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. 79 437 files from 1 744 authors, of which 61 785 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.
When setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model. When building offline/air-gapped AI tools. When troubleshooting local LLM server connections.
Orchestrator discipline plugin documentation index. Load when needing to read about orchestration patterns, delegation rules, or context window management.
Orchestrator context window discipline enforcement. Prevents the orchestrator from reading source files it will not edit, running diagnostic commands that waste context, and rationalizing delegation bypasses. Use when setting up orchestrator guardrails, reviewing delegation discipline, or diagnosing context window waste in multi-agent workflows. Activates PreToolUse hooks that surface decision points before source file reads and diagnostic command execution.
This skill should be used when the user asks to install Perl modules, use cpanm, create a cpanfile, manage Perl dependencies, set up Carton, configure local lib, or mentions CPAN, cpanminus, module installation, or Perl package management.
This skill should be used when the user asks to "write a Perl script", "create Perl code", "modern Perl best practices", "Perl 5.30+", "use strict warnings autodie", or mentions Perl pragmas, subroutines, error handling, or scripting patterns. Provides comprehensive Perl 5.30+ development guidance.
This skill should be used when the user asks to "install perlbrew", "set up Perl environment", "install Perl version", "manage Perl versions", "switch Perl version", "install plenv", or mentions Perl version management, development environment setup, or multiple Perl installations.
This skill should be used when the user asks to lint Perl code, run perlcritic, check Perl style, format Perl code, run perltidy, or mentions Perl Critic policies, code formatting, or style checking.
This skill should be used when the user asks to write Perl tests, test Perl code, use Test More, run prove, create test suite, mock Perl, or mentions Perl testing, TAP, Test Class, Test Deep, or test-driven development in Perl.
This skill should be used when the user asks to "validate Perl script", "check Perl syntax", "verify Perl code", "/perl-validate", or mentions script validation, compile check, security review, or best practice compliance for Perl code.
Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.
Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.
Create high-quality Claude Code agents from scratch or by adapting existing agents as templates. Use when the user wants to create a new agent, modify agent configurations, build specialized subagents, or design agent architectures. Guides through requirements gathering, template selection, and agent file generation following Anthropic best practices (v2.1.63+).
Agent Skills Open Standard reference (agentskills.io). Use when creating portable skills for Claude Code, Cursor, Gemini CLI, OpenAI Codex, VS Code, Roo Code, and 20+ compatible agents. Covers frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring. Load before creating cross-agent skills.
Knowledge reference for Autonomous Refinement Loop research — pattern research into prerequisites for autonomous execution without synchronous human blocking gates. Defines failure categories, prerequisites, and conditions for replacing human judgment with machine-verifiable checks. Use when designing or evaluating autonomous agent loops, gate conditions, or HOOTL execution patterns.
Assess a plugin and create refactoring task files for parallel agent execution. Use when you need to analyze a plugin structure, score its quality, and generate a phased refactoring plan with design map and implementation tasks.
Audit agent lifecycle — validates agent execution capability against configuration. Accepts plugin path, runs 8 semantic audits (capability vs config alignment, skill loading correctness, inter-agent contracts, prompt contradictions, tool sufficiency, dead agents, scriptable patterns, pattern learning), writes reports to .plugin-creator/audits/. Use when auditing agent lifecycle, checking agent capabilities, verifying tool access, finding dead agents, validating agent contract alignment, or confirming agents can execute workflows.
Evaluate a single skill's quality against its stated purpose. Classifies the skill's purpose type, then scores applicable quality categories — universal dimensions always apply; structural dimensions (scripts, references, assets) are scored only when warranted by the skill's purpose. A focused 20-line behavioral skill with no bundled resources scores fully on all applicable categories. Use when auditing skill quality, checking marketplace readiness, evaluating skill completeness, performing pre-publication evaluation.
Audit skill lifecycle by tracing call chains, detecting circular dependencies, finding instruction contradictions, identifying duplicated datasets, analyzing bidirectional coherence, discovering scriptable sequences, and learning patterns. Use when checking skill coherence, validating skill workflow, finding semantic gaps in plugin structure, or auditing plugin before marketplace submission. Generates audit reports to .plugin-creator/audits/ with findings by dimension.
Complete reference for Claude Code plugins system (April 2026). Use when creating plugins, understanding plugin.json schema, marketplace configuration, bundling skills/commands/agents/hooks/MCP/LSP/monitor servers, plugin caching, validation, or distribution. Covers plugin components, directory structure, installation scopes, environment variables, CLI commands, debugging, and enterprise features.
Claude Code session log schema — JSONL record types, message structure, tool call/result pairing, subagent file locations, team session layout, task/plan/team configuration paths. Use when parsing ~/.claude/projects/**/*.jsonl files, writing PostToolUse hooks that measure response sizes, building session analyzers, or any agent that reads or queries Claude session transcripts.
Reference guide for Claude Code skills system (March 2026). Use when creating, modifying, or understanding skills, SKILL.md format, frontmatter fields, hooks, context fork, or skill best practices.
Reference spec and schema for Claude Code subagents — covers built-in agents (Explore, Plan, general-purpose), all frontmatter fields (name, description, tools, disallowedTools, model, permissionMode, maxTurns, skills, mcpServers, hooks, memory, background, effort, isolation, color, initialPrompt), scope and file locations, invocation patterns (@-mention, --agent, --agents CLI), tool restrictions, and example subagent definitions. Use when creating, configuring, or debugging a subagent definition file, looking up a frontmatter field, choosing between subagents and agent teams, or understanding what loads at subagent startup.
Create and configure slash commands for Claude Code — the legacy .claude/commands/ format. Use when asked to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or for guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices. Commands are the legacy format superseded by skills — for new development prefer /plugin-creator:skill-creator
Decide which plugin component type to use and how to organize components at scale. Covers the component lifecycle (discovery and activation phases), decision framework for choosing between commands, skills, agents, hooks, and MCP servers, and organization patterns for each component type. Use when asking "which component type should I use", "command vs skill vs agent", "when to use a hook vs MCP server", "component lifecycle", "how to organize plugin components", "plugin structure patterns", or "scale a plugin with many components".
Design pattern for converting rule-following, checklist, or rubric skills into a fan-out map-reduce ensemble of parallel rigid sub-agents with corroboration-weighted merge; worker model tier and diversity are knobs matched to inference load and stakes, not fixed values. Apply when creating or refactoring a skill or agent that applies 10+ independent criteria in a single pass. Triggers on: 'review against a checklist', 'fan out', 'map reduce review', 'ensemble', 'split the rules', 'apply rubric', or any large ruleset being applied by one agent in one pass. NOT for tight single-pass transforms or rulesets under 5 criteria.
Use when refactoring is complete and needs validation. Performs holistic review of completed plugin refactoring, validates improvements against original assessment score, checks for documentation drift, and creates follow-up task files if issues remain
Autonomous feature research and gap analysis. Use when starting /add-new-feature or analyzing existing architecture documents. Explores codebase patterns, identifies ambiguities, and produces feature-context-{slug}.md for orchestrator RT-ICA phase. Does NOT make technical decisions.
Guide for creating Claude Code plugin hooks — language selection heuristic (Node.js default, match project runtime when obvious), hooks.json configuration, event selection, prompt-based vs command hooks, ${CLAUDE_PLUGIN_ROOT} paths, stdio suppression, timeout sizing, and testing. Use when adding hooks to a plugin, creating PreToolUse/PostToolUse/Stop/SubagentStop/SessionStart/UserPromptSubmit hooks, or wiring hook scripts to hooks.json.
Hook system fundamentals — all events, configuration structure, matchers per event type, environment variables, execution behavior, security, and debugging. Use when creating hooks, understanding hook events, matchers, configuration locations, environment variables, or troubleshooting hook issues.
Cross-platform hooks reference for AI coding assistants — Claude Code, GitHub Copilot, Cursor, Windsurf, Amp. Covers hook authoring in Node.js (ESM and CJS) and Python, per-platform event schemas, inline-agent hooks and MCP in agent frontmatter, common JSON I/O, exit codes, best practices, and a fetch script to refresh docs from official sources. Use when writing, reviewing, or debugging hooks for any AI assistant.
Hook JSON input/output API reference — what data hooks receive via stdin and what JSON they can return to control Claude Code behavior. Use when writing hook scripts, checking exit code behavior, building JSON output for PreToolUse permissions, or understanding event-specific input schemas.
Hook recipes and working examples — plugin hooks, frontmatter hooks in skills/agents/commands, prompt-based LLM hooks, and complete code examples in Python and Node.js. Use when building hook scripts, integrating hooks into plugins, implementing prompt-based hooks, or looking for hook configuration patterns.
Use when a refactoring task file exists from /assessor and tasks need execution. Reads task files, resolves dependencies, delegates to specialist agents (SKILL_SPLIT, AGENT_OPTIMIZE, DOC_IMPROVE), and tracks completion with parallel orchestration
Use when checking skill quality, validating frontmatter before commit, or diagnosing validator warnings. Runs the plugin validator on a skill, agent, or plugin directory — reports token complexity, broken links, frontmatter issues, and structural problems. Pass the path as an argument.
Integrate MCP servers into Claude Code plugins — covers .mcp.json configuration, plugin.json mcpServers field, server types (stdio, SSE, HTTP, WebSocket), environment variable expansion, tool naming conventions, OAuth and token authentication, security best practices, and testing workflows. Use when adding an MCP server to a plugin, configuring MCP authentication, debugging MCP tool discovery, setting up Model Context Protocol integration, or choosing between stdio and SSE transport types.
Configure and manage Claude Code persistent memory (CLAUDE.md, auto memory, rules) across sessions. Use when setting up project memory, organizing .claude/rules/, managing auto memory files, creating CLAUDE.md with imports, debugging memory loading, or advising on memory hierarchy and best practices.
Define and develop plugin mission statements — purpose, values, anti-patterns, and trade-offs. Use when creating a new plugin, auditing an existing plugin's alignment, or providing a reference for the alignment check loop to evaluate decisions against. Produces mission.json with [draft] status and creates a backlog interview task for the human to refine it.
Optimize existing CLAUDE.md, SKILL.md, agent definitions, and other AI-facing files for Claude comprehension and economy. Scope: optimization of existing content only — not upstream sync, not read-only auditing. Measures baseline metrics, delegates to @ai-doc-optimizer agent with file-type-specific context, runs independent verification via second agent, measures post-optimization metrics, and presents comprehensive before/after report. Supports iterative mode for large targets. Use when improving prompt effectiveness, reducing token waste, or rewriting instructions for LLM consumption. Invoke with /optimize-claude-md <file-or-directory>.
Use when writing delegation instructions to subagents, authoring CLAUDE.md files, rules, skills, or agent definitions, or auditing existing AI-facing content for bloat. Activates on "write a rule for", "add to CLAUDE.md", "create an agent", "update memory", or any request to author AI-facing instruction content. Removes discoverable data, explained-away knowledge, invented constraints, and stale cached facts.
Plugin creator documentation index. Load when needing to read about plugin validation error codes, skill creation, agent creation, or plugin structure.
Use when creating a new Claude Code plugin from scratch — orchestrates prerequisite check, user discussion, parallel research, design with verification, atomic implementation, multi-layer validation, documentation, and final verification. For existing plugin improvement, use /plugin-creator:plugin-lifecycle instead.
Orchestrate the full plugin development lifecycle from blank canvas to marketplace-ready. Use when creating a new plugin, improving an existing plugin, fixing validation errors, or taking a plugin through assessment, research, design, creation, debugging, optimization, and verification. Complements /plugin-creator:plugin-creator which provides the detailed new-plugin creation workflow with discussion capture, parallel research, and atomic implementation.
Per-project plugin configuration via .local.md files — covers the .claude/plugin-name.local.md pattern for storing user-configurable settings with YAML frontmatter and markdown body. Use when implementing plugin settings, reading YAML frontmatter from hooks, creating configuration-driven behavior, managing agent state files, or adding per-project plugin configuration. Covers file structure, parsing techniques, common patterns (temporarily active hooks, agent state management, configuration-driven behavior), security considerations, and best practices.
Optimize CLAUDE.md files and Skills for Claude Code CLI. Use when reviewing, creating, or improving system prompts, CLAUDE.md configurations, or Skill files. Transforms negative instructions into positive patterns following Anthropic's official best practices.
Start a complete plugin refactoring workflow that analyzes plugin structure, creates a refactoring plan with tasks, and guides through execution. Use when you need to refactor an entire plugin — triggers assessment, design, planning, and parallel agent execution phases.
Assess and refactor oversized or multi-domain skills. First determines whether splitting or references/ extraction is appropriate — then executes the correct action. Use when a skill exceeds token thresholds (SK006/SK007) or covers multiple independent domains. Performs candidate assessment before any structural changes; cohesive single-intent skills are redirected to references/ extraction instead of splitting. When splitting is warranted — domain analysis gate, split plan, new SKILL.md generation, validation, and backwards-compatible facade conversion.
Configure Claude Code permissions — tool approval rules, permission modes, managed policies, and sandboxing. Use when setting up permission rules, configuring allow/deny/ask policies, debugging permission prompts, deploying managed settings for organizations, or controlling Bash/Read/Edit/WebFetch/MCP/Agent tool access.
Use when creating a new skill or updating an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Activates on "create a new skill", "add a skill to plugin", or "update existing skill".
Sync a skill's content against the upstream library it covers — check whether the API descriptions, version references, and SOURCE: citations inside SKILL.md and its reference files still reflect what the library actually does today. Use when a library has released updates that may have changed the APIs the skill covers, when a skill references an old library version, when asked to sync, refresh, update, or check a skill against upstream docs, when the skill's content may have drifted from current library behavior, or when SOURCE: citations are stale. Accepts a SKILL.md path, skill directory, or plugin directory.
Start or complete a specific refactoring task from a task file. Use when a sub-agent needs to pick up a refactoring task, update its status, implement acceptance criteria, and run verification steps.
Analysis criteria, transformation patterns, output format, and validation checklist for refactoring Claude Code agent prompt files. Load this skill when preparing to run the subagent-refactorer agent or when reviewing agent prompt files for structural, model optimization, or instruction quality improvements.
Write or rewrite frontmatter description fields for Claude Code skills and agents. Use when creating new skills/agents, description exceeds 1024 characters, description uses forbidden YAML multiline indicators (>-, |-), description lacks trigger keywords, or when optimizing descriptions for AI tool selection. Ensures descriptions are single-line, complete, informative, third-person, front-loaded with trigger conditions.
Process quality methodology for the process-siren agent — use before or during Mermaid conversion when the source process shows ambiguity, missing decisions, undefined actors, vague conditions, or structural weakness. Provides triage sequence, excellence criteria, and an improvement framework drawn from Lean, Six Sigma, BPR, Design Thinking, Systems Thinking, and Theory of Constraints. Activates when source content is poorly structured enough that converting it as-is would encode wrong behavior for AI readers.
Mermaid diagram syntax reference for all diagram types — flowchart, sequence, class, state, ER, gantt, git graph, mindmap, timeline, user journey, pie, quadrant, XY chart, block, sankey, C4, kanban, and more. Use when constructing or debugging any Mermaid diagram definition.
Optimize processes in a file or directory by converting prose/bullet workflows to Mermaid diagrams — delegates to the process-siren:process-siren agent. Use when given a single SKILL.md, agent file, CLAUDE.md, or rules file to convert, or a directory containing any of those. Supports --dry-run or --report for read-only planning mode.
Analyzes failing test cases to determine whether failures indicate genuine bugs or incorrect test implementations. Use when debugging test failures, investigating test errors, classifying failures as test bugs vs implementation bugs vs ambiguous behavior, or when given specific failing test names or pytest output. Applies balanced investigative reasoning — never auto-fixes tests without establishing root cause first.
Use when writing asyncio Python code — async/await coroutines, concurrent I/O with asyncio.gather, task creation and cancellation, semaphore rate limiting, producer-consumer queues, async context managers, async generators, WebSocket servers, aiohttp web scraping, async database operations, run_in_executor for blocking calls, or testing async code with pytest-asyncio. Covers FastAPI and aiohttp patterns, synchronization primitives, timeout handling, and common pitfalls like event loop blocking and missing await.
Runs structured Python cleanup and modernization — static analysis via prek/ruff, smell investigation to root cause, typed-boundary hardening by inventorying Any usage, and modernization within the project's requires-python lane. Use when refactoring Python code, removing dead code, hardening type boundaries, or running a modernization pass on a file or scope.
Performs checklist-driven review of pytest test suites against coverage thresholds (80% line/branch minimum, 95% for critical paths), AAA pattern adherence, pytest-mock usage, test isolation, naming clarity, type hints, and flaky pattern detection. Use when auditing test quality before a release, reviewing coverage gaps, checking tests for completeness or best practices, or validating mocking standards. Accepts a test file or directory as input and outputs prioritized findings grouped by HIGH, MEDIUM, and LOW priority.
Use when creating a new feature development task — scaffolds a structured task file at .claude/tasks/{feature-name}.md with phased breakdown (Design, Implementation, Testing, Documentation), acceptance criteria, context preservation, and TaskCreate tracking. Activates on "create a feature task", "set up development tracking", "plan a feature implementation", or when preparing work for python-cli-architect or python-pytest-architect agents.
Claude Skills — questions
Answers built from the skills we actually parsed.