Skills DirectoryClaude Code Skills
Claude Code skills package repeatable developer workflows into reusable instructions. Use them for code review, debugging, frontend polish, testing, documentation, infrastructure, and project-specific automation.
Indexed skills
96,810
Search focus
Claude Code
Security context
Scanned
Top matching skills
Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
Scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources. Use when creating a custom skill, standardizing skill structure across a team, or packaging a skill for distribution.
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
Build reusable Claude Code skills from any topic — /create-skill explores the codebase, drafts the SKILL.md interactively, and ships a slash command.
Claude Code skill for citation workflow via OpenAlex and CrossRef
Analyze session work and automatically convert reusable patterns into Claude Code skills. Use when: "세션을 스킬로", "스킬 만들어", "이거 스킬로", "skill factory", "이 작업 자동화해", "스킬 추출", "make this a skill", "extract skill", "convert to skill", "스킬 팩토리", "자동 스킬 생성". Differs from skill-creator (archived) and manage-skills (drift detection): this skill actively analyzes sessions, checks for duplicates, and creates skills via Agent Teams.
Teaches design patterns for workflow-based Claude Code skills and provides a review agent for auditing existing skills
Automatically reviews and fixes Claude Code skills through iterative refinement until they meet quality standards.
Expert guidance for creating, writing, building, and refining Claude Code Skills. Covers SKILL.md authoring, router patterns, progressive disclosure, references, workflows, templates, and self-healing via heal-skill.
MCP (Model Context Protocol) integration for OpenClaw/Clawdbot. Use when you need to: - Connect and orchestrate MCP tool servers (filesystem, GitHub, etc.) - Persist state across sessions with IndexedDB/localStorage - Sync sessions across multiple devices
Converts Claude Code skills to Gemini CLI extensions and vice versa. Use when the user wants to make a skill cross-platform compatible, port a skill between platforms, or create a universal extension that works on both Claude Code and Gemini CLI.
Best use cases
The highest-value Claude Code skills encode engineering habits: test-first development, systematic debugging, framework conventions, design-system rules, secure code review, deployment checklists, and repository-specific workflows.
Install fewer, better skills
A small set of precise Claude Code skills usually works better than a giant pile of overlapping rules. Pick skills that trigger on clear tasks and keep broad personality or style instructions in project context instead.
Security matters for coding agents
Coding skills may include commands, scripts, or repo access patterns. Review the security grade and source before installing a skill that can influence code, files, secrets, or deployment workflows.
Why security-scanned skills matter
Skills can influence agent behavior, suggest commands, include helper files, or touch code and data. Skills Directory adds security context so you can inspect risk before installing a workflow from a public repo.
See the security modelFrequently asked questions
Where do Claude Code skills live?
Claude Code commonly loads skills from project-level or user-level skills directories. Many skills are distributed as GitHub folders containing a SKILL.md file and optional support files.
What are the best Claude Code skills?
The best skills are workflow-specific: code review, frontend design, testing, debugging, API design, docs, security, and deployment skills tend to produce the most repeatable value.
Can Claude Code skills include scripts?
Yes, some skills include supporting scripts or reference files. That is powerful, but it also means you should inspect source and security signals before installing.