> ## Documentation Index
> Fetch the complete documentation index at: https://to11.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Skills

> Publish a coding-agent skill once, and every developer who follows it has the current version in the directories their agent reads.

A coding agent is only as good as the instructions it has on hand: how your team triages an incident, reviews a migration, or names a feature flag. Those instructions usually live as a folder someone copied into `~/.claude/skills` months ago, and every copy drifts on its own schedule.

to11 keeps them in one place. A skill is written once and stored as a version in a [project](https://to11.ai/docs/platform/projects.md). Every developer who follows the project receives it — and receives the next version the same way — without anyone copying a file.

## How a skill travels

```text theme={null}
  author                      to11 project                   every developer
  ─────────                   ────────────                   ───────────────
  incident-triage/            incident-triage                ~/.claude/skills/incident-triage
    SKILL.md      ── store ──▶  v1 v2 v3 v4                  ~/.agents/skills/incident-triage
    references/                         ▲
                                        │
                                   latest ────── sync ────▶  (current version, on disk)
```

Two acts move a skill from a folder to a machine:

* **Store** writes a new immutable version of the whole folder and moves the skill's one label, `latest`, to it. The version lands on your own machine too. Nothing is pinned: your configuration follows `latest`, which is now this version, and a `version:` pin you already had moves to it.
* **Sync** makes a machine match its configuration: a machine following `latest` receives the newest version, and a machine pinned to a version keeps it. It runs when a developer asks for it, and automatically while their agent is open.

A store is a publish. What a machine does with it is decided on the machine, which is the next section.

## Who decides what a machine receives

What a developer receives is decided by configuration files, not by the platform:

* **A developer's own file** (`~/.to11/skills.yaml`) names the projects they follow, and which agents get the files.
* **A repository's file** (`<repo>/.to11/skills.yaml`) is committed, so the skills a team relies on for work in that repository reach everyone who works there — in addition to their own.
* **Disabling a skill is yours to decide.** A developer can decline any skill in their own directories, decline one a repository asks for with `enforced: true`, and hold a skill at a version while `latest` moves on.

The platform never pushes a file onto a machine that did not ask for it. See [Choosing which skills you receive](https://to11.ai/docs/skills/choosing-skills.md) for the common cases, and the [configuration reference](https://to11.ai/docs/reference/cli/configuration.md#precedence) for the exact precedence rules.

## Where the files land

The CLI writes each skill where the agent already looks for skills, so there is no agent setting to change:

| Target | Directory | Read by |
| - | - | - |
| Claude Code | `.claude/skills/<slug>` | Claude Code |
| Codex | `.agents/skills/<slug>` | in a repository: Codex, Cursor, GitHub Copilot, Gemini CLI and other agents; at home: Codex, Cline, Warp, Zed and other agents |

Both are relative to your home directory for your own skills, and to the repository root for a repository's. `.agents/skills` is the folder the Agent Skills ecosystem shares, so the Codex target reaches more agents than Codex. At home, Cursor, GitHub Copilot and Gemini CLI read their own folders (`~/.cursor/skills`, `~/.copilot/skills`, `~/.gemini/skills`) instead; point a [`standard` target](https://to11.ai/docs/reference/cli/configuration#where-skills-land) at one to reach them there. A skill already in one of those directories that to11 did not write is left alone and reported. Only an explicit `to11 skill sync --force` replaces one that a published skill needs the name of.

## Staying current without asking

The [to11 plugin](https://github.com/to11ai/to11-code-plugin), which `to11` offers to install for Claude Code and Codex when it links a location, refreshes skills while a session is open — when it starts, when you submit a prompt, and in Claude Code before a skill is used. A refresh inside the cache window (60 seconds by default) makes no request, and a refresh never blocks the work that triggered it. `to11 skill sync` refreshes on demand.

## Where to read them

Skills are written as folders and stored from the [to11 CLI](https://to11.ai/docs/reference/cli.md). The dashboard lists them beside your chat prompts, shows each file as a machine receives it, and compares versions. It does not edit them — a skill's source of truth is its folder. [What a skill is](https://to11.ai/docs/skills/concepts.md) explains why, and what a skill can and cannot carry.

Skills use the same permissions as prompts; there is no separate set. See [Roles & permissions](https://to11.ai/docs/platform/roles-and-permissions.md).

## Next steps

> [card] [Quickstart](https://to11.ai/docs/skills/quickstart.md)
>
> Receive a skill and publish your own — in one pass.

> [card] [What a skill is](https://to11.ai/docs/skills/concepts.md)
>
> The folder format, its limits, and what a skill cannot carry.

> [card] [Receiving skills](https://to11.ai/docs/skills/receiving-skills.md)
>
> Install the CLI and configure a machine or a repository.

> [card] [Publishing skills](https://to11.ai/docs/skills/publishing-skills.md)
>
> Store a version from a folder; everyone who follows the project receives it.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.