke when the user asks about probe sdk or related SKILL.md workflows.1.4kinstalls130Build Zoom Meeting AppThe build-zoom-meeting-app skill is designed for build or embed a Zoom meeting flow. Use when implementing Meeting SDK joins, web or mobile meeting embeds, meeting lifecycle flows, or when deciding between Meeting SDK and. /build-zoom-meeting-app Use this skill for embedded meeting experiences and meeting lifecycle implementation. Covers Meeting SDK selection and platform routing Join/auth implementation planning Meeting creation plus join flow design Web vs native platform considerations Meeting SDK vs Video SDK boundary decisions Workflow 1. Invoke when the user implementing Meeting SDK joins, web or mobile meeting embeds, meeting lifecycle flows, or when deciding between Meeting SDK and Video SDK.1.4kinstalls131Rivet SdkThe rivet-sdk skill is designed for reference skill for Zoom Rivet SDK. Use after routing to a Rivet-based server workflow when implementing auth handling, webhook consumers, API wrappers, multi-module. Zoom Rivet SDK Background reference for Zoom Rivet as a JavaScript and TypeScript server framework for Zoom integrations. Rivet is recommended for faster server-side scaffolding, but it is not mandatory. Invoke when the user asks about rivet sdk or related SKILL.md workflows.1.4kinstalls132Zoom OauthThe zoom-oauth skill is designed for reference skill for Zoom authentication. Use after routing to an auth workflow when choosing app credentials, grant types, scopes, token refresh behavior, or debugging Zoom. Zoom OAuth Background reference for Zoom auth and token lifecycle behavior. Prefer setup-zoom-oauth first, then use this skill for the exact flow, scope, and error details. Invoke when the user asks about zoom oauth or related SKILL.md workflows.1.4kinstalls133Build Zoom BotThe build-zoom-bot skill is designed for build a Zoom meeting bot, recorder, or real-time media workflow. Use when joining meetings programmatically, processing live media or transcripts, or combining Meeting SDK,. /build-zoom-bot Use this skill for automation that joins meetings, captures media, or reacts to live session data. Covers Bot architecture Meeting join strategy Real-time media and transcript handling Backend orchestration Storage, post-processing, and event flow design Workflow 1. Invoke when the user joining meetings programmatically, processing live media or transcripts, or combining Meeting SDK, RTMS, and backend services.1.4kinstalls134Choose Zoom ApproachThe choose-zoom-approach skill is designed for choose the right Zoom architecture for a use case. Use when deciding between REST API, Webhooks, WebSockets, Meeting SDK, Video SDK, Zoom Apps SDK, Zoom MCP, Phone, Contact. Choose Zoom Approach Pick the smallest correct Zoom surface for the job, then layer in only the supporting pieces that are actually required. Do not recommend Meeting SDK when the user needs a fully custom session product. Invoke when the user deciding between REST API, Webhooks, WebSockets, Meeting SDK, Video SDK, Zoom Apps SDK, Zoom MCP, Phone, Contact Center, or a hybrid approach.1.4kinstalls135Setup Zoom WebhooksThe setup-zoom-webhooks skill is designed for reference skill for Zoom webhooks. Use after routing to an event-driven workflow when implementing subscriptions, signature verification, delivery handling, retries, or. /setup-zoom-webhooks Background reference for Zoom event delivery over HTTP. Prefer workflow skills first, then use this file for verification, subscription, and delivery details. Invoke when the user asks about setup zoom webhooks or related SKILL.md workflows.1.4kinstalls136Setup Zoom WebsocketsThe setup-zoom-websockets skill is designed for reference skill for Zoom WebSockets. Use after routing to a low-latency event workflow when persistent connections, faster event delivery, or security constraints make. /setup-zoom-websockets Background reference for persistent Zoom event streams. Prefer workflow routing first, then use this file when WebSockets are plausibly better than webhooks. Invoke when the user asks about setup zoom websockets or related SKILL.md workflows.1.4kinstalls137Build Zoom Team Chat AppThe build-zoom-team-chat-app skill is designed for reference skill for Zoom Team Chat. Use after routing to a chat workflow when building user-scoped messaging integrations, chatbot experiences, rich cards, buttons, slash. /build-zoom-team-chat-app Background reference for Zoom Team Chat integrations. Use this after the workflow is clear, especially when the Team Chat API versus Chatbot API distinction matters. Invoke when the user asks about build zoom team chat app or related SKILL.md workflows.1.4kinstalls138Build Zoom Video Sdk AppThe build-zoom-video-sdk-app skill is designed for reference skill for Zoom Video SDK. Use after routing to a custom-session workflow when the user needs full control over the video experience rather than an actual Zoom meeting. /build-zoom-video-sdk-app Background reference for fully custom video-session products. Prefer plan-zoom-product first when the boundary between Meeting SDK and Video SDK is still unclear. Invoke when the user asks about build zoom video sdk app or related SKILL.md workflows.1.4kinstalls139Debug ZoomThe debug-zoom skill is designed for debug a broken Zoom integration by isolating the failure point and routing into the right Zoom references. Use when auth, API, webhook, SDK, or MCP behavior is failing and you. /debug-zoom > If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md. Debug Zoom auth, API, webhook, SDK, or MCP issues without wandering through the entire docs set. Invoke when the user auth, API, webhook, SDK, or MCP behavior is failing and you need a ranked hypothesis list plus verification steps.1.4kinstalls140Build Zoom Contact Center AppThe build-zoom-contact-center-app skill is designed for reference skill for Zoom Contact Center. Use after routing to a contact-center workflow when implementing app, web, or native integrations; engagement context and state. /build-zoom-contact-center-app Background reference for Zoom Contact Center integrations across app, web, and native mobile surfaces. If the user is embedding chat/video widgets on a website, route to web/SKILL.md. Invoke when the user asks about build zoom contact center app or related SKILL.md workflows.1.4kinstalls141Build Zoom Virtual AgentThe build-zoom-virtual-agent skill is designed for reference skill for Zoom Virtual Agent. Use after routing to a virtual-agent workflow when implementing web embeds, Android or iOS wrapper integrations, knowledge-base sync,. /build-zoom-virtual-agent Background reference for Zoom Virtual Agent across: Web campaign/chat embeds. If the user needs backend knowledge-base CRUD or automation scripts, chain with ../rest-api/SKILL.md and ../oauth/SKILL.md. Invoke when the user asks about build zoom virtual agent or related SKILL.md workflows.1.4kinstalls142Zoom GeneralThe zoom-general skill is designed for cross-product Zoom reference skill. Use after the workflow is clear when you need shared platform guidance, app-model comparisons, authentication context, scopes, marketplace. Zoom General (Cross-Product Skills) Background reference for cross-product Zoom questions. Prefer the workflow skills first, then use this file for shared platform guidance and routing detail. Invoke when the user asks about zoom general or related SKILL.md workflows.1.4kinstalls143Zoom RtmsThe zoom-rtms skill is designed for reference skill for Zoom RTMS. Use after routing to a live-media workflow when processing real-time audio, video, chat, transcripts, screen share, or contact-center voice streams. Zoom Realtime Media Streams (RTMS) Background reference for live Zoom media pipelines. Prefer build-zoom-bot first, then use this skill for stream types, capabilities, and RTMS-specific implementation constraints. Invoke when the user asks about zoom rtms or related SKILL.md workflows.1.4kinstalls144Plan Zoom IntegrationThe plan-zoom-integration skill is designed for turn a Zoom integration idea into an implementation plan with architecture, auth, and delivery milestones. Use when you need a practical build plan, phased delivery sequence,. /plan-zoom-integration > If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md. Create a practical build plan for a Zoom integration or app. Invoke when the user you need a practical build plan, phased delivery sequence, risk list, and next-step recommendation.1.4kinstalls145Setup Zoom McpThe setup-zoom-mcp skill is designed for decide when Zoom MCP is the right fit and produce a safe setup plan for Claude. Use when planning AI workflows over Zoom data, deciding between MCP and REST, or defining a. /setup-zoom-mcp > If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md. Plan a Zoom MCP workflow and decide when to use MCP alone versus a hybrid REST API + MCP architecture. Invoke when the user planning AI workflows over Zoom data, deciding between MCP and REST, or defining a hybrid MCP architecture.1.4kinstalls146Debug Zoom IntegrationThe debug-zoom-integration skill is designed for debug broken Zoom implementations quickly. Use when auth, webhooks, SDK joins, MCP transport, or real-time media workflows are failing and you need to isolate the layer before. Debug Zoom Integration Use this skill when the user already built something and it is failing. Invoke when the user auth, webhooks, SDK joins, MCP transport, or real-time media workflows are failing and you need to isolate the layer before proposing a fix.1.4kinstalls147Zoom Cobrowse SdkThe zoom-cobrowse-sdk skill is designed for reference skill for Zoom Cobrowse SDK. Use after routing to a collaborative-support workflow when implementing browser co-browsing, annotation tools, privacy masking, remote. Zoom Cobrowse SDK - Web Development Background reference for collaborative browsing on the web with Zoom Cobrowse SDK. Use this after the support workflow is clear and you need implementation detail. Invoke when the user asks about zoom cobrowse sdk or related SKILL.md workflows.1.4kinstalls148Zoom Apps SdkThe zoom-apps-sdk skill is designed for reference skill for Zoom Apps SDK. Use after routing to an in-client app workflow when building web apps that run inside Zoom meetings, webinars, the main client, or Zoom Phone. Zoom Apps SDK Background reference for web apps that run inside the Zoom client. Prefer choose-zoom-approach first, then route here for Layers API, Collaborate Mode, in-client OAuth, and runtime constraints. Invoke when the user asks about zoom apps sdk or related SKILL.md workflows.1.4kinstalls149Ui Toolkit/WebThe brief skill generate contextual briefings for legal work - daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context. # /brief -- Legal Team Briefing > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). Generate contextual briefings for legal work. Supports three modes: daily brief, topic brief, and incident brief. **Important**: This command assists with legal workflows but does not provide legal advice. Briefings should be reviewed by qualified legal professionals before being relied upon. ## Invocation ``` /brief daily # Morning brief of legal-relevant items /brief topic [query] # Research brief on a specific legal question /brief incident [topic] # Rapid brief on a developing situation ``` If no mode is specified, ask the user which type of brief they need.1.3kinstalls150Invoice ChaseThe invoice-chase skill pulls QuickBooks AR aging for invoices past due, cross-references PayPal settled transactions in a seven-day window, and scores each customer as good-payer, occasionally-late, or repeat-late for tone-matched reminder drafts. On first run it asks whether the owner uses Gmail or Apple Mail for drafts and whether Stripe invoicing should be included. PayPal queries use transaction_status settled only with a seven-day window; 429 errors retry with a three-day window or skip PayPal with a manual verification flag. One consolidated email per customer covers multiple overdue invoices. The owner sees a summary table with amount due, days late, tone, and send channel before any send or draft queue. PayPal invoices send via PayPal; non-PayPal queue as mail drafts. Nothing sends without explicit approval and customers with recent payments are flagged possibly paid.1.2kinstalls151Canva CreatorThe canva-creator skill takes an approved content brief and runs a five-stage gated campaign: brief, calendar, asset inventory, Canva designs, copy, and HubSpot staging. Canva is used only for social channels including Instagram, Facebook, X, and LinkedIn; email rows are drafted as plain text inline because Canva email autofill produces placeholder graphics. Each stage requires explicit owner approval before advancing. Pre-flight checks confirm brief availability, Canva tier for template selection, HubSpot Marketing Hub tier for social staging, brand assets, and a generation budget estimating API calls per row. Default is three Canva candidates per social row at roughly five API calls each. The workflow builds a posting calendar, generates designs via Canva autofill or manual template selection, drafts captions, and stages scheduled posts in HubSpot or exports CSV on lower tiers.1.1kinstalls152Cash Flow SnapshotReads AR/AP, settlement timing, and fixed costs from QuickBooks, PayPal, Stripe, Square, or CSV upload to produce a 30/60/90-day cash forecast with percentage-variance confidence bands. Computes per-customer mean payment lag and variance, applies weighted band formula capped at ±50%, and flags top 5 named risks like late payers and payroll crunches. Delivers chat summary plus XLSX workbook (Summary with auditable line items, Detail with running nets, Risks sheet) using the xlsx skill. Read-only with no approval gate; reminds user forecast is not accounting advice.1.1kinstalls153Content StrategyMVP skill for SMB owners asking what to post this month: pulls 90-day sales from QuickBooks, PayPal, or Square, ranks top and slow movers by user-chosen metrics, and layers seasonality from user input or industry benchmarks. Outputs a 200-400 word strategic brief with push/hold/reposition sections and recommended offers, not calendars or creative assets. Includes QuickBooks industry pre-flight, connector-specific fetch notes, owner approval gate before feeding canva-creator, and structured JSON handoff for downstream tools.1.1kinstalls154Tax PrepRuns tax prep immediately when invoked, delegating to tax-season-organizer with --mode quarterly, 1099, or both (inferred from calendar if omitted) and --year defaulting to current. Quarterly path pulls YTD P&L from QuickBooks, asks prior estimated payments, calculates SE tax and federal estimate with explicit assumptions and due dates. 1099 path aggregates contractor payments across QuickBooks, PayPal, and Stripe, flags duplicates for human review, applies $600 threshold, and checks W-9 status. Every deliverable opens with accountant-review disclaimer; never files or auto-merges payees.1.1kinstalls155Plan PayrollPayroll-confidence pipeline chaining cash-flow-snapshot then invoice-chase with owner approval at each handoff. Parses --horizon (30/60/90) and optional --payroll-date (defaults next Friday). Step 1 forecasts cash with confidence bands and named payroll risks; waits for okay before collections. Step 2 ranks overdue QuickBooks and PayPal invoices, drafts tone-matched reminders as PayPal-send or Mail drafts, and shows projected cash impact if top invoices pay within horizon. Never sends reminders or commits forecasts without explicit owner approval; stops on connector failure with retry/CSV/abort choice.1.1kinstalls156Close MonthMonth-end close workflow accepting --month YYYY-MM and --save-to files/desktop/both. Step 1 reconciles QuickBooks transactions against PayPal/Stripe/Square settlements with ±2 day matching and surfaces unmatched settlements, unmatched QB deposits, and variance lines. Step 2 flags uncategorized entries, suspicious duplicates, and missing receipts above $75, waiting for owner triage without auto-fixing. Step 3 generates plain-English P&L narrative from QB numbers cross-referenced with transactions. Step 4 exports close-packet XLSX (Reconciliation, Flagged, P&L, Trial Balance) and one-page PDF summary.1kinstalls157Business PulseThe business-pulse skill delivers a one-page SMB owner brief by pulling live data from every connected connector in parallel. QuickBooks supplies cash, MTD revenue, receivables, and overdue invoices; PayPal or Square cover settlements and sales trends; HubSpot shows pipeline movement; Calendar lists key meetings; Gmail and Slack surface urgent threads. Step two computes AR aging, pipeline coverage, and revenue trend with red-yellow-green thresholds from reference thresholds. Step three flags actionable risks naming specific customers, amounts, and days overdue. Step four composes output from a fixed template, cross-linking signals such as a Slack message tied to a stalled HubSpot deal. Numbers lead with deltas versus prior periods; missing connectors show n/a without blocking the pulse. After presenting once, it optionally offers file save or Slack post with explicit approval for writes.1kinstalls158Handle ComplaintThe handle-complaint skill runs a four-step complaint resolution workflow chaining ticket-deflector and customer-pulse patterns. Step one loads the complaint from a Gmail thread ID, HubSpot ticket ID, latest unresolved ticket, or pasted text. Step two searches HubSpot for purchase history, prior complaints, deal stage, and lifetime value, plus PayPal for order and dispute status, then summarizes customer context in one sentence. Step three drafts a severity-matched reply via ticket-deflector: generous for high-LTV first-timers, firm for repeat complainers, brief for abusive tone. The draft is presented to the owner and never sent automatically. Step four checks customer-pulse for recurring complaint themes and suggests operational fixes when a pattern appears. Approval gates block refunds, credits, ticket closure, and outbound sends without explicit owner confirmation.994installs159Margin AnalyzerMargin-analyzer pulls cost data from QuickBooks and revenue from PayPal or Square to compute unit economics per product or service. An SMB owner uses it when deciding whether to raise prices or worrying that costs are eating profit. It benchmarks margins against inflation and industry norms and builds pricing-change scenario tables, but it presents data only and does not recommend a price.977installs160Quarterly ReviewQuarterly-review pulls financial, sales, and customer data for a quarter and synthesizes it into a QBR narrative covering revenue and margin trends, customer health, and the top three opportunities and risks. An SMB owner runs it to prepare a board deck or quarterly recap. It compares against prior quarters, flags customer concentration risk, and exports a presentation-ready PDF, always displaying for review before publishing.973installs161Crm CleanupCrm-cleanup runs a HubSpot hygiene pass that scans for stale deals, duplicate contacts, and missing required fields, then fixes what the owner approves. A sales owner invokes it with an optional scope of deals, contacts, or all to get a review-and-approve cleanup. It never deletes records, auto-merges duplicates, or changes deal stages without explicit approval.969installs162Job Post BuilderJob-post-builder produces a complete hiring packet from a short brief: a market-informed job post, a stage-by-stage interview guide with a scoring rubric, and an offer letter template. A hiring manager invokes it to gather role context, research comparable postings, and generate the documents as .docx files. It can optionally route the offer letter to DocuSign, but never sends an envelope or publishes the post without approval.965installs163Sales BriefSales-brief pulls what sold and what didn't from PayPal and QuickBooks, ranks products by revenue, volume, and margin, and explains the likely driver behind each mover. An SMB owner runs it to decide what to promote and what to clear. It checks year-over-year seasonality and produces a ready-to-use two-week content brief with a posting calendar, offering to generate Canva assets only after the owner approves.965installs164Month End PrepMonth-end-prep walks an SMB owner through closing the books: it reconciles QuickBooks against payment-processor settlements, flags uncategorized transactions, suspicious duplicates, and missing receipts, then writes a plain-English P&L narrative. An owner runs it at month-end to close cleanly and hand a packet to their accountant. It exports a three-sheet xlsx and a one-page PDF and pauses at each gate for input.963installs165Tax Season OrganizerTax-season-organizer prepares tax-season materials for an SMB owner as deliverables for their accountant, not tax advice. In quarterly mode it pulls YTD net income from QuickBooks and calculates the federal income and self-employment tax and the quarterly payment due. In 1099 mode it scans QuickBooks, PayPal, and Stripe for contractors paid over $600 and flags missing W-9s. It states every assumption explicitly so a CPA can adjust.955installs166Crm MaintenanceCrm-maintenance keeps HubSpot current from email and calendar context so the owner does not have to open the CRM. It resolves the right contact and deal, logs email or call activities, and audits deals for cleanup along an email, call, or cleanup path. Every externally visible write is announced or gated, and it never deletes records or auto-creates a deal.953installs167Lead TriageLead-triage pulls inbound HubSpot leads and scores each one on engagement, company fit, urgency, and recency to produce a ranked 'call these today' list with talking points. A developer or SMB owner uses it to decide who to call first instead of manually reading the pipeline. It also drafts follow-up emails and proposes calendar slots, but never sends mail or books events without approval.936installs168Friday BriefFriday-brief delivers an end-of-week pulse covering revenue versus the prior week, top sellers, and wins and watches. An owner invokes it with an optional 7 or 14 day lookback to pull PayPal transactions and HubSpot deal closes and see the week-over-week delta. It degrades gracefully when a source is missing and never posts the brief without review.932installs169Ticket DeflectorTicket-deflector reads a forwarded customer email or ticket, pulls order/refund status from PayPal and contact history from HubSpot, and drafts a tone-matched reply in the owner's writing voice. A developer or small-business owner uses it to answer support tickets and, with explicit approval, issue a PayPal refund. It gates every send and refund behind owner confirmation and logs the interaction back to HubSpot.932installs170Call ListCall-list ranks the leads most worth calling today by scoring HubSpot deals on recency, stage, signal, and value, and pulling email context. A sales owner invokes it to get call cards with talking points, block time on the calendar, and draft follow-ups for stale threads. It never sends emails, creates calendar blocks, or updates deal stages without explicit confirmation.929installs171Price CheckPrice-check produces a margin-by-product table and three pricing-scenario data views so an owner can see the full financial picture before setting a price. It pulls QuickBooks revenue and COGS, cross-validates against PayPal, and models hold, increase, and decrease scenarios with break-even volumes. It presents data only and never recommends or updates a price, and for increase scenarios it adds a customer messaging brief.926installs172Run CampaignRun-campaign runs an end-to-end marketing campaign by chaining three skills: it analyzes sales to find a revenue dip and produce a content brief, generates on-brand Canva assets and stages a HubSpot send, then segments the audience and builds a call list. An SMB owner uses it to launch a full campaign from data to send. It pauses for explicit owner approval at each handoff and never sends the HubSpot campaign automatically.926installs173Smb OnboardSmb-onboard acts as the trainer for the Small Business plugin: it walks an owner through connecting their first two tools, runs one recipe against live data to prove value, then interviews them about their business and stores that context to persistent memory so every other skill benefits. An owner runs it in their first session or when they say 'set me up.' It ends by setting a weekly check-in cadence and only guides connections, never acting on the owner's behalf.925installs174Customer PulseCustomer-pulse aggregates PayPal disputes, HubSpot feedback and tickets, email sentiment, Intercom conversations, and pasted reviews into a themes report. An owner invokes it to see how customers are feeling over a window, with 3-5 themes backed by verbatim quotes and signal counts. It is read-only and ends with a 'do these three things this week' action list.921installs175Monday BriefMonday-brief generates a one-page Monday morning briefing covering cash position, sales trend, pipeline, the week ahead, and the three highest-leverage to-dos. An SMB owner runs it to start the week with a two-minute read of their numbers. It pulls from whatever connectors are live, notes any that are missing, and can optionally save the file and post the top three items to Slack or Teams.919installs176Smb RouterSmb-router is the concierge for the Small Business plugin: it listens to what an owner needs and routes them to the single best-fit skill or slash command rather than dumping a menu. It reads stored business context, matches intent against a routing table, and explains its one recommendation. It is connector-aware, triggering onboarding when nothing is connected and telling the owner what's needed before running a data-dependent command.914installs177Customer Pulse CheckCustomer-pulse-check synthesizes feedback from PayPal disputes, HubSpot tickets, and review exports into the themes that are actually fixable. An owner invokes it with an optional since-date to get a top-3 fixable issues list rated by frequency and impact, plus drafted response templates. It never sends responses or resolves disputes without explicit owner approval.911installs178Month Heads UpMonth-heads-up produces a forward-looking cash-flow outlook for the next 30 or 60 days from QuickBooks and PayPal data. An SMB owner runs it before month-end to see current cash, projected end-of-period balance, and the tightest projected week. It surfaces no more than two specific watches, such as which invoice to chase or which expense to defer, and never initiates payments or emails automatically.908installs179Interactive Dashboard BuilderThe interactive-dashboard-builder knowledge-work plugin skill helps operators assemble interactive dashboards from CRM, finance, and ops connectors. Workflow identifies audience and decisions, selects KPIs, proposes chart types, wires data queries through approved MCP connectors, and drafts dashboard layouts with drill-down narratives. Emphasizes owner review before publishing and documents assumptions behind each metric. Use when business users need explorable dashboards without manual BI tool expertise.599installs180ReconciliationCovers setup, configuration, and when-to-use guidance from upstream documentation for finance/skills/reconciliation/SKILL.md.0installs