Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 696 files from 2 113 authors, of which 68 413 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Reference for Claude Code's 6 Task Management tools — TaskCreate, TaskGet, TaskList, TaskUpdate (structured tracking) and TaskOutput, TaskStop (background execution). Covers tool parameters, status lifecycle, completion rules, dependency management, and conventions
Produce a structured codebase analysis report with architecture overview, critical files, patterns, and actionable recommendations. Use when asked to "analyze codebase", "explore codebase", "understand this codebase", "map the codebase", "give me an overview of this project", "what does this codebase do", "codebase report", "project analysis", "audit this codebase", or "how is this project structured".
Provides language-specific patterns for TypeScript, Python, and React including idioms, best practices, and common patterns. Use when implementing features in these languages.
Conduct an adaptive interactive interview on any topic and produce a structured markdown report, summary, or implementation plan. Use when the user says "interview me", "interview me about", "run an interview on", "help me think through", or wants guided discovery on any subject. Also triggers on "talk me through", "explore X with me", "help me plan Y", or "walk me through my thinking on Z" when the user wants a guided conversation rather than a direct answer. Applies broadly — career decisions, project ideas, product direction, personal goals, research questions, team problems — not just technical topics.
Deep exploration and synthesis workflow using Agent Teams with dynamic planning and hub-and-spoke coordination. Use when asked for "deep analysis", "deep understanding", "analyze codebase", "explore and analyze", or "investigate codebase".
Reference for Claude Code Agent Teams — lifecycle, messaging, spawning, orchestration, and hooks
>- Reference patterns for search, optimization, and greedy algorithms. Covers binary search (classic and on-answer), two pointers, sliding window, greedy strategies, prefix sums, merge intervals, and monotonic stack. Use when solving problems that involve searching sorted data, optimizing over constraints, processing subarrays/substrings, or reducing range queries.
>- Reference for string algorithm patterns — KMP, Z-function, Rabin-Karp, Manacher's, string hashing, suffix arrays, and Aho-Corasick. Covers recognition signals, core ideas, Python templates, edge cases, and common mistakes for each technique.
Reference for dynamic programming patterns — recognition signals, constraint mapping, Python templates, edge cases, and common mistakes for 8 core DP techniques
>- Solve competitive programming and LeetCode-style problems with educational explanations. Use when asked to "solve this problem", "help with this leetcode", "competitive programming solution", "solve this algorithm problem", "coding challenge solution", "how to solve this coding problem", or any algorithmic problem-solving request.
>- Reference for advanced data structure patterns used in competitive programming and technical interviews. Covers heaps, monotonic stacks, tries, segment trees, Fenwick trees, stack-based parsing, and ordered sets with Python templates, recognition signals, and edge case guidance.
>- Reference patterns for mathematical and combinatorial problem-solving. Covers modular arithmetic, prime sieves, GCD/LCM, binomial coefficients, fast exponentiation, counting techniques, inclusion-exclusion, and game theory. Load this skill when a problem involves number theory, combinatorics, modular operations, or strategic game analysis.
>- Verify a competitive programming or LeetCode solution for correctness, edge cases, and performance. Use when asked to "verify my solution", "check my code", "is this solution correct", "test my solution", "review my competitive programming answer", "validate my algorithm", or any solution verification request.
>- Reference patterns for graph algorithm problems including BFS, DFS, Dijkstra, topological sort, union-find, MST, Bellman-Ford, and bipartite checking. Provides recognition signals, Python templates, edge cases, and common mistakes for each technique. Use when solving problems involving graphs, trees, shortest paths, connectivity, or dependency ordering.
Provides architectural pattern knowledge for designing feature implementations including MVC, event-driven, microservices, and CQRS patterns. Use when designing system architecture or choosing implementation patterns.
>- Systematic, hypothesis-driven debugging workflow with triage-based track routing. Use when asked to "fix this bug", "debug this", "why is this failing", "this is broken", "investigate this error", "track down this issue", or any debugging situation. Supports --deep flag to force full investigation.
Keep a Changelog format guidelines and entry writing best practices. Use when writing changelog entries, updating CHANGELOG.md, or following Keep a Changelog specification.
Provides code quality principles including SOLID, DRY, testing strategies, and best practices for implementation review. Use when reviewing code or applying quality standards.
>- Captures project-specific patterns and anti-patterns into the project's CLAUDE.md. Loaded by other skills (bug-killer, feature-dev, etc.) when they discover project-specific knowledge worth encoding for future sessions.
Feature development workflow with exploration, architecture, implementation, and review phases. Use for implementing new features or significant changes.
>- Generate a markdown report documenting codebase changes from the current session — files added, modified, deleted, and a summary of what was done. Use when asked to "document changes", "generate change report", "save changes report", "what did I change", "session report", "summarize my changes", or "write a changes report".
>- Documentation management workflow for MkDocs sites and standalone markdown files — initialize, generate, update docs, and create change summaries. Use when asked to "create docs", "write README", "update documentation", "generate docs site", "write CONTRIBUTING", "manage documentation", or "docs changelog".
Commit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
>- Unified entry point for creating or updating OpenCode tools (skills, agents, commands) with dependency awareness. Orchestrates the creation of multiple related artifacts in a single session. Use when user says "create opencode tool", "new opencode tool", "oc-tool-dev", or wants to create/update an OpenCode artifact and may need supporting artifacts.
Prepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.
>- Guides through creating a new OpenCode command with interactive interview, $VARIABLE configuration, and validation. Use when user says "create opencode command", "new opencode command", "build command for opencode", or wants to create an OpenCode command markdown file.
>- Guides through creating a new OpenCode-compatible agent with interactive interview, permission configuration, and validation. Use when user says "create opencode agent", "new opencode agent", "build agent for opencode", or wants to create an OpenCode agent markdown file.
>- Guides through creating a new OpenCode-compatible skill with interactive interview, best-practice enforcement, and validation. Use when user says "create opencode skill", "new opencode skill", "build skill for opencode", or wants to create an OpenCode SKILL.md file.
>- Updates an existing OpenCode command to match current platform best practices, fixes deprecated patterns, and validates the result. Use when user says "update opencode command", "fix opencode command", "migrate command to opencode", or wants to modernize an existing OpenCode command file.
>- Updates an existing OpenCode agent to match current platform best practices, fixes deprecated patterns, and validates the result. Use when user says "update opencode agent", "fix opencode agent", "migrate agent to opencode", or wants to modernize an existing OpenCode agent file.
Analyzes the Agent Alchemy plugin ecosystem to detect dependency issues across all plugin groups
Bumps plugin versions across the Agent Alchemy ecosystem
>- Updates an existing OpenCode skill to match current platform best practices, fixes deprecated patterns, and validates the result. Use when user says "update opencode skill", "fix opencode skill", "migrate skill to opencode", or wants to modernize an existing OpenCode SKILL.md file.
>- Convert Claude Code plugins into generic, platform-agnostic format. Supports full conversion (skills, agents, hooks), flatten mode (skills only — agents converted to skills, hooks absorbed), or nested mode (agents nested as pure markdown within parent skills, hooks absorbed). Full mode supports per-group or unified output layouts — unified merges all groups into a single directory organized by component type. Strips Claude Code-specific implementation details to produce clean markdown files preserving only the intent and instructions. Use when asked to "make this portable", "convert to generic format", "export plugin", "create universal skills", "strip platform dependencies", "make harness-agnostic", "decouple from Claude Code", "flatten to skills only", "nest agents in skills", or when the user wants their plugin content usable outside Claude Code. Also use when the user wants to share skills with teams using different agent frameworks.
Validates adapter files against live platform documentation to detect stale mappings,missing features, and outdated version information
Analyze an existing spec for inconsistencies, missing information, ambiguities, and structure issues. Use when user says "analyze spec", "review spec", "spec quality check", "validate requirements", "audit spec", or "check spec quality".
Updates previously-ported plugins when source plugins change or the target platform evolves
Converts Agent Alchemy plugins into formats compatible with other AI coding platforms
Create a new specification through an adaptive interview process with proactive recommendations and optional research. Use when user says "create spec", "new spec", "generate spec", or wants to start a specification document.
Execute pending tasks in dependency order with wave-based concurrent execution via Agent Teams
Execute pending Claude Code Tasks in dependency order with wave-based concurrent execution and adaptive verification. Supports task group filtering and configurable parallelism. Use when user says "execute tasks", "run tasks", "start execution", "work on tasks", or wants to execute generated tasks autonomously.
Analyze test coverage and identify gaps with actionable recommendations
Generate Claude Code native Tasks from an existing spec. Use when user says "create tasks", "generate tasks from spec", "spec to tasks", "task generation", or wants to decompose a spec into implementation tasks.
Transform SDD tasks into test-first TDD task pairs. Reads existing tasks from /create-tasks and generates paired test tasks with RED-GREEN dependencies. Use when user says "create tdd tasks", "add tdd pairs", "convert to tdd", or wants to apply test-first ordering to SDD tasks.
Execute TDD task pairs autonomously with RED-GREEN-REFACTOR verification. Orchestrates wave-based execution with strategic parallelism, routing TDD tasks to tdd-executor agents and non-TDD tasks to standard task-executor. Use when user says "execute tdd tasks", "run tdd tasks", "start tdd execution", or wants to execute TDD-paired tasks from create-tdd-tasks.
Generate test files from acceptance criteria or existing code. Supports criteria-driven mode (from specs/tasks) and code-analysis mode (from source files). Auto-detects test framework and spawns test-writer agents for parallel generation.
Designs implementation blueprints for features using exploration findings and architectural best practices (converted from agent)
Run a full RED-GREEN-REFACTOR TDD workflow for a feature. Accepts a feature description, task ID, or spec section as input. Presents a plan for confirmation then runs autonomously through all TDD phases.
Produce a structured codebase analysis report with architecture overview, critical files, patterns, and actionable recommendations. Use when asked to "analyze codebase", "explore codebase", "understand this codebase", "map the codebase", "give me an overview of this project", "what does this codebase do", "codebase report", "project analysis", "audit this codebase", or "how is this project structured".
Explores codebases to find relevant files, trace execution paths, and map architecture with team communication capabilities for collaborative analysis (converted from agent)
Synthesizes exploration findings into unified analysis with deep investigation capabilities and completeness evaluation (converted from agent)
Provides language-specific patterns for TypeScript, Python, and React including idioms, best practices, and common patterns. Use when implementing features in these languages.
Deep exploration and synthesis workflow with dynamic planning and hub-and-spoke coordination. Use for deep analysis, deep understanding, or codebase investigation.
Behavioral rules and lifecycle event handlers for the core-tools package. Defines automated behaviors that trigger at specific points in the agent workflow. (converted from hooks)
Guides discovery and application of project-specific conventions including code patterns, naming, structure, and team practices. Use when exploring a codebase or implementing features to match existing patterns.
>- Provides Mermaid diagram syntax, best practices, and styling rules for technical visualizations. Use when creating diagrams, flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, architecture diagrams, C4 diagrams, visualizations, or any visual documentation in markdown. Always use this skill when generating or updating Mermaid code blocks.
Systematic, hypothesis-driven debugging workflow with triage-based track routing. Use for debugging, fixing bugs, and investigating errors.
Provides architectural pattern knowledge for designing feature implementations including MVC, event-driven, microservices, and CQRS patterns. Use when designing system architecture or choosing implementation patterns.
Executes diagnostic investigation tasks to test debugging hypotheses. Runs tests, traces execution, checks git history, and reports evidence. (converted from agent)
Reviews git history and updates CHANGELOG.md with entries for [Unreleased] section (converted from agent)
Claude Skills — questions
Answers built from the skills we actually parsed.