LeoYeAI/agent-master-skills / skills/bengii-gemini-fix
openclaw
FlaggedComprehensive guide for installing, configuring, operating, and troubleshooting OpenClaw β a self-hosted, multi-channel AI agent gateway. Use when the user asks about OpenClaw setup, configuration, channel management (WhatsApp/Telegram/Discord/Slack/iMessage/etc.), model provider setup, Gateway operations, multi-agent routing, security hardening, troubleshooting, or any maintenance task related to their local OpenClaw installation. Also use when encountering errors from `openclaw` CLI commands or the Gateway daemon.
README.md
View on GitHub# OpenClaw Agent Skill π¦
[δΈζζζ‘£](README_CN.md) | English
A comprehensive **Agent Skill** for installing, configuring, operating, and troubleshooting [OpenClaw](https://github.com/openclaw/openclaw) β a self-hosted, multi-channel AI agent gateway.
## What is This?
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:
- π§ **Installation & Updates** β Install, upgrade, or migrate OpenClaw
- βοΈ **Configuration** β Edit `openclaw.json`, set up models, manage secrets
- π‘ **Channel Management** β Set up WhatsApp, Telegram, Discord, Slack, iMessage, and 15+ other channels
- π **Gateway Operations** β Start, stop, restart, health check, remote access
- π€ **Multi-Agent Routing** β Configure multiple agents with isolated workspaces and sessions
- π **Security Hardening** β Audit, lock down access, manage tokens and secrets
- π **Troubleshooting** β Diagnose and fix common errors from CLI and Gateway
## Skill Structure
```
OpenClaw-Skill/
βββ SKILL.md # Main entry (core workflows, commands, troubleshooting)
βββ references/
βββ architecture.md # Gateway architecture, wire protocol, pairing, invariants
βββ agent_runtime.md # Agent runtime, bootstrap, agent loop, hooks, timeouts
βββ bonjour.md # Bonjour/mDNS: TXT keys, wide-area DNS-SD, debugging
βββ channel_routing.md # Channel routing, session keys, Mattermost, BlueBubbles
βββ channels.md # 20+ channel setup guides (WhatsApp, Telegram, Discord, etc.)
βββ clawhub.md # ClawHub public skill registry, CLI commands
βββ gateway_internals.md # Network model, lock, health, doctor, logging, background exec
βββ gateway_ops.md # Gateway operations, service management
βββ heartbeat.md # Heartbeat: config, delivery, visibility, HEARTBEAT.md
βββ media.md # Media: camera capture, images, audio/voice notes, transcription
βββ memory.md # Memory system, vector search, hybrid BM25, QMD backend
βββ model_failover.md # Model failover, OAuth, auth profiles, cooldowns
βββ multi_agent.md # Multi-agent routing, bindings, per-agent config
βββ pairing.md # Gateway pairing: node approval, CLI, API, auto-approval
βββ polls.md # Polls (Telegram, WhatsApp, Discord, MS Teams)
βββ presence_discovery.md # Presence system, discovery (Bonjour/Tailscale)
βββ providers.md # 20+ model providers (Anthropic, OpenAI, Ollama, etc.)
βββ queue.md # Command queue: steer/followup/collect modes
βββ security.md # Auth, access control, hardening baseline
βββ streaming.md # Block streaming, chunking, coalescing, preview modes
βββ thinking.md # Thinking levels, verbose directives, reasoning visibility
βββ tui.md # TUI: keyboard shortcuts, slash commands, pickers, local shell
βββ voice.md # Talk Mode (voice interaction) + Voice Wake (wake words)
βββ ... (51 reference files total)
```
**Total: ~5,500+ lines** of structured reference covering all core OpenClaw functionality.
## Installation
### For Antigravity (Claude)
Copy the skill folder to your Antigravity skills directory:
```bash
# Clone this repo
git clone https://github.com/win4r/OpenClaw-Skill.git
# Copy to your skills directory
cp -r OpenClaw-Skill ~/.gemini/antigravity/skills/openclaw
```
The skill will be automatically detected and triggered when you ask about OpenClaw-related tasks.
### For Other AI Assistants
The `SKILL.md` and `references/` files contain structured documentation that can be adapted for any AI assistant that supports skill/knowledge injection.
## Usage Examples
Once installed, just ask naturally:
| What You Say | What the AI Does |
|---|---|
| "Help me upgrade OpenClaw" | Runs `npm install -g openclaw@latest`, `openclaw doctor`, restarts Gateway, verifies |
| "Set up a Telegram bot" | Walks through bot creation, token setup, config, and verification |
| "Gateway is not responding" | Runs diagnostic command ladder: status β logs β doctor β channels probe |
| "Lock down my OpenClaw security" | Runs security audit, applies hardened baseline, fixes permissions |
| "Add a second agent for work" | Creates agent, sets up workspace, configures bindings, restarts |
| "EADDRINUSE error" | Identifies port conflict, runs `openclaw gateway --force` or changes port |
## Key Commands Quick Reference
```bash
# 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
# 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
```
## Documentation Source
This skill is built from the official [OpenClaw Documentation](https://docs.openclaw.ai/), covering:
- [Install](https://docs.openclaw.ai/install)
- [Gateway Architecture](https://docs.openclaw.ai/concepts/architecture)
- [Agent Runtime](https://docs.openclaw.ai/concepts/agent)
- [Agent Loop](https://docs.openclaw.ai/concepts/agent-loop)
- [Configuration](https://docs.openclaw.ai/gateway/configuration)
- [Channels](https://docs.openclaw.ai/channels)
- [Model Providers](https://docs.openclaw.ai/providers)
- [Model Failover & OAuth](https://docs.openclaw.ai/concepts/model-failover)
- [Tools](https://docs.openclaw.ai/tools)
- [Thinking Levels](https://docs.openclaw.ai/tools/thinking)
- [Command Queue](https://docs.openclaw.ai/concepts/queue)
- [Streaming & Chunking](https://docs.openclaw.ai/concepts/streaming)
- [Memory & Vector Search](https://docs.openclaw.ai/concepts/memory)
- [ClawHub Registry](https://docs.openclaw.ai/tools/clawhub)
- [Multi-Agent Routing](https://docs.openclaw.ai/concepts/multi-agent)
- [Talk Mode & Voice Wake](https://docs.openclaw.ai/nodes/talk)
- [Polls](https://docs.openclaw.ai/automation/poll)
- [Presence & Discovery](https://docs.openclaw.ai/concepts/presence)
- [ACP Agents](https://docs.openclaw.ai/pi)
- [Security](https://docs.openclaw.ai/gateway/security)
- [Troubleshooting](https://docs.openclaw.ai/gateway/troubleshooting)
- [CLI Reference](https://docs.openclaw.ai/cli)
## License
This skill is provided as-is for use with AI assistants. OpenClaw itself is [MIT licensed](https://github.com/openclaw/openclaw/blob/main/LICENSE).
## Contributing
Issues and PRs welcome! If OpenClaw releases new features or changes, feel free to update the reference files accordingly.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |