Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
14,280 skills from 417 repositories · updated 32 minutes ago
1,527 skills
- tabular-document-reviewborghei/Claude-SkillsExtract structured data from multiple documents into comparison matrix with citations. Use for bulk document review.EngineeringNo warnings★ 962↓ —
- md-reviewborghei/Claude-SkillsPre-publication quality gate for authored Markdown — heading structure, on-disk link resolution, readability, accessibility, terminology. Use when reviewing docs before publishing, wiring a docs CI gate, or auditing a Markdown corpus.EngineeringNo warnings★ 962↓ —
- reflectborghei/Claude-SkillsTurn reflection into decisions by scoring predictions against outcomes and tracking whether commitments held. Use when running a quarterly review, scoring forecast calibration, or reflection keeps producing notes instead of change.EngineeringNo warnings★ 962↓ —
- openai-apicoco-research/cocoUse when implementing GPT chat, streaming, function calling, embeddings for RAG, images, audio or batch jobs, or troubleshooting 429 rate limits and API or TypeScript errors. Stateless OpenAI patterns that prevent 16 documented errors.EngineeringNo warnings★ 911↓ —
- llm-cost-optimizerborghei/Claude-SkillsThis skill should be used when the user asks to "estimate LLM costs", "count tokens in prompts", "optimize prompt token usage", "compare model pricing", or "reduce LLM API costs".EngineeringNo warnings★ 962↓ —
- code-tourborghei/Claude-SkillsBuild ordered, annotated tours of an unfamiliar codebase and keep the anchors from rotting. Use when onboarding an engineer, handing off a service, or explaining a subsystem before a review.EngineeringNo warnings★ 962↓ —
- git-workflowBagelHole/DevOps-Security-Agent-SkillsImplement Git branching strategies, PR workflows, and release management patterns. Configure GitFlow, trunk-based development, or GitHub Flow for team collaboration. Use when establishing version control workflows or improving development team collaboration.EngineeringReview first★ 1.2K↓ —
- 编程手XiaoMaColtAI/math-modeling-skill数学建模的 Python 或 MATLAB 实现、运行、表格输出、可视化和复现阶段。EngineeringNo warnings★ 1.9K↓ —Also in 1 other repo
- cli-anythingcoco-research/cocoWrap any command-line tool into a JSON-emitting agent skill. Use when you want to make a CLI reliably callable and parseable by an AI agent — introspect its --help, define a structured-output (--json) contract and a stable error contract, then generate a SKILL.md wrapper with verified examples. Triggers on "wrap this CLI", "make X agent-usable", "generate a skill for this command", "turn a tool into an agent skill".EngineeringReview first★ 911↓ —
- ios-ettrace-performancedpearson2699/swift-ios-skillsUse when capturing or analyzing ETTrace profiles for a focused iOS launch or runtime flow, including exact-build dSYM UUID matching, Simulator or device capture, processed per-thread flamegraph JSON, sampled inclusive/exclusive time, unresolved symbols, and comparable verification. Use debugging-instruments or swiftui-performance for generic profiling instead.EngineeringNo warnings★ 1.2K↓ —
- hook-factoryalirezarezvani/claude-code-skill-factoryGenerate production-ready Claude Code hooks with interactive Q&A, automated installation, and enhanced validation. Supports 10 templates across 7 event types for comprehensive workflow automation.EngineeringNo warnings★ 893↓ —
- agent-factoryalirezarezvani/claude-code-skill-factoryClaude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patternsEngineeringNo warnings★ 893↓ —
- codex-cli-bridgealirezarezvani/claude-code-skill-factoryBridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both toolsEngineeringNo warnings★ 893↓ —
- coco-clicoco-research/cocoInstall, update, version-check, or uninstall the Coco open-source AI workflow framework via bin/coco.js. Use when setting up Coco on a machine, checking out the pinned release tag into an existing clone, checking the installed version, or removing it. npx cocosuperintelligence is the published path (clones the pin and installs). Triggers on "install coco", "update coco", "set up coco", "coco cli", "uninstall coco".EngineeringReview first★ 911↓ —
- route-scanninghuangjia2019/claude-code-engineeringScan Express.js source files to discover all API route definitions.EngineeringNo warnings★ 1.1K↓ —
- api-generatinghuangjia2019/claude-code-engineeringGenerate API endpoint documentation from Express route files. Use when the user asks to generate, update, or review API docs for Express.js routes.EngineeringNo warnings★ 1.1K↓ —
- code-reviewinghuangjia2019/claude-code-engineeringReview code for quality, security, and best practices. Use when the user asks for code review, wants feedback on their code, mentions reviewing changes, or asks about code quality.EngineeringNo warnings★ 1.1K↓ —Also in 1 other repo
- api-documentinghuangjia2019/claude-code-engineeringGenerate API documentation from code. Use when the user wants to document APIs, create API reference, generate endpoint documentation, or needs help with OpenAPI/Swagger specs.EngineeringNo warnings★ 1.1K↓ —Also in 1 other repo
- api-generatinghuangjia2019/claude-code-engineeringGenerate API endpoint code and documentation from specifications. Use when the user wants to create new API endpoints, generate route handlers, scaffold REST APIs, or produce OpenAPI/Swagger specs from code.EngineeringNo warnings★ 1.1K↓ —Also in 1 other repo
- hf-clisickn33/agentic-awesome-skillsCurated upstream guidance for Hf Cli; use when the workflow matches the user goal.EngineeringReview first★ 48.3K↓ —
- anth-common-errorsjeremylongshore/tons-of-skills-marketplaceDiagnose and fix Anthropic Claude API errors by HTTP status code. Use when encountering API errors, debugging failed requests, or troubleshooting authentication, rate limiting, or input validation issues. Trigger with phrases like "anthropic error", "claude api error", "fix anthropic 429", "claude not working", "debug claude api".EngineeringReview first★ 2.9K↓ —
- env-managementaipoch/open-scienceUse when a notebook run fails on a missing package (ImportError, ModuleNotFoundError, "there is no package called"), when you need to inspect an installed package version, or when you need to install, add, or manage Python or R packages for the notebook runtime. Covers inspect_packages, routing Python vs R through manage_packages, why in-cell %pip/!pip/install.packages() and OS installers are forbidden, restarting the kernel after an install, and when to stop and ask the user.EngineeringReview first★ 5.3K↓ —
- anth-debug-bundlejeremylongshore/tons-of-skills-marketplaceCollect Anthropic Claude API debug evidence for support and troubleshooting. Use when encountering persistent API issues, preparing support tickets, or collecting diagnostic information including request IDs and rate limit headers. Trigger with phrases like "anthropic debug", "claude debug bundle", "collect anthropic logs", "anthropic diagnostic", "claude support ticket".EngineeringReview first★ 2.9K↓ —
- openclawthedotmack/claude-memPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + MoreEngineeringReview first★ 102.2K↓ —