80,000+ Skills to Supercharge Claude
The open directory for GitHub-integrated capabilities, tools, and prompts for your AI workflows.
Bootstrap or maintain a Codex skills repo with auto-sync to ~/.codex/skills; use when setting up a shared skills reposit...
Standardize git commit messages using a consistent convention and guide clean-history workflows. Use when a user asks fo...
ai-task-runner
by UTohru
このスキルは外部のAI エージェントを実行するためのスキルです。 実装や調査の作業を別のAIエージェントに委譲してください。...
owasp-security-review
by ayuzaka
Security review and implementation support based on OWASP Cheat Sheet Series. Use for code review requests, security-rel...
skill-review
by ayuzaka
Review Agent Skills and provide findings and improvement suggestions from the perspective of official specification comp...
upgrade-integration
by JDerekLomas
Integrate Carnegie Learning's UpGrade A/B testing platform into LMS and EdTech applications. Guides setup of decision po...
async-python-patterns
by dredd-us
Implement AsyncIO patterns for I/O-bound tasks with asyncio.gather, semaphores, and FastAPI async endpoints. Use for con...
queue-based-flow
by dredd-us
Stack prompts in queue while agent runs, minimizing context switches to achieve sustained 6k lines per day output and pr...
progressive-metadata
by dredd-us
Pattern for creating skills with YAML frontmatter that enables progressive disclosure and token optimization. Use when b...
doc-to-skill-scraper
by dredd-us
Scrape external documentation (API references, library docs, protocol specifications) and generate Claude Agent Skills i...
claude-md-memory
by dredd-us
Central CLAUDE.md file with project guidelines auto-injected into system prompt, achieving 10% accuracy lift in multi-ho...
markdown-formatter
by dredd-us
Format and lint Markdown documents with consistent style, proper heading hierarchy, link validation, and code block form...
api-integrator
by dredd-us
Integrate external REST and GraphQL APIs with proper authentication (Bearer, Basic, OAuth), error handling, retry logic,...
experience-library
by dredd-us
Capture task outcomes, score performance, and derive rules as token priors for continual learning without model weight c...
skill-creator
by dredd-us
Meta-skill to generate new Claude Agent Skills from natural-language descriptions. Use when creating skills, building cu...
plan-execute
by dredd-us
Two-phase workflow that generates explicit YAML plan before execution, with approval gates and checkpointing. Use for co...
uncertainty-routing
by dredd-us
Route tasks to small model by default, escalate to large model only on low confidence detection, achieving 87% faster le...
vibe-coding-yaml
by dredd-us
AI outputs YAML descriptors instead of code, CLI executes deterministically for 100% auditable behavior with zero slop....
theory-grounding-reflecto...
by dredd-us
Extract lessons from task failures using Reflector agent, merge insights via Curator pattern, achieving 10% accuracy imp...
code-testing
by dredd-us
Generate and run unit and integration tests using pytest (Python) or Jest (JavaScript) with fixtures, mocks, and async s...
smart-skill-loading
by dredd-us
Auto-detect and load minimal context from Skills folders using progressive disclosure, trimming 1400 tokens from system...
continuous-skill-polishin...
by dredd-us
Convert repeated tasks into versioned skills, track performance gaps, and iteratively polish through Git version control...
parallel-session-orchestr...
by dredd-us
Run multiple agent tasks in parallel cloud sandboxes with real-time progress monitoring, achieving 2x throughput vs sequ...
life-sciences-connector
by dredd-us
Query PubMed and scientific databases for protocols, analyze biological data with Biopython, handle HIPAA-compliant data...