Agent skills

Skills you can use with AI coding agents, indexed from public GitHub repositories.

Latest Most Popular

building-mcp-servers Expert at integrating MCP servers into Claude Code plugins. Auto-invokes when configuring MCP servers (stdio/SSE/HTTP/WebSocket), writing .mcp.json files, or adding external tool integrations.
C0ntr0lledCha0s/claude-code-plugin-automations 3
building-commands Expert at creating and modifying Claude Code slash commands. Auto-invokes when creating/updating commands, modifying command frontmatter (model, allowed-tools, argument-hint), designing workflows, or writing to */commands/*.md files.
C0ntr0lledCha0s/claude-code-plugin-automations 3
building-hooks Expert at creating Claude Code event hooks for automation and policy enforcement. Auto-invokes when creating/updating hooks, modifying hooks.json, designing event-driven automation, or writing hook configurations.
C0ntr0lledCha0s/claude-code-plugin-automations 3
building-plugins Expert at creating Claude Code plugins that bundle agents, skills, commands, and hooks. Auto-invokes when creating/structuring plugins, writing plugin.json manifests, or bundling components into packages.
C0ntr0lledCha0s/claude-code-plugin-automations 3
example-skill Expert at performing task X automatically. Auto-invokes when the user wants to do Y, needs help with Z, or encounters situation W.
C0ntr0lledCha0s/claude-code-plugin-automations 3
building-skills Expert at creating and modifying Claude Code skills. Auto-invokes when creating/updating skills, modifying skill frontmatter (allowed-tools, description), designing skill architecture, or writing to */skills/*/SKILL.md files.
C0ntr0lledCha0s/claude-code-plugin-automations 3
investigating-codebases Automatically activated when user asks how something works, wants to understand unfamiliar code, needs to explore a new codebase, or asks questions like "where is X implemented?", "how does Y work?", or "explain the Z component"
C0ntr0lledCha0s/claude-code-plugin-automations 3
researching-best-practices Automatically activated when user asks "what's the best way to...", "how should I...", "what are best practices for...", or requests recommendations, industry standards, or proven approaches for implementing features
C0ntr0lledCha0s/claude-code-plugin-automations 3
analyzing-patterns Automatically activated when user asks to "find patterns in...", "identify repeated code...", "analyze the architecture...", "what design patterns are used...", or needs to understand code organization, recurring structures, or architectural decisions
C0ntr0lledCha0s/claude-code-plugin-automations 3
creating-feedback-loops Expert at creating continuous improvement feedback loops for Claude's responses. Use when establishing self-improvement processes, tracking progress over time, or implementing iterative refinement workflows.
C0ntr0lledCha0s/claude-code-plugin-automations 3
analyzing-response-quality Expert at analyzing the quality of Claude's responses and outputs. Use when evaluating response completeness, accuracy, clarity, or effectiveness. Auto-invokes during self-reflection or when quality assessment is needed.
C0ntr0lledCha0s/claude-code-plugin-automations 3
improving-components Expert at automatically applying improvements to Claude Code components based on quality analysis. Enhances descriptions, optimizes tool permissions, strengthens security, and improves usability. Works in conjunction with analyzing-component-quality skill.
C0ntr0lledCha0s/claude-code-plugin-automations 3
analyzing-component-quality Expert at analyzing the quality and effectiveness of Claude Code components (agents, skills, commands, hooks). Assumes component is already technically valid. Evaluates description clarity, tool permissions, auto-invoke triggers, security, and usability to provide quality scores and improvement suggestions.
C0ntr0lledCha0s/claude-code-plugin-automations 3
suggesting-improvements Expert at suggesting specific, actionable improvements to Claude's responses and work. Use when Claude's output needs enhancement, when quality issues are identified, or when iterating on solutions.
C0ntr0lledCha0s/claude-code-plugin-automations 3
coordinating-projects Automatically activated when user mentions multi-project coordination, cross-project dependencies, portfolio management, roadmap planning, resource allocation across projects, or asks to coordinate/manage multiple projects simultaneously. Provides strategic project coordination expertise.
C0ntr0lledCha0s/claude-code-plugin-automations 3
planning-sprints Automatically activated when user mentions sprint planning, backlog refinement, iteration planning, sprint goals, capacity planning, velocity tracking, or asks to plan/start/close a sprint. Provides comprehensive sprint planning expertise using agile best practices.
C0ntr0lledCha0s/claude-code-plugin-automations 3
docling-serve Use docling through docling-serve to parse pdf, docx and other document formats.
Shura1oplot/agents-stuff 1
firecrawl Official Firecrawl CLI skill for web scraping, search, crawling, and browser automation. Returns clean LLM-optimized markdown. USE FOR: - Web search and research - Scraping pages, docs, and articles - Site mapping and bulk content extraction - Browser automation for interactive pages Must be pre-installed and authenticated. See rules/install.md for setup, rules/security.md for output handling.
Shura1oplot/agents-stuff 1
research-analysis-modeling Business analysis, research, data analytics (gather, process, quality control), assumptions, financial and economic modeling
Shura1oplot/agents-stuff 1
journalist-editor Summarize, distill, and denoise business texts (reports, articles, press releases). Remove fluff, detect bias and manipulation, produce executive summaries. Audience is business analysts and senior managers.
Shura1oplot/agents-stuff 1
session-learner Extract and persist learnings from the current session. This skill should be used when the user wants Claude to analyze the conversation and capture insights, patterns, preferences, or knowledge discovered during work. Triggers on requests like "learn from this session", "what did we learn", or "capture insights".
anexpn/claude-plugins 1
dev-guided Human-in-the-loop iterative development. Use when requirements will emerge during implementation, decisions need human approval at each step, or work will span multiple sessions with frequent feedback loops. Creates problem statement, decisions log, runbook, and progress tracking.
anexpn/claude-plugins 1
systematic-debugging Structured debugging methodology for investigating and resolving technical issues. Use this skill when debugging any technical problem, investigating errors, or troubleshooting unexpected behavior to ensure root cause analysis rather than symptom treatment.
anexpn/claude-plugins 1
dev-auto Autonomous development workflow. Generate detailed specs, plans, and tasks for autonomous agent execution with session memory tracking.
anexpn/claude-plugins 1