Discover Claude Skills, Codex Skills, and reusable Agent Skills with install commands, source repositories, use cases, and security information.
vercel-labs / agent-skills
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
mattpocock / skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
shadcn / ui
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".
juliusbrussee / caveman
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"
juliusbrussee / caveman
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
leonxlnx / taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
mattpocock / skills
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
anthropics / skills
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
vercel-labs / agent-skills
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
Common questions about Agent Skills and safe installation
Agent Skills are reusable capability packages that an AI agent loads when needed. They commonly include a SKILL.md file, operating instructions, workflows, scripts, and optional resources. When a task matches the skill description, the agent reads the relevant content to perform specialized work.
Claude Skills are skills designed for Claude Code or other Claude agent workflows. After installation, Claude Code can load the SKILL.md when a task matches its description. You should still review the instructions, scripts, dependencies, and permission scope before use.
Codex Skills are Agent Skills that OpenAI Codex can load to add domain knowledge, repeatable procedures, and tool workflows. They are typically installed from a source repository into a skills directory and then used by Codex when a matching task appears.
The open SKILL.md pattern can be used or adapted by Claude Code, OpenAI Codex, Cursor, GitHub Copilot, Gemini CLI, VS Code, and other coding agents. Installation paths, triggering rules, and supported resources differ between products.
Treat a skill like code: inspect its SKILL.md, scripts, dependencies, requested permissions, and source repository before installation. Security badges are useful signals, not guarantees; use least privilege whenever a skill can access shells, networks, or credentials.
Entries are deduplicated by normalized source repository and skill identifier. When the same skill appears in several directories or awesome lists, or supports both Claude and Codex, its sources and compatibility data are merged into one record instead of creating duplicates.
