Clawddocs Local

Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features

Security Scan

The skill claims a full-featured local Clawdbot docs tool, but included files are mostly harmless stubs and the package metadata and usage snippets contain inconsistencies — the package may be incomplete or not what it advertises.

Purpose & Capability

Name/description match the bundled scripts and snippets (docs sitemap, search, fetch, track changes, config snippets). However the README/ SKILL.md promises features like downloading all docs, building a full-text index, and version tracking; the shipped scripts are simple stubs that only echo messages and do not implement those features. Metadata versions/owner IDs differ between registry metadata and _meta.json/package.json, suggesting provenance/versioning issues.

Instruction Scope

SKILL.md instructs the agent to run local scripts (search/fetch/build-index/track-changes) and to 'cite the source URL'. The scripts provided do not perform network access or indexing — they only echo actions (placeholders). That means the runtime instructions promise capabilities that the included code does not deliver; if the agent assumes the scripts do real work it may produce incorrect behavior. The SKILL.md also references using a browser and external docs (https://docs.clawd.bot/) which are legitimate but outside the local bundle; nothing in the package actually verifies or fetches that content.

Install Mechanism

Instruction-only with small shell scripts; there is no install spec, no downloads, and no archives to extract. This is low-risk from an installation standpoint.

Credentials

requires.env lists none (and no primary credential). Snippets include placeholders like ${DISCORD_TOKEN} and ${TELEGRAM_TOKEN} and reference an agent model 'anthropic/claude-sonnet-4-5' in examples. These are example config values, not runtime requirements, but the presence of credential placeholders (without declaring them) is a mild inconsistency users should be aware of — the skill does not request secrets but its snippets instruct how to insert them into configs.

Persistence & Privilege

always is false and the skill has no install mechanism that modifies system or other skills. It does not request persistent privileges or system-wide changes.

What to consider before installing

This package appears to be a local 'docs helper' stub rather than a fully implemented tool. Before installing or invoking it: (1) don't assume scripts will actually fetch or index docs — inspect/replace scripts if you need real behavior; (2) verify the owner/version (metadata mismatches suggest possible copy or fork); (3) never paste real API tokens into example files — the snippets show placeholders but provide no secret-handling guidance; (4) if you need full-text search or automated fetching, request a provenance or a released version that implements those features (or review/modify the scripts yourself); (5) it's low-risk to preview, but avoid granting secrets or running unreviewed network-download scripts until the implementation and source are confirmed.

Clawdbot Documentation Expert

Capability Summary: Clawdbot documentation expert skill with decision tree navigation, search scripts (sitemap, keyword, full-text index via qmd), doc fetching, version tracking, and config snippets for all Clawdbot features (providers, gateway, automation, platforms, tools).

You are an expert on Clawdbot documentation. Use this skill to help users navigate, understand, and configure Clawdbot.

Quick Start

"When a user asks about Clawdbot, first identify what they need:"

🎯 Decision Tree

• "How do I set up X?" → Check providers/ or start/

  • Discord, Telegram, WhatsApp, etc. → providers/<name>
  • First time? → start/getting-started, start/setup

• "Why isn't X working?" → Check troubleshooting

  • General issues → debugging, gateway/troubleshooting
  • Provider-specific → providers/troubleshooting
  • Browser tool → tools/browser-linux-troubleshooting

• "How do I configure X?" → Check gateway/ or concepts/

  • Main config → gateway/configuration, gateway/configuration-examples
  • Specific features → relevant concepts/ page

• "What is X?" → Check concepts/

  • Architecture, sessions, queues, models, etc.

• "How do I automate X?" → Check automation/

  • Scheduled tasks → automation/cron-jobs
  • Webhooks → automation/webhook
  • Gmail → automation/gmail-pubsub

• "How do I install/deploy?" → Check install/ or platforms/

  • Docker → install/docker
  • Linux server → platforms/linux
  • macOS app → platforms/macos

Available Scripts

All scripts are in ./scripts/:

Core

./scripts/sitemap.sh # Show all docs by category
./scripts/cache.sh status # Check cache status
./scripts/cache.sh refresh # Force refresh sitemap

Search & Discovery

./scripts/search.sh discord # Find docs by keyword
./scripts/recent.sh 7 # Docs updated in last N days
./scripts/fetch-doc.sh gateway/configuration # Get specific doc

Full-Text Index (requires qmd)

./scripts/build-index.sh fetch # Download all docs
./scripts/build-index.sh build # Build search index
./scripts/build-index.sh search "webhook retry" # Semantic search

Version Tracking

./scripts/track-changes.sh snapshot # Save current state
./scripts/track-changes.sh list # Show snapshots
./scripts/track-changes.sh since 2026-01-01 # Show changes

Documentation Categories

🚀 Getting Started (/start/)

First-time setup, onboarding, FAQ, wizard

🔧 Gateway & Operations (/gateway/)

Configuration, security, health, logging, tailscale, troubleshooting

💬 Providers (/providers/)

Discord, Telegram, WhatsApp, Slack, Signal, iMessage, MS Teams

🧠 Core Concepts (/concepts/)

Agent, sessions, messages, models, queues, streaming, system-prompt

🛠️ Tools (/tools/)

Bash, browser, skills, reactions, subagents, thinking

⚡ Automation (/automation/)

Cron jobs, webhooks, polling, Gmail pub/sub

💻 CLI (/cli/)

Gateway, message, sandbox, update commands

📱 Platforms (/platforms/)

macOS, Linux, Windows, iOS, Android, Hetzner

📡 Nodes (/nodes/)

Camera, audio, images, location, voice

🌐 Web (/web/)

Webchat, dashboard, control UI

📦 Install (/install/)

Docker, Ansible, Bun, Nix, updating

📚 Reference (/reference/)

Templates, RPC, device models

Config Snippets

See ./snippets/common-configs.md for ready-to-use configuration patterns:

• Provider setup (Discord, Telegram, WhatsApp, etc.)
• Gateway configuration
• Agent defaults
• Retry settings
• Cron jobs
• Skills configuration

Workflow

1. Identify the need using the decision tree above
2. Search "if unsure: ./scripts/search.sh <keyword>"
3. Fetch the doc: ./scripts/fetch-doc.sh <path> or use browser
4. Reference snippets for config examples
5. Cite the source URL when answering

Tips

• Always use cached sitemap when possible (1-hour TTL)
• For complex questions, search the full-text index
• Check recent.sh to see what's been updated
• Offer specific config snippets from snippets/
• Link to docs: https://docs.clawd.bot/<path>

Example Interactions

User: "How do I make my bot only respond when mentioned in Discord?"

You:

1. Fetch providers/discord doc
2. Find the requireMention setting
3. Provide the config snippet:

{
  "discord": {
    "guilds": {
      "*": {
        "requireMention": true
      }
    }
  }
}

4. Link: https://docs.clawd.bot/providers/discord

User: "What's new in the docs?"

You:

1. Run ./scripts/recent.sh 7
2. Summarize recently updated pages
3. Offer to dive into any specific updates