LaunchKit · 2026
Back to Skills

clawd-docs-v2

Smart ClawdBot documentation access with local search index.

14
4.6k downloads
by @aranej

Setup & Installation

openclaw skills install @aranej/clawd-docs-v2

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install clawd-docs-v2

Version History

v2.2.0Jan 26, 2026 - Version note by skill developer:

MAJOR: Migrated from brightdata to native web_fetch tool - zero cost documentation access! Removed mcporter dependency. Added curl-based refresh script.

What This Skill Does

Provides access to ClawdBot documentation through a 3-layer system: pre-cached golden snippets, a local search index, and on-demand page fetching. Common queries are answered from local files to minimize token usage. TTL-based freshness tracking determines when cached content should be refreshed.

Serving 80-90% of queries from pre-cached local snippets costs 0 tokens, compared to 8-12k tokens per full page fetch.

When to use it

  • Looking up Telegram channel setup steps
  • Troubleshooting OAuth token expiry errors
  • Checking how to update ClawdBot
  • Configuring a new messaging provider
  • Finding memory and vector search documentation

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: How do I set up Telegram?

AGENT
  1. 1Check ~/clawd/data/docs-snippets/ for a telegram-setup.md snippet
  2. 2Read the cached snippet from disk (0 tokens consumed)
  3. 3Return setup instructions from the cached content
OUTPUT

Telegram setup instructions served from local cache without any web fetch