dotneet/claude-code-marketplace
10 skills11.7k installs30 starsGitHub
Install
npx skills add https://github.com/dotneet/claude-code-marketplaceSkills in this repo
1Typescript React ReviewerExpert code reviewer for TypeScript React 19 applications Use when reviewing React code identifying anti-patterns evaluating state management or assessing code maintainability Triggers code review requests PR reviews React architecture evaluation identifying code smells TypeScript type safety checks useEffect abuse detection state management review name typescript-react-reviewer description Expert code reviewer for TypeScript React 19 applications Use when reviewing React code identifying anti-patterns evaluating state management or assessing code maintainability Triggers code review requests PR reviews React architecture evaluation identifying code smells TypeScript type safety checks useEffect abuse detection state management review TypeScript React 19 Code Review Expert Expert code reviewer with deep knowledge of React 19's new features TypeScript best practices state management patterns and common anti-patterns Review Priority Levels Critical Block Merge These issues cause bugs memory leaks or architectural problems Issue Why It's Critical useEffect for derived state Extra render cycle sync bugs Missing cleanup in useEffect Memory leaks Direct state mutation push splice Silent.8kinstalls2Prompt Improverprompt-improver is a Claude Code marketplace skill that rewrites prompts to add explicit constraints, clearer instructions, and more reliable tool-calling behavior before you ship skills, subagents, or marketplace automations. Developers reach for prompt-improver when draft prompts are vague, omit edge cases, or produce inconsistent agent actions during Claude Code workflows. The skill focuses on prompt structure and constraint language rather than application code, making it a pre-deployment polish step for agent configurations.458installs3Code Modularization Evaluatorcode-modularization-evaluator is a Claude Code skill (version 1.0.0) from dotneet/claude-code-marketplace that evaluates module boundaries using Vlad Khononov's Balanced Coupling Model. It scores integration strength across four levels (intrusive through contract), distance across seven scopes, and volatility via DDD subdomain classification, then maps nine connascence types from name through identity. Red flags include CBO above 14, circular module dependencies, and intrusive cross-service database access. Output follows a structured assessment with coupling tables, connascence issues, and a prioritized refactoring plan. Reach for it before merging large refactors or designing new service boundaries.430installs4Google Calendargoogle-calendar is a dotneet/claude-code-marketplace skill for wiring Google Calendar into apps and AI agents. It helps developers implement scheduling flows, read free-busy availability, and create or update events programmatically through Google's Calendar API rather than manual UI steps. Reach for it when building meeting bots, booking assistants, standup schedulers, or workflow agents that must propose times, confirm conflicts, and persist events to a user's calendar. The skill targets OAuth-connected automation where calendar state must stay synchronized with conversational or backend triggers.416installs5Perplexity Searchperplexity-search is a Claude Code marketplace skill that embeds Perplexity-powered web search directly in agent sessions so developers can pull current facts, citations, API documentation, and market context without leaving the coding flow. The skill returns sourced answers useful when training data is stale or when verifying competitor moves, pricing pages, or newly shipped API behavior. Reach for perplexity-search during spike work, integration planning, or debugging errors tied to recent library releases. It suits engineers using Claude Code who want retrieval-augmented research with citations instead of guessing from model memory. Use it before committing to an architecture, when validating third-party docs, or when a task needs fresh web evidence alongside repo context.415installs6Call Cursor Agentcall-cursor-agent is a cross-agent integration skill for developers running Claude Code who want Cursor to execute a bounded task and return results into the same session. The skill checks for cursor-agent with which, then invokes cursor-agent --model with a task heredoc, defaulting to composer-1 when no model is specified. It fits parallelizing implementation, exploratory edits, or offloading a slice while Claude Code retains orchestration. Use call-cursor-agent when cursor-agent is installed and a subtask is concrete enough to hand off via CLI.413installs7Call Codexcall-codex is a Claude Code marketplace skill from dotneet/claude-code-marketplace that offloads defined coding tasks to OpenAI Codex while Claude Code keeps orchestrating the repository session. The workflow checks whether the codex binary is installed with which codex, then runs codex exec --sandbox danger-full-access with a heredoc task description and recommends maximum Bash timeout for long jobs. Developers reach for call-codex when a subtask benefits from Codex's execution model, when Claude Code should stay in planner-or-reviewer mode, or when parallel agent backends can shorten implementation time. The skill skips subsequent steps cleanly when Codex is not installed.380installs8Suggest Agent Rulessuggest-agent-rules is a Claude Code skill from dotneet/claude-code-marketplace that analyzes repository context and produces tailored agent rules, constraints, and guardrails. It helps developers codify project conventions, forbidden patterns, and workflow boundaries so Claude Code or Cursor agents follow team standards. Developers invoke it when onboarding AI assistants to an existing repo, replacing ad-hoc prompt instructions with durable rule files. The skill turns codebase signals into actionable agent configuration rather than generic best-practice lists.378installs9Context7context7 is a research plugin skill in dotneet/claude-code-marketplace that calls Context7 at https://context7.com/api/v2 with a CONTEXT7_API_KEY (ctx7sk- prefix). Its 3-step workflow resolves a library ID via GET /libs/search using libraryName and query, retrieves snippets via GET /context with libraryId and query, then answers with code examples and source URLs. Triggers include explicit "use context7" requests, library API questions, version-specific docs, and uncertain API details. The bundled references/api_reference.md documents authentication, trustScore selection, and 404/429 error handling. Use context7 whenever framework docs may have changed since model training—middleware setup, hook APIs, or package migrations.377installs10Call Claudecall-claude is a minimal Claude Code marketplace skill for delegating work to a separate Claude process from shell workflows. It first checks whether the claude binary is installed using which claude, exiting gracefully when absent. For task execution it runs claude -p --dangerously-skip-permissions with a heredoc-fed task description, and recommends setting the maximum Bash tool timeout because runs may be long. Developers use call-claude inside marketplace automations when a parent agent should hand off an isolated subtask—code review passes, batch transformations, or scripted pipelines—without embedding raw API calls. The pattern suits Claude Code environments where the CLI is already authenticated and non-interactive execution is required.372installs