Claude Code skills
Find curated Claude Code Skills with readable sources. Learn where Skills load, how to run or install them, and how to check your own Skill across Agents.
Agents
npx skilld run owner/repo/skillClaude Code reads Skills from .claude/skills. It supports the shared Agent Skills format.
Check discovery paths and execution requirements before using the same Skill in another Agent.
skilld gives you a curated set of those Skills, each written by a person in their own repository, and one command that puts a Skill in front of Claude Code.
What are Claude Code Skills
A Skill is a directory with a SKILL.md file. The file starts with a name and a description, then holds instructions in Markdown. A Skill can carry supporting files: scripts, references, templates.
Claude Code reads each description at the start of a session. When your request matches, it loads the full file and follows it. You can also call a Skill by name with /<skill>.
A Skill differs from CLAUDE.md. CLAUDE.md loads at the start of a session.
A Skill's body loads when invoked, then remains in the conversation.
See Claude Code's Skill lifecycle.
To write your own, follow Create a Claude Code Skill. The complete example includes discovery paths and task checks for Codex and Gemini CLI too.
How to add Skills to Claude Code
- Project:
.claude/skills/<skill>/SKILL.md. Commit it, and every teammate gets it. - Global:
~/.claude/skills/<skill>/SKILL.md, for every project. IfCLAUDE_CONFIG_DIRis set, Claude Code and skilld both use$CLAUDE_CONFIG_DIR/skills.
Install a Skill for Claude Code
npx skilld install owner/repo/skill --agent claude-codeThe Skill lands in .claude/skills. Add --global to install to ~/.claude/skills instead. skilld detects the Agents in your project and on your machine. If it finds only one, omit --agent.
Start a new Claude Code session after an install. Skills load at startup.
Run a Skill without installing it
npx skilld run owner/repo/skillskilld run prints the Skill and writes no file. Give the command to Claude Code. It reads the Skill and follows it for this session. Nothing lands in your repository, and no lockfile changes.
Curated Skills for Claude Code
Claude Code runs subagents and long sessions, so these Skills cover agent workflows. Skills here come from the curated registry; a person admitted each one.
Use when executing implementation plans with independent tasks in the current session
Compact the current conversation into a handoff document for another agent to pick up.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
Validates skills in this repo against agentskills.io spec and Claude Code best practices. Use via /validate-skills command.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automate browser interactions, test web pages and work with Playwright tests.
All 37 Skills in Agent workflows
Claude Code can also search the registry itself, with the skilld Skill or the skilld MCP server. See the setup
Read before you run. A Skill is instructions for your Agent. Open the source file first. What skilld verifies, and what it never claims .