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

# Skills overview

> How skills extend the AI — folders with SKILL.md instructions, scripts, and references, auto-injected into the system prompt.

Skills are how Open Computer Use teaches models domain-specific workflows without fine-tuning. Each skill is a folder with `SKILL.md` instructions (read by the AI before starting a task) and optional helper scripts and reference docs. Skills are mounted read-only inside every sandbox at `/mnt/skills/` and exposed to the model through the system prompt.

## Why skills

* **Repeatable quality.** The docx skill bundles tracked-changes via OOXML redlining — you get consistent Word output every time, across any model.
* **Model-agnostic.** Claude, GPT-4o, Qwen, Mistral — same skill, same output shape. Write once, use everywhere.
* **Pluggable.** Built-in skills are baked into the Docker image. User skills are uploaded as ZIPs and bind-mounted per user.
* **Auto-discovery.** The server builds an `<available_skills>` XML block and injects it into the system prompt. The model picks the right skill without being named.

## How a skill runs

1. On chat start, `skill_manager.get_user_skills(email)` resolves which skills this user has enabled.
2. The system prompt gets an `<available_skills>` block listing names, descriptions, and paths.
3. The model picks a skill based on the task and reads the skill's `SKILL.md` via `view` tool.
4. The skill's scripts live under `/mnt/skills/{category}/{name}/scripts/` — the model runs them via `bash_tool`.

<Frame>
  <img src="https://mintcdn.com/yambr/AQ23_2YQrfJDjXh_/images/diagrams/dynamic-skills.svg?fit=max&auto=format&n=AQ23_2YQrfJDjXh_&q=85&s=da06e22f28cdb38a8b27d2ca383cadc6" alt="Dynamic per-user skill injection" width="750" height="420" data-path="images/diagrams/dynamic-skills.svg" />
</Frame>

## Categories

| Category  | Mount                          | Source                                    |
| --------- | ------------------------------ | ----------------------------------------- |
| `public`  | `/mnt/skills/public/{name}/`   | Baked into the Docker image               |
| `example` | `/mnt/skills/examples/{name}/` | Baked; opt-in via Settings Wrapper        |
| `user`    | `/mnt/skills/user/{name}/`     | ZIP from Settings Wrapper, cached on host |

Without the Settings Wrapper, all 13 public skills are always enabled for everyone.

## Next

<CardGroup cols={2}>
  <Card title="User guide" icon="book" href="/skills/user-guide">
    What each skill does, how they appear to the model.
  </Card>

  <Card title="Full reference" icon="list" href="/skills/reference">
    13 built-in skills + 14 examples with capabilities.
  </Card>

  <Card title="Dynamic injection" icon="gear" href="/skills/dynamic">
    The internals — cache layers, fallbacks, mounts.
  </Card>

  <Card title="Creating a skill" icon="wand-magic-sparkles" href="/skills/creating">
    Folder layout, SKILL.md format, publishing.
  </Card>
</CardGroup>