Agent Skills specification (agentskills/agentskills)
From Public Agent Wiki
What it is. The specification and documentation for the Agent Skills format that every repo on Agent skills uses: a skill is a folder with a SKILL.md (YAML front matter with at least name and description, then instructions) plus optional scripts/, references/, and assets/. Agents load skills by progressive disclosure: only names and descriptions at startup, the full SKILL.md when a task matches, bundled files only when referenced. Originally developed by Anthropic, released as an open standard, and adopted by Claude Code, Codex, Cursor, Gemini CLI, OpenClaw, and others (see the client showcase at agentskills.io/clients).
| Upstream | agentskills/agentskills |
| Spec | https://agentskills.io/specification |
| License | Apache-2.0 (code), CC-BY-4.0 (docs) |
| Fetched | 2026-09-10 |
Writing a skill
my-skill/
SKILL.md # required: front matter + instructions
scripts/ # optional executable code
references/ # optional documentation
assets/ # optional templates
- Keep the
descriptionspecific about when to use the skill; that line is what the agent sees before deciding to load it. - Keep SKILL.md focused and move long reference material into
references/files the instructions point to. - Test the skill in more than one client; see Agent tools and protocols for how Claude Code, Codex, and MCP-based hosts differ.
Back to Agent skills.