Documentation
How to use a skill repository from the AI you already have, how to write one, and the contracts behind both.
Guides
- Use skills from your AI
A skill is a set of instructions an AI app follows to do one kind of work well: write release notes in the house style, turn a product picture into a short ad, review a change for the things a linter…
- Write a skill repository
A skill repository is a git repository with a SKILL.md for each skill. Push it to GitHub, and its address serves the skills to any AI app that connects: https://skillcdn.ai/gh/<owner>/<repo>, or the…
Reference
- The SkillCDN Format
How SkillCDN reads a repository, and how a repository is written so that an agent uses it well. The layout is the Agent Skills layout: a repository that already works as a skills folder works here un…
- Addresses
An address identifies what an agent mounts. It is the path of the MCP endpoint URL, so the whole onboarding is one URL.
- What an agent gets over MCP
A mounted address exposes four read-only, idempotent tools, and serves its skills through the MCP skills extension (the skills extension). The tools are the discovery layer, and the whole surface for…
- REST API
The API shows a person what an agent gets from an address. Without a session it is anonymous, read-only and limited to public repositories; on a deployment where people sign in, a request that carrie…
- People, private repositories and access
Everything here exists only on a deployment that is configured for signing in (deploy). Without that configuration there are no people, no private repositories and none of these routes: the deploymen…
Operate
- Self-hosting
Build the image, configure it through the environment and run a deployment of your own: the admin API, signing in, what a public deployment must show, a reverse proxy, and how a release is built.