Dynamic skills

Resolution pipeline

On every chat start, the server calls skill_manager.get_user_skills(email). The result resolves through three fallback levels:

Memory cache — 60-second TTL. Same (email) hit twice in a minute = dict lookup.
Settings Wrapper API — if MCP_TOKENS_URL is set, fetches the user’s enabled skills.
Disk cache — if the API is down but we cached last known good, reuse it.
Hardcoded defaults — all 13 public skills.

Without the Settings Wrapper, step 4 always wins — everyone gets the full public set.

System prompt injection

The skill list becomes an <available_skills> XML block injected into the system prompt:

<available_skills>
  <skill>
    <name>docx</name>
    <description>Create and edit Word documents with tracked changes</description>
    <path>/mnt/skills/public/docx/</path>
  </skill>
  <!-- ... -->
</available_skills>

The model reads this once per chat and then consults SKILL.md files on demand.

User skill mounts

User-uploaded skills (ZIPs from the Settings Wrapper) are:

Downloaded and extracted atomically: unzip to temp, rename to final.
Cached under /data/skills-cache/{name}/ on the host.
Tracked in .manifest.json (name → SHA-256 + timestamp).
Bind-mounted into the sandbox at /mnt/skills/user/{name}/ — read-only.

Stale cache reuse: if the API or download fails but old cache exists, use it. Docker daemon needs host paths for bind mounts — configured via SKILLS_CACHE_HOST_PATH.

Core functions (`skill_manager.py`)

Function	Purpose
`get_user_skills(email)`	Async — full resolution with all fallbacks
`get_user_skills_sync(email)`	Sync — reads cache only (called from the Docker-creation thread)
`ensure_skill_cached(skill)`	Download + extract user-uploaded ZIP
`build_available_skills_xml(skills)`	`<available_skills>` for the system prompt
`build_sub_agent_skills_text(skills)`	Skill list for the sub-agent prompt
`get_skill_mounts(skills)`	Dict of bind mounts for user skills

HTTP endpoints

Endpoint	Returns
`GET /system-prompt?user_email=X&chat_id=Y`	Rendered per-user prompt
`GET /skill-mounts?user_email=X`	Bind-mount descriptors for user skills
`GET /skill-list?user_email=X`	Formatted skill list for sub-agent prompts

Configuration

Var	Default	Purpose
`MCP_TOKENS_URL`	(empty)	Settings Wrapper URL
`MCP_TOKENS_API_KEY`	(empty)	Internal API key
`SKILLS_CACHE_DIR`	`/data/skills-cache`	In-container cache path
`SKILLS_CACHE_HOST_PATH`	`/tmp/skills-cache`	Host path for Docker mounts

Verify

# System prompt should list skills
curl "http://localhost:8081/system-prompt?user_email=admin@open-computer-use.dev&chat_id=test" | head -50

# Bind mounts
curl "http://localhost:8081/skill-mounts?user_email=admin@open-computer-use.dev"

# Skill list
curl "http://localhost:8081/skill-list?user_email=admin@open-computer-use.dev"

Getting started

Demo course

Yambr Platform

Self-hosting

Features

Skills

Integrations

Reference

Dynamic skills

Resolution pipeline

System prompt injection

User skill mounts

Core functions (`skill_manager.py`)

HTTP endpoints

Configuration

Verify

​Resolution pipeline

​System prompt injection

​User skill mounts

​Core functions (skill_manager.py)

​HTTP endpoints

​Configuration

​Verify

Resolution pipeline

System prompt injection

User skill mounts

Core functions (`skill_manager.py`)

HTTP endpoints

Configuration

Verify