Use Case
Agent Skills Open Standard isn't just for solo use β teams can share skills and build consistent AI workflows across the organization. The official specification repository for the Agent Skills open standard β the SKILL.md format that powers cross-platform AI agent skill interoperability. Maintained by the agentskills organization, this repo defines how skills should be structured, what metadata is required, and how agents should discover and invoke skills. If you're building skills for distribution, this is the authoritative reference. The standard is now adopted by Claude Code, Codex CLI, Cursor, Gemini CLI, and 30+ other tools. This guide covers how to deploy Agent Skills Open Standard for your team, standardize prompts, and create shared workflows that everyone can use.
Install Agent Skills Open Standard in your project directory: .claude/skills/agentskills-spec/
Commit the skill folder to your repository so the whole team has access
Document your team's standard prompts in a shared README
Use Agent Skills Open Standard in code reviews, standups, and planning sessions
Iterate: collect feedback from the team and refine your prompts
Copy these prompts and use them with your AI agent after installing Agent Skills Open Standard
How can my team use Agent Skills Open Standard together?
Set up Agent Skills Open Standard for our project so everyone can use it
Create a shared workflow using Agent Skills Open Standard for our team
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install agentskills-specOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install agentskills-specβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/agentskills-spec/π‘Extract and place the folder at the path above, then restart your agent.