agents365-ai/365-skills
15 skills35.9k installs435 starsGitHub
Install
npx skills add https://github.com/agents365-ai/365-skillsSkills in this repo
1Drawio SkillThe drawio-skill generates .drawio XML and exports PNG, SVG, PDF, or JPG locally through the native draw.io desktop CLI without browser automation. Use it for polished precise diagrams including architecture, network topology, strict UML, ERD, and ML model figures when custom styling, swimlanes, or embeddable exports matter. PNG, SVG, and PDF support --embed-diagram so exported files retain editable XML, signaled with double extensions like name.drawio.png. Route casual whiteboard looks to excalidraw or tldraw, diagrams-as-code in git to mermaid or plantuml, and freeform sketching to tldraw per skill guidance. macOS installs via brew install --cask drawio or GitHub releases; resolve the draw.io binary path before running export commands. Critical XML rule: every edge mxCell must include mxGeometry relative=1 child or diagrams break. The skill covers shape vocabulary, swimlanes, ML architecture templates, and CLI export flags for agent-generated diagrams.6.7kinstalls2Creating Mermaid DiagramsThe creating-mermaid-diagrams skill generates .mmd text diagrams with automatic layout and exports to PNG, SVG, or PDF using local mmdc or the Kroki API when Node is unavailable. Prerequisites are npm global @mermaid-js/mermaid-cli or curl for Kroki. Workflow checks optional upstream version tags once per 24 hours, verifies mmdc or falls back to Kroki, picks a diagram type, writes the .mmd file, validates before export, then reports output paths. Validation is mandatory: run mmdc to a temp PNG or POST to kroki.io/mermaid/svg and fix syntax before exporting. Supported types include flowchart, sequence, class, ER, state, Gantt, pie, gitGraph, C4Context, and mindmap with reference docs per type. Export examples use mmdc at 2048px width with white background and optional themes, or Kroki POST for svg, png, and pdf. Common mistakes cover wrong sequence arrows, unquoted special characters, missing participants, and blank output without -w 2048. Proactive use is encouraged for systems with three or more components, API flows, auth sequences, schemas, or state machines.3.2kinstalls3ExcalidrawThe excalidraw skill generates .excalidraw JSON diagrams and exports to PNG or SVG for architecture, flowcharts, and system visualizations. Kroki API via curl provides zero-install SVG export; excalidraw-brute-export-cli with Firefox enables local PNG and SVG. Workflow checks dependencies, plans visual metaphor and palette, writes excalidraw JSON section by section for large diagrams, exports, verifies render quality, and loops minimal edits until approved. Design principles favor roughness 0 clean lines, Helvetica fontFamily 2, typography over boxes with under thirty percent of text inside rectangles, 60-30-10 color rule from a fixed semantic palette, and arrow semantics for solid primary, dashed async, and dotted optional flows. Community libraries via excalidraw_lib.py merge vector AWS, Azure, and network icons without image elements. Route polished UML to drawio, diagrams-as-code to mermaid, and infinite canvas needs to tldraw instead.3.1kinstalls4Plantuml SkillThe plantuml-skill generates PlantUML diagram files and exports PNG or SVG using the Kroki API with curl only, avoiding local Java installs by default. Modes include generate from description, from source code, markdown embed rendering, refine existing puml, and review readability. Workflow covers dependency check, diagram type selection, puml authoring with startuml markers, Kroki POST with HTTP status capture, validation loop treating non-200 and empty outputs as failures, and up to three self-correction rounds degrading exotic shapes and skinparam themes. Vision self-check catches label truncation, overlap, wrong orientation, and edge spaghetti with two fix rounds. Reference docs route from-source-code and markdown-embed paths. Diagram types span sequence, component, class, ER, activity, state, C4, mind map, and Gantt. Use when users request UML diagrams, architecture charts, sequence flows, or PlantUML blocks embedded in Markdown for Confluence or Notion publishing.2.7kinstalls5Tldraw SkillUse when user requests diagrams flowcharts architecture charts or visualizations Also use proactively when explaining systems with 3 components complex data flows or relationships that benefit from visual representation Generates tldr JSON files and exports to PNG SVG locally using kitschpatrol tldraw-cli The tldraw-skill skill documents workflows and patterns from the repository SKILL md name tldraw-skill description Use when user requests diagrams flowcharts architecture charts or visualizations Also use proactively when explaining systems with 3 components complex data flows or relationships that benefit from visual representation Generates tldr JSON files and exports to PNG SVG locally using kitschpatrol tldraw-cli license MIT homepage https github com Agents365-ai tldraw-skill compatibility Requires Node js kitschpatrol tldraw-cli on PATH macOS Linux Windows Self-check step requires a vision-enabled model e g Claude Sonnet Opus gracefully skipped if unavailable platforms macos linux windows metadata openclaw requires bins tldraw emoji os darwin linux win32 install id npm-tldraw kind npm package kitschpatrol tldraw-cli global true bins tldraw label Install tldraw-cli via npm h.2.5kinstalls6Semanticscholar SkillThe semanticscholar-skill runs a four-phase workflow: plan strategy, execute one Python script with s2.py prelude, deduplicate results, and present findings. Critical rule forbids sequential Bash API calls; all searches run in a single script with built-in rate limiting. Strategies map to search_bulk, search_relevance, search_snippets, match_title, get_paper, citations, recommendations, and author endpoints. build_bool_query helps disambiguate terms; filters cover year, venue, citations, open access, and publication types. S2_API_KEY optional for higher limits. Agents default to bulk search unless TLDR or inline author details require relevance mode. Use for literature discovery, citation analysis, paper lookup by DOI, or researcher publication lists.2.3kinstalls7Paper FetchThe paper-fetch 365-skills skill obtains research PDFs when users provide DOI, arXiv identifiers, titles, citations, or DOI lists. It tries open-access resolvers, publisher pages, and preprint archives with clear failure reporting. Agents verify metadata matches the requested work and prefer legal open copies. Use for literature review, reference gathering, or downloading papers from academic identifiers. Fetches PDFs from DOI, arXiv, title, or citation input. Open-access resolver strategies with fallbacks. Batch DOI list support with per-item status. Metadata verification before download. Literature review and reference workflows. Fetch paper PDFs by DOI, arXiv ID, title, or citation with open-access resolution strategies.2.3kinstalls8Asta Skillasta-skill is an agent skill from agents365-ai/365-skills that domain expertise for ai2 asta mcp tools (semantic scholar corpus). intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and aut. # Asta MCP — Academic Paper Search Asta is Ai2's Scientific Corpus Tool, exposing the Semantic Scholar academic graph over MCP (streamable HTTP transport). This skill tells agents **which Asta tool to call for which intent**, and how to compose them into useful workflows. - **MCP endpoint:** `https://asta-tools.allen.ai/mcp/v1` - **Auth:** `x-api Developers invoke asta-skill during idea/research work for documentation 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.2.1kinstalls9Journal AbbrevThe journal-abbrev skill is designed for use when looking up journal or magazine name abbreviations, converting between full names and ISO 4/MEDLINE abbreviations, processing BibTeX files for journal name. Never guess abbreviations — even common journals have non-obvious abbreviations. | Command | |---------------|---------| | Abbreviate a journal name | python3 jabbrv.py abbrev "Nature Medicine" | | Expand an abbreviation | python3 jabbrv.py expand "Nat. Invoke when the user looking up journal or magazine name abbreviations, converting between full names and ISO 4/MEDLINE abbreviations, processing BibTeX files for journal name standardization, or answering questions about 期刊缩写/杂志缩写.1.9kinstalls10Video Podcast MakerThe video-podcast-maker skill use when the user gives a topic and wants an automated topic-driven narrated explainer podcast or knowledge-summary video Bilibili YouTube Xiaohongshu Douyin WeChat Channels or asks to learn visual design patterns from a reference video image Trigger when the user mentions creating a knowledge video narrated explainer video podcast or talking-head topic video from a topic even if they don't say video podcast explicitly Do NOT trigger for generic video editing trimming for REQUIRED Load Remotion Best Practices First This skill depends on remotion-best-practices You MUST invoke it before proceeding Invoke the skill tool named remotion-best-practices Video Podcast Maker Automated pipeline for 4K Bilibili horizontal knowledge videos from a topic Coding agent TTS backend Remotion FFmpeg Contents Bootstrap bootstrap update check prerequisites run before Step 1 Execution Modes execution-modes Auto vs Interactive default decisions Workflow workflow the 15 steps phase-file pointers mandatory stops Hard Rules hard-rules non-negotiable production constraints output specs Per-Video Layout per-video-layout directory structure public-dir naming Additional Resources.1.8kinstalls11Target PrioritizationThe target-prioritization skill prioritize drug targets from a ranked gene list (e.g., scRNA-seq DE output) by orchestrating parallel API queries against UniProt, OpenTargets (with integrated DepMap CRISPR essentiality + gnomAD constraint), PubMed, the Human Protein Atlas (HPA), and ChEMBL tool compounds, then re-ranking by a composite score combining protein localization, druggability, disease genetics, tissue specificity (safety), focus-cell-type expression, CRISPR essentiality, LoF safety constraint, and research maturity. # Target Prioritization A multi-source drug-target due-diligence pipeline for ranked gene lists. ## When this skill triggers The user has a list of candidate genes (typically from a DE / DEG / scRNA-seq analysis) and wants a per-gene dossier across multiple evidence dimensions plus a composite re-ranking. The DE statistical rank is just the entry point; the final priority is informed by protein biology, genetics, druggability, and research maturity. Common input shapes: - A CSV with a `gene` column (DE output like `expression_table_pass_either_1s.csv`) - A plain-text gene list (one symbol per line) - A list of symbols inline in the user's message ## Output T.1.8kinstalls12Pi PromptingThe pi-prompting skill internal guidance for composing prompts that Pi runs (DeepSeek by default) handle reliably for coding, review, diagnosis, and research tasks # Pi Prompting Use this skill when `pi:pi-rescue` needs to ask Pi for help on a non-trivial coding or investigation task. Pi runs whatever model the user has configured. By default this plugin targets DeepSeek V4 (Pro for review, Flash for everyday tasks). The guidance below assumes the prompt may run on either a non-reasoning model (Flash) or a reasoning model (Pro). Bias toward concrete, numbered checklists rather than abstract instructions - both model classes follow those reliably. Core rules: - Prefer one clear task per Pi run. Split unrelated asks into separate runs. - Tell Pi what done looks like. Do not assume it will infer the desired end state. - State explicit grounding rules whenever an unsupported guess would degrade quality. - Use stable XML-style tag blocks so the prompt has obvious internal structure.1.8kinstalls13Pi Result HandlingThe pi-result-handling skill internal guidance for presenting Pi helper output back to the user # Pi Result Handling When the helper returns Pi output: - Preserve the helper's verdict, summary, findings, and next steps structure. - For review output, present findings first and keep them ordered by severity. - Use the file paths and line numbers exactly as the helper reports them. - Preserve evidence boundaries. If Pi marked something as an inference, uncertainty, or follow-up question, keep that distinction. - Preserve output sections when the prompt asked for them, such as observed facts, inferences, open questions, touched files, or next steps. - If there are no findings, say that explicitly and keep the residual-risk note brief. - If Pi made edits, say so explicitly and list the touched files when the helper provides them. - For `pi:pi-rescue`, do not turn a failed or incomplete Pi run into a Claude-side implementation attempt. Report the failure and stop.1.8kinstalls14Pi Cli RuntimeThe pi-cli-runtime skill internal helper contract for calling the pi-companion runtime from Claude Code # Pi Runtime Use this skill only inside the `pi:pi-rescue` subagent. Primary helper: - `node "${CLAUDE_PLUGIN_ROOT}/scripts/pi-companion.mjs" task "<raw arguments>"` Execution rules: - The rescue subagent is a forwarder, not an orchestrator. Its only job is to invoke `task` once and return that stdout unchanged. - Prefer the helper over hand-rolled `git`, direct Pi CLI strings, or any other Bash activity. - Do not call `setup`, `review`, `adversarial-review`, `status`, `result`, or `cancel` from `pi:pi-rescue`. - Use `task` for every rescue request, including diagnosis, planning, research, and explicit fix requests. - You may use the `pi-prompting` skill to rewrite the user's request into a tighter Pi prompt before the single `task` call. - That prompt drafting is the only Claude-side work allowed. Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.1.8kinstalls15Scholar Deep ResearchA Claude Code skill that runs an end-to-end academic literature-review workflow, turning a question into a cited, structured report. It federates seven scholarly sources, deduplicates and ranks results, chases citations across two backends, and runs a mandatory self-critique before output. A developer or researcher uses it for literature reviews, surveys, and comparative analyses.38installs