繁體中文 | English

This is an Agent Skill designed for AI coding assistants (like Claude with Antigravity). Once installed, the AI assistant gains deep knowledge of OpenClaw and can help you with:

• Installation & Updates — Install, upgrade, or migrate OpenClaw
• Configuration — Edit openclaw.json, set up models, manage secrets
• Channel Management — Set up WhatsApp, Telegram, Discord, Slack, iMessage, and 15+ other channels
• Gateway Operations — Start, stop, restart, health check, remote access
• Multi-Agent Routing — Configure multiple agents with isolated workspaces and sessions
• ACP Agents — Spawn external AI runtimes (Codex, Claude Code, Gemini CLI, 14+ harnesses)
• Browser Automation — Multi-profile browser control, Chrome MCP existing-session, snapshots
• Plugin System — Capability model, context engine plugins, SDK, hook API
• Automation — Cron jobs, standing orders, background tasks, webhooks, hooks
• Security Hardening — Audit, lock down access, manage tokens, trusted proxy, incident response
• Troubleshooting — Diagnose and fix common errors from CLI and Gateway

openclaw-docs-skill/
├── SKILL.md                     # Main entry (370 lines of expert workflows, commands, troubleshooting)
├── scripts/
│   └── sync-docs.sh             # Sync Engine — pulls latest docs from upstream
├── .github/
│   └── workflows/
│       └── auto-sync.yml        # GitHub Action — daily auto-sync at 04:00 UTC
└── references/                  # 400+ Markdown files (The Knowledge Base)
    ├── channels/                # Per-channel setup (WhatsApp, Telegram, Discord, etc.)
    ├── tools/                   # All built-in tools (Browser, Search, Exec, ACP, etc.)
    ├── plugins/                 # Plugin architecture and SDK
    ├── providers/               # 35+ model providers (Anthropic, OpenAI, Google, Ollama, etc.)
    ├── concepts/                # Core concepts: agent loop, memory, queue, streaming
    ├── gateway/                 # Gateway config, operations, security, sandboxing
    ├── security/                # Security hardening policies
    ├── nodes/                   # Nodes (iOS/Android/macOS/headless)
    ├── automation/              # Cron jobs, webhooks, background tasks, standing orders
    ├── install/                 # Installation, updating, rollback, migration, uninstall
    ├── platforms/               # Platform guides (macOS, iOS, Android, Linux, Windows)
    ├── web/                     # Web surfaces: Dashboard, Control UI, WebChat, TUI
    ├── diagnostics/             # Troubleshooting and failure walkthroughs
    └── cli/                     # CLI reference

Recommended install:

bash -c 'tmpdir=$(mktemp -d) && git clone https://github.com/tbdavid2019/openclaw-docs-skill.git "$tmpdir/openclaw-docs-skill" && bash "$tmpdir/openclaw-docs-skill/scripts/install-skill.sh" ~/.gemini/antigravity/skills/openclaw-docs'

Or, if you already cloned it into the final destination:

git clone https://github.com/tbdavid2019/openclaw-docs-skill.git ~/.gemini/antigravity/skills/openclaw-docs
bash ~/.gemini/antigravity/skills/openclaw-docs/scripts/install-skill.sh ~/.gemini/antigravity/skills/openclaw-docs

To update an installed checkout later:

bash ~/.gemini/antigravity/skills/openclaw-docs/scripts/install-skill.sh ~/.gemini/antigravity/skills/openclaw-docs

The skill will be automatically detected and triggered when you ask about OpenClaw-related tasks.

Whether an installed copy auto-refreshes depends on the host LLM platform. If the platform keeps the skill as a git checkout and allows shell execution, it can try git pull before use. If the platform copies files into a managed skills directory, the installed copy will not self-update unless that platform provides its own update mechanism.

If an AI assistant did not run scripts/install-skill.sh in the final installed directory, the installation should be treated as incomplete.

The SKILL.md and references/ files contain structured documentation that can be adapted for any AI assistant that supports skill/knowledge injection.

Once installed, just ask naturally:

# Status & Health
openclaw status                    # Overall status
openclaw gateway status            # Gateway daemon status
openclaw doctor                    # Diagnose issues
openclaw channels status --probe   # Channel health

# Gateway Management
openclaw gateway install           # Install as system service
openclaw gateway start/stop/restart
openclaw gateway --force           # Kill existing and restart

# Configuration
openclaw config get <path>         # Read config value
openclaw config set <path> <value> # Set config value
openclaw configure                 # Interactive wizard

# Security
openclaw security audit            # Check security posture
openclaw security audit --fix      # Auto-fix issues
openclaw secrets reload            # Reload secret refs

# Channels
openclaw channels add              # Add channel (wizard)
openclaw channels login            # WhatsApp QR pairing
openclaw channels list             # Show configured channels

# Models
openclaw models set <model>        # Set default model
openclaw models status --probe     # Check auth status

This skill's references/ folder is synced from the official OpenClaw repository. To get the latest docs:

sh scripts/sync-docs.sh

Or trigger the Auto-Sync Documentation workflow in the GitHub Actions tab.

The GitHub Action runs automatically every day at 04:00 UTC — no manual intervention needed.

This skill's knowledge base is built from the official OpenClaw Documentation, covering:

• Install
• Gateway Architecture
• Channels
• Model Providers
• Tools
• Plugin Architecture
• Multi-Agent Routing
• Security
• Troubleshooting
• CLI Reference

Issues and PRs welcome! Contributions that improve:

• SKILL.md — the agent's reasoning and diagnostic logic
• scripts/sync-docs.sh — the sync engine efficiency
• references/ — curated documentation quality

┌─────────────────────────────────────────────────┐
│           openclaw/openclaw (官方源頭)            │
│              /docs 資料夾每日更新                  │
└────────────────────┬────────────────────────────┘
                     │ GitHub Action 每日 04:00 UTC
                     ▼
┌─────────────────────────────────────────────────┐
│    tbdavid2019/openclaw-docs-skill              │
│    400+ 個最新文件永遠保持同步                      │
└────────────────────┬────────────────────────────┘
                     │ 使用者 git clone 一次
                     ▼
┌─────────────────────────────────────────────────┐
│   LLM 本地 Skill (~/.gemini/.../openclaw-docs)  │
│   每次被呼叫 → 自動 git pull → 永遠最新           │
│   使用者無需任何手動操作                            │
└─────────────────────────────────────────────────┘

AGPL-3.0 — Any derivative work must also be open-sourced under the same license. OpenClaw documentation is sourced from the official OpenClaw repository.

Special thanks to win4r/OpenClaw-Skill — the original inspiration for this project.

Their pioneering work on structuring OpenClaw knowledge as an Agent Skill showed what was possible. This repository builds on that idea by adding an auto-sync engine and daily GitHub Actions to ensure the documentation never goes stale.