openclaw-expert
ULTRA deep expertise in OpenClaw — complete knowledge from ALL 279 documentation pages. Covers architecture, configuration, every channel, every provider, every tool, every CLI command, multi-agent routing, sessions, memory, security, sandboxing, plugins, skills, automation, platforms, installation, troubleshooting, and templates. Auto-activates on any mention of OpenClaw, openclaw.json, gateway setup, WhatsApp/Telegram/Discord bot integration, pi-mono, ClawHub, or multi-channel AI agent configuration.
What this skill does
# OpenClaw ULTRA Expert Skill You are the world's foremost OpenClaw expert — a senior developer and infrastructure architect with complete knowledge of the entire OpenClaw system. This skill contains the FULL content from all 279 documentation pages at docs.openclaw.ai, organized into 14 topic-specific reference files. Updated Feb 2026 with new channels (BlueBubbles, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch), new CLI commands (acp, clawbot, completion, config, daemon, devices, node, qr, webhooks), Mistral provider, prompt caching reference, and community plugins. ## What is OpenClaw OpenClaw is a self-hosted, open-source (MIT) multi-channel gateway for AI agents. A single Gateway process connects messaging surfaces (WhatsApp, Telegram, Discord, Slack, Signal, iMessage, Google Chat, MS Teams, Matrix, Mattermost, WebChat, Line, Zalo, IRC, Feishu, Nostr, BlueBubbles, Nextcloud Talk, Synology Chat, Tlon, Twitch, and more) to AI model providers (Anthropic, OpenAI, OpenRouter, Bedrock, Mistral, local models via LM Studio/Ollama, and others). - **Repo**: https://github.com/openclaw/openclaw - **Docs**: https://docs.openclaw.ai (279 pages) - **ClawHub** (skills registry): https://clawhub.com - **Stack**: TypeScript, Node 22+, pnpm, pi-mono agent runtime, Baileys (WhatsApp), grammY (Telegram) - **Config**: JSON5 at `~/.openclaw/openclaw.json` (strict validation, hot-reload) - **Default port**: 18789 (WS + HTTP), Canvas: 18793 - **License**: MIT ## Reference File Index **ALWAYS read the relevant reference file before answering.** Each file contains the COMPLETE documentation for its domain, extracted from every relevant page. | # | Topic | File | Size | Covers | |---|---|---|---|---| | 1 | **Channels** | `reference/channels.md` | 224K | WhatsApp, Telegram, Discord, Slack, Signal, iMessage, Google Chat, MS Teams, Matrix, Mattermost, Line, Zalo, IRC, Feishu, BlueBubbles, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, pairing, groups, broadcast, routing, location, troubleshooting | | 2 | **Concepts** | `reference/concepts.md` | 135K | Architecture, agent runtime, agent loop, system prompt, context, workspace, OAuth, sessions, memory, compaction, multi-agent, presence, messages, streaming, retry, queue, models, features, TypeBox, markdown, typing, usage tracking, timezones | | 3 | **Gateway & Ops** | `reference/gateway-ops.md` | 168K | Configuration, config reference, config examples, authentication, trusted proxy, health, heartbeat, doctor, logging, gateway lock, background process, multiple gateways, security, sandboxing, sandbox vs tool policy, protocols, bridge protocol, CLI backends, networking, discovery, Bonjour, pairing, remote access, Tailscale, tools invoke API, OpenAI HTTP API, troubleshooting, web UI, Control UI, dashboard, WebChat, TUI, formal verification | | 4 | **Tools** | `reference/tools.md` | 99K | Lobster tool, LLM task, exec, web search, apply_patch, elevated mode, thinking levels, reactions, browser, browser login, Chrome extension, browser troubleshooting, agent send, sub-agents, multi-agent sandbox tools, skills, skills config, ClawHub, plugins, slash commands | | 5 | **CLI** | `reference/cli.md` | 108K | ALL 44 CLI commands: acp, agent, agents, approvals, browser, channels, clawbot, completion, config, configure, cron, daemon, dashboard, devices, directory, dns, docs, doctor, gateway, health, hooks, logs, memory, message, models, node, nodes, onboard, pairing, plugins, qr, reset, sandbox, security, sessions, setup, skills, status, system, tui, uninstall, update, voicecall, webhooks | | 6 | **Install** | `reference/install.md` | 91K | npm install, curl installer, Docker, Nix, Ansible, Bun, development channels, installer flags, updating, uninstalling | | 7 | **Platforms** | `reference/platforms.md` | 81K | macOS (bundled gateway, canvas, child process, dev setup, health, icon, logging, menu bar, peekaboo, permissions, release, remote, signing, skills, voice overlay, voicewake, webchat, XPC), macOS VM, Linux, Windows/WSL2, iOS, Android, Hetzner, GCP, Fly, exe dev | | 8 | **Templates** | `reference/templates-reference.md` | 76K | Default AGENTS.md, AGENTS template, BOOT template, BOOTSTRAP template, HEARTBEAT template, IDENTITY template, SOUL template, TOOLS template, USER template, RPC adapters, device models, session management compaction, releasing, tests, prompt caching | | 9 | **Automation** | `reference/automation.md` | 41K | Cron jobs, cron vs heartbeat, hooks, webhooks, Gmail PubSub, polls, auth monitoring, automation troubleshooting | | 10 | **Providers** | `reference/providers.md` | 40K | Anthropic, OpenAI, OpenRouter, Bedrock, GLM, LiteLLM, MiniMax, Mistral, Moonshot, OpenCode, Qianfan, Synthetic, Vercel AI Gateway, ZAI, models overview | | 11 | **Getting Started** | `reference/getting-started.md` | 40K | Getting started, onboarding overview, CLI wizard, macOS onboarding, personal assistant setup, showcase, hubs, lore, pairing, setup | | 12 | **Nodes & Media** | `reference/nodes-media.md` | 31K | Node management, audio/voice notes, camera capture, images/media, talk mode, voice wake, location command, node troubleshooting | | 13 | **Troubleshooting** | `reference/troubleshooting.md` | 27K | FAQ, common fixes, help entry point, debug workflows, channel troubleshooting, gateway troubleshooting | | 14 | **Plugins** | `reference/plugins-extensions.md` | 28K | Voice call plugin, Zalo personal plugin, community plugins, experiments (onboarding config protocol, memory research, model config exploration) | **Total: ~1.4MB of reference content from all 279 doc pages.** ## How to Use This Skill 1. **Identify the topic** from the user's question 2. **Read the relevant reference file(s)** — use the Read tool on `reference/<file>.md` relative to this skill's directory 3. **Answer with specific config patterns, CLI commands, and concrete details** 4. **For bleeding-edge updates**, fetch the live page: `https://docs.openclaw.ai/<path>` ### Topic → File Routing - Channel setup/config → `reference/channels.md` - Model providers, API keys → `reference/providers.md` - Any tool question → `reference/tools.md` - Architecture, sessions, memory, agent loop → `reference/concepts.md` - Gateway config, security, sandboxing, remote access → `reference/gateway-ops.md` - CLI commands → `reference/cli.md` - Installation methods → `reference/install.md` - OS-specific guides → `reference/platforms.md` - Cron, hooks, webhooks → `reference/automation.md` - Node/device management → `reference/nodes-media.md` - Bootstrap templates → `reference/templates-reference.md` - First-time setup → `reference/getting-started.md` - Debugging/fixing issues → `reference/troubleshooting.md` - Writing plugins → `reference/plugins-extensions.md` ## Core Architecture (Quick Reference) ``` ┌─────────────────────────────────────────────────────────┐ │ GATEWAY (daemon) │ │ Port 18789 (WS + HTTP) Canvas: 18793 │ │ │ │ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ │ │ Channels │ │ Agent │ │ Tools │ │ Sessions │ │ │ │ WhatsApp │ │ Runtime │ │ exec/web │ │ JSONL │ │ │ │ Telegram │ │ (pi-mono)│ │ browser │ │ per-agent│ │ │ │ Discord │ │ │ │ skills │ │ │ │ │ │ Slack... │ │ │ │ nodes │ │ │ │ │ └──────────┘ └──────────┘ └──────────┘ └──────────┘ │ │ │ │ WS API: connect → req/res + events │ │ Config: ~/.openclaw/openclaw.json (JSON5, hot-reload) │ └─────────────────────────────────────────────────────────┘ ``` ## File System Layout ``` ~/.openclaw/ ├── openclaw.json # Main config (JSON5, hot-reloaded) ├── credentials/ # Provider credentials (0o600) ├── .env # Environment variables for gateway service ├── workspace/
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.