openclaw-docs-sync
Sync OpenClaw + ClawHub + Skills docs into a local mirror for the QMD memory backend.
Best use case
openclaw-docs-sync is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sync OpenClaw + ClawHub + Skills docs into a local mirror for the QMD memory backend.
Teams using openclaw-docs-sync should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/openclaw-docs-sync/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How openclaw-docs-sync Compares
| Feature / Agent | openclaw-docs-sync | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Sync OpenClaw + ClawHub + Skills docs into a local mirror for the QMD memory backend.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# OpenClaw Docs Sync
## Purpose
Keep a local mirror of the OpenClaw framework docs, ClawHub CLI/docs, and the Skills repository. OpenClaw's built-in QMD memory backend indexes these docs for hybrid semantic search.
## When to use
Use this skill when the agent needs **fresh documentation** or **precise references** from:
- OpenClaw framework docs
- ClawHub CLI/docs
- Skills repo (all `SKILL.md` files)
## Setup
### Step 1: Run the sync script
Run the script whenever you need a fresh mirror:
```bash
# Recommended (portable)
npx tsx scripts/sync-docs.ts
# Or with Bun (fastest)
bun run scripts/sync-docs.ts
```
What it does:
- Mirrors OpenClaw `docs/` into `~/.openclaw/docs/openclaw-docs/`
- Mirrors ClawHub `docs/` into `~/.openclaw/docs/clawhub-docs/`
- Mirrors Skills `skills/` into `~/.openclaw/docs/openclaw-skills/`
- Runs security scans on downloaded content
### Step 2: Add to openclaw.json
After syncing, add the path to your `openclaw.json` config using `memory.qmd.paths`:
```json
{
"memory": {
"backend": "qmd",
"citations": "auto",
"qmd": {
"includeDefaultMemory": true,
"update": { "interval": "5m" },
"paths": [
{
"name": "openclaw-docs",
"path": "~/.openclaw/docs",
"pattern": "**/*.{md,mdx}"
}
]
}
}
}
```
## How the agent uses synced docs
Once configured in `openclaw.json`, OpenClaw's QMD memory backend automatically:
1. **Indexes** the synced docs on startup and at regular intervals (default 5m)
2. **Embeds** chunks for hybrid search (BM25 + vectors + reranking)
3. **Searches** via `memory_search` tool when you ask questions
4. **Retrieves** exact file content via `memory_get` tool
The agent will cite sources like:
```
Source: qmd/openclaw-docs/concepts/memory.md#L45-L52
```
## Repo structure in synced mirror
```
~/.openclaw/docs/
├── openclaw-docs/ # OpenClaw framework docs
├── clawhub-docs/ # ClawHub CLI docs
└── openclaw-skills/ # All SKILL.md files from skills repo
```
## Notes
- The sync script only ingests `.md` and `.mdx` files
- Synced docs are read-only; edit upstream repos to update
- Security scans run automatically; threats logged to `~/.openclaw/security-scan.log`
- See [QMD Backend docs](https://docs.openclaw.ai/concepts/memory#qmd-backend-experimental) for full configuration optionsRelated Skills
write-docs
Write documentation with real, validated examples. Executes commands through the user to capture actual output. Use for any new documentation or major doc updates.
wiki-docs
Document custom Magento 2 site functionality in the project wiki. Systematically captures custom features, modules, configurations, and business logic for client handover and developer onboarding.
update-docs
Update documentation pages to match source code changes on the current branch
update-docs-and-commit
Updates documentation files (changelog, architecture, project_status) based on git changes, then stages and commits all changes. Use after completing features or fixes.
three-tier-docs
Use after code changes. Syncs CLAUDE.md, CONTEXT.md, and docs/ai-context/ automatically.
sync-docs
Strategic documentation sync - review docs before implementation (pull context) OR export learnings after implementation (push to living docs). NOT bidirectional - two separate one-way operations at different phases.
smart-pr-docs
Intelligent PR documentation generator that analyzes code changes, tracks ripple effects across the codebase, updates claude.md files, and creates visual dependency maps. USE WITH codebase-architecture-mapper for elite "System-Aware" context.
skill-sync-checker
Detects content drift between skill files and their source documents. Helps maintain skills that are derived from other documentation by comparing content and flagging outdated sections.
review-docs
Review documentation (README.md and CLAUDE.md) for quality, completeness, and consistency. Use when asked to review docs, check documentation, validate README files, or audit CLAUDE.md coverage.
reindex-docs
Re-index all PDF and HTML documents, update index.html, and commit/push changes to the repository
pitchdocs-suite
One-command generation and audit of the full public repository documentation set — README, CHANGELOG, ROADMAP, CONTRIBUTING, CODE_OF_CONDUCT, SECURITY, issue templates, PR template, and discussion templates. Use when setting up a new repo or auditing an existing one.
organize-agent-docs
Organize project agentic documentation into universal (AGENTS.md) and agent-specific files (CLAUDE.md, GEMINI.md, etc.). Use when asked to "organize agent docs", "separate agent instructions", "restructure AGENTS.md", or when a project has agent documentation that mixes universal and tool-specific content.