agentleFS
Sign inStart free
weininghuiweininghui/skills/clawdbot-documentation-expert/SKILL.md

clawdbot-documentation-expert

Skill1 starsChanged 13 days agoMITView on GitHub

Use this skill when the user wants to learn about Clawdbot features, configuration, or troubleshooting. You become an expert on the Clawdbot documentation.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants to learn about Clawdbot features, configuration, or troubleshooting.

    line 10
  2. Distinctive:

    Always start by fetching the live sitemap to get up-to-date documentation:

    line 21
  3. Distinctive:

    When the user wants details on a topic, fetch it with the browser:

    line 86
  4. Distinctive:

    Always cite the specific doc URL when answering

    line 113
  5. Distinctive:

    If docs have changed, re-fetch the sitemap

    line 114

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

迁移说明:本技能原为 OpenClaw / ClawHub 生态技能,现已转为 WorkBuddy 技能规范。正文如出现 openclaw / clawhub / claw 命令或 ~/.openclaw 路径,请忽略该命令形式,改用 WorkBuddy 等价操作:技能目录 = ~/.workbuddy/skills/<name>/;装包用 pip / npm;联网用 WebSearch / WebFetch;读写文件用 Read / Write / Edit;执行命令用 Bash(Windows 走 PowerShell 工具)。

Clawdbot Documentation Expert

Use this skill when the user wants to learn about Clawdbot features, configuration, or troubleshooting. You become an expert on the Clawdbot documentation.

How to Use

  1. Fetch the sitemap to get the current documentation structure
  2. Present topic categories to the user
  3. Read specific docs based on user interest
  4. Answer follow-up questions with documentation references

Step 1: Fetch Current Sitemap

Always start by fetching the live sitemap to get up-to-date documentation:

curl -s https://docs.clawd.bot/sitemap.xml | grep -oP '(?<=<loc>)[^<]+' | sort

Step 2: Documentation Categories

The docs are organized into these main sections:

🚀 Getting Started (/start/)

  • getting-started, onboarding, setup, wizard, pairing
  • clawd, hubs, faq, lore, showcase

🔧 Gateway & Operations (/gateway/)

  • configuration, configuration-examples, authentication
  • health, heartbeat, logging, troubleshooting
  • remote, tailscale, sandboxing, security
  • doctor, discovery, bonjour, pairing

💬 Providers (/providers/)

  • discord, telegram, whatsapp, slack, signal
  • imessage, msteams, grammy
  • troubleshooting, location

🧠 Core Concepts (/concepts/)

  • agent, agent-loop, agent-workspace, multi-agent
  • session, sessions, session-tool, session-pruning
  • messages, group-messages, groups
  • models, model-providers, model-failover
  • queue, retry, streaming, typing-indicators
  • system-prompt, timezone, oauth, presence
  • architecture, compaction, usage-tracking

🛠️ Tools (/tools/)

  • bash, browser, skills, skills-config
  • elevated, reactions, slash-commands
  • subagents, thinking, clawdhub, agent-send

⚡ Automation (/automation/)

  • cron-jobs, webhook, poll
  • gmail-pubsub, auth-monitoring

💻 CLI (/cli/)

  • gateway, message, sandbox, update

📱 Platforms (/platforms/)

  • macos, linux, windows, ios, android, hetzner
  • Mac-specific: bundled-gateway, canvas, child-process, webchat, voice-overlay, voicewake, permissions, etc.

📡 Nodes (/nodes/)

  • camera, audio, images, location-command, talk, voicewake

🌐 Web (/web/)

  • webchat, dashboard, control-ui

📦 Install (/install/)

  • docker, ansible, bun, nix, updating

📚 Reference (/reference/)

  • AGENTS.default, RELEASING, rpc, device-models
  • Templates: AGENTS, BOOTSTRAP, HEARTBEAT, IDENTITY, SOUL, TOOLS, USER

Step 3: Read Specific Documentation

When the user wants details on a topic, fetch it with the browser:

Use pi_browser to navigate to the specific doc URL, then snapshot to read it.

Example URLs:

Workflow Example

User: "Tell me about Clawdbot"

You: Present the high-level categories above and ask which area interests them.

User: "I want to learn about Discord setup"

You: Navigate to https://docs.clawd.bot/providers/discord, read it, and explain the key points.

User: "How do I configure requireMention?"

You: Reference the specific section from the Discord docs and provide the config example.

Tips

  • Always cite the specific doc URL when answering
  • If docs have changed, re-fetch the sitemap
  • For complex topics, offer to read multiple related docs
  • Provide code/config examples directly from the docs

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free