openclaw-clawdoc

OpenClaw channel configuration. Use when setting up, auditing, or troubleshooting messaging channels: Discord, Telegram, WhatsApp, Slack, Signal, Matrix, iMessage, IRC, Feishu, LINE, GoogleChat, Mattermost, Microsoft Teams, Nextcloud Talk, Nostr, QQ Bot, Synology Chat, Twitch, Tlon, Zalo, Voice Call, Raft, ClickClack, plus location and qa-channel. (BlueBubbles was the prior iMessage path and is now removed; see references/bluebubbles.md for the migration guide.) Triggers on: channel config, dmPolicy, group policy, allowFrom, pairing, broadcast groups, channel pairing, matrix migration, push rules, raft consensus, location, setup channel, connect channel.

OpenClaw configuration expert and system doctor. Use for unclassified config questions that don't map to a more specific skill — for specific areas use their dedicated skills (see skill map below). Triggers on: openclaw expert, config doctor, system health, gateway diagnostics, openclaw master, openclaw overview, openclaw help.

OpenProse workflow language for OpenClaw. Use when running the /prose slash command or the open-prose plugin. Canonical docs: docs.openclaw.ai/prose. Triggers on: prose, openprose, /prose, .prose files, prose workflow, multi-agent workflow, parallel agents, agent orchestration.

OpenClaw model providers. Use when configuring LLM providers (60+ individual provider files tracked: OpenAI, Anthropic, Gemini, Bedrock, Ollama, DeepSeek, Groq, Together, Cerebras, xAI, Cohere, Deepgram, SenseAudio, Tencent, VolcEngine, and more), API keys, OAuth, auth profiles, model failover, API key rotation, billing disable backoff, and usage tracking. Triggers on: provider, model, API key, OAuth, Anthropic, OpenAI, Gemini, Bedrock, Ollama, failover, auth profile, billing disable, key rotation, Cohere, Deepgram, transcription, SenseAudio, speech to text, Tencent, VolcEngine, Doubao, voice provider, STT provider.

Guided first-run setup for ClawDoc (the docs/skills themselves), NOT for OpenClaw runtime first-run (use openclaw-start for that). Walks through installing ClawDoc skills, configuring docs sync, and end-to-end verification of the ClawDoc layer. Triggers on: "ClawDoc first run", "ClawDoc setup", "install ClawDoc", "ClawDoc getting started", "set up ClawDoc skills", "ClawDoc install verification".

OpenClaw multi-agent system. Use when setting up multiple agents, bindings, channel routing, per-agent sandbox, tool policies, ACP runtimes, workspace bootstrap, subagent limits, context pruning, or per-agent thinking/reasoning overrides. Also covers: multi-agent-sandbox-tools, qa-e2e-automation, session-tool reference docs. Triggers on: "multi-agent", "bindings", "routing", "agentId", "workspace", "sandbox", "tool policy", "per-agent", "ACP", "acp", "runtime", "bootstrap", "subagent", "sessions_spawn", "contextPruning", "thinkingDefault", "reasoningDefault", "fastModeDefault", "execApprovals", "sandbox mode", "sandbox scope".

Automation in OpenClaw — cron jobs, hooks, tasks, webhooks, poll, standing orders, Task Flow, Clawflow. Also covers: auth-monitoring, clawflow, commitments, cron-vs-heartbeat, standing-orders reference docs. Use when: scheduling recurring tasks, setting up cron jobs, configuring webhooks, reacting to events with hooks, running background tasks, orchestrating multi-step workflows, using standing orders to inject persistent instructions. Triggers on: "automation", "cron", "schedule", "webhook", "hook", "task", "background", "standing order", "recurring", "every x minutes", "task flow", "clawflow", "poll", "CI", "logging", "automation troubleshooting", "gmail", "pubsub", "gmail pubsub", "cron vs heartbeat", "scheduled task", "commitments", "auth monitoring", "clawflow workflow".

OpenClaw CLI commands reference. Use when explaining openclaw commands: openclaw status, openclaw gateway, openclaw plugins, openclaw memory, openclaw agents, openclaw channels, openclaw config, openclaw sessions, openclaw cron, openclaw hooks, openclaw pairing, openclaw acp. Triggers on: "openclaw CLI", "openclaw command", "openclaw status", "CLI", "command line", "openclaw hooks", "openclaw pairing", "policy", "conformance", "doctor lint", "taskflow", "troubleshooting", "automation troubleshooting", "automation".

OpenClaw core concepts. Use when explaining architecture, memory, sessions, compaction, streaming, multi-agent design, sandboxing, agent bootstrap, message flow, queue modes, model failover, system prompt, SOUL.md, timezone, OAuth flows, presence, the OpenClaw SDK, the database-first migration to SQLite, doctor migrations from legacy JSON stores, or the cache layer refactor. Triggers on: how does it work, architecture, session, compaction, streaming, bootstrap, context, queue, message flow, failover, features, retry, typebox, models, model-providers, usage-tracking, markdown, formatting, qa, matrix, rpc, adapters, OAuth, oauth flow, presence, user presence, agent presence, sdk, software development kit, OpenClaw SDK, openclaw sdk, programmatic access, sqlite, database first, database-first, migration, migrations.

OpenClaw gateway configuration reference. Use when auditing, editing, or troubleshooting openclaw.json. Covers ALL config keys: agents, channels, memory, tools, providers, session, messages, sandbox, plugins, env, model routing. Triggers on: "config", "openclaw.json", "configuration", "config reference", "config audit", "gateway config", "session config", "channel config", "runtime", "model routing", "env vars", "gateway won't start", "config error", "how to configure", "openclaw doctor", "pairing", "background process", "remote gateway", "auth", "credential", "SecretRef", "secretref", "usage tracking", "secrets plan", "credential surface", "gateway HTTP API", "telemetry", "prometheus", "opentelemetry", "multiple gateways". For gateway HTTP API, telemetry endpoints, secrets backend, sandbox policies, and gateway runtime: see also openclaw-gateway.

OpenClaw gateway operations and HTTP/API surface. Use when configuring gateway runtime, the OpenAI-compatible HTTP API, OpenResponses API, observability (OpenTelemetry, Prometheus), secrets, sandbox vs tool policy vs elevated, security audit, gateway troubleshooting, gateway exposure (Tailscale/runbook), or gateway-owned node pairing for iOS / remote nodes (Option B). Triggers on: gateway, gateway config, configuration, HTTP API, OpenAI compatible, OpenResponses, telemetry, OpenTelemetry, prometheus, metrics, secrets, secret resolution, sandbox, tool policy, elevated, security audit, security-audit-checks, exposure, Tailscale, runbook, doctor, diagnostic, CLI backends, config-agents, config-channels, config-tools, pairing, gateway-owned, gateway owned, gatewayowned, node pairing, node pairing flow, pairing option, pairing approval.

Help, FAQ, and testing for OpenClaw. Use when: looking up an everyday question about models, auth, or basic usage, finding a FAQ entry, running test suites (testing-live), running repo scripts under ./scripts, or asking "how do I…" in plain language. For deeper diagnostics use openclaw-troubleshooting instead. Triggers on: "help", "faq", "how do I", "how to", "common question", "everyday", "basic usage", "testing", "testing-live", "codex agentic parity", "scripts", "repository scripts".

Install, update, migrate, or uninstall OpenClaw. Use when: installing OpenClaw from scratch, deploying to Docker, Railway, Fly, GCP, Azure, Kubernetes, Hetzner, Podman, Bun, Nix, or from source; updating OpenClaw to a new version; migrating from another platform; uninstalling. Triggers on: "install", "update", "upgrade", "docker", "railway", "fly", "gcp", "azure", "kubernetes", "hetzner", "podman", "bun", "nix", "migration", "migrate", "uninstall", "from source", "stable channel", "beta channel", "dev channel", "installer", "release channel".

OpenClaw memory systems. Use when configuring memory backends (builtin, QMD, Honcho, sqlite-vec, pgvector), embedding providers, memory search (semantic, BM25, hybrid), active memory, dreaming, memory-wiki, citations, or recall. Triggers on: memory, memory search, memory backend, memory config, QMD, Honcho, sqlite-vec, pgvector, vector search, embedding, BM25, hybrid search, active memory, dreaming, memory wiki, citations, recall, semantic search, search memory, find in notes, what do you remember, query memory, configure Honcho, sqlite-vec setup, memory not working, search results wrong, embeddings broken, vector database not working, memory search not finding anything, how to set up memory, memory backend setup.

Pairing and using companion nodes (iOS, Android, macOS) with OpenClaw. Use when: pairing a phone or tablet as a node, using camera or canvas from an agent, VoiceWake, talk, audio input, location from a node, device notifications, screen sharing. Triggers on: "node", "pairing", "voicewake", "camera", "canvas", "audio", "talk", "location", "notifications", "screen", "android", "ios", "paired device", "media understanding", "inbound media".

OpenClaw on different platforms and operating systems. Use when: running OpenClaw on Android, iOS, macOS, Windows, Linux, Raspberry Pi, Oracle Cloud, or DigitalOcean. Triggers on: "android", "ios", "macos", "windows", "linux", "raspberry pi", "oracle", "digitalocean", "platform", "mac menu bar", "menu bar", "voice overlay".

OpenClaw plugin system. Use when installing, configuring, debugging, or building plugins; understanding plugin slots, capability model, plugin manifest, SDK entry points, hook system, or plugin allow/deny. Also covers the ClawHub public registry (publish, browse, install from clawhub CLI). Triggers on: plugin, plugins install, plugin slot, plugin config, extension, plugin manifest, plugin SDK, channel plugin, provider plugin, tool plugin, hook plugin, building plugins, plugin capability, plugin allow list, plugin shape, ClawHub, clawhub CLI, clawhub auth, publish skill, publish plugin, registry, browse plugins, install from ClawHub, npm install, plugin not loading, plugin conflict, disabled plugin, plugin API, openclaw plugins, policy, conformance, openshell, codex harness, codex supervisor, exec approvals, memory wiki, browser login, context engine, plugin slots.

General OpenClaw reference docs. Use when looking for conceptual reference material that doesn't map to a specific skill: token usage, transcript hygiene, session compaction, rich output protocol, SecretRef credential surface, application modernization plan, releasing OpenClaw, or prompt caching (knobs, merge order, per-agent cache behavior, cache-ttl tuning). Triggers on: "token", "transcript", "session compaction", "rich output", "SecretRef", "credentials", "releasing", "application plan", "release validation", "release stages", "CI pipeline", "CI", "prompt caching", "prompt-caching", "prompt cache", "cache retention", "cache-ttl", "cache ttl", "merge order", "knobs".

First run, bootstrapping, and onboarding OpenClaw. Use when: running OpenClaw for the first time, using the setup wizard, configuring the workspace, bootstrapping an agent, understanding the onboarding flow, using openclaw onboard CLI. Triggers on: "start", "bootstrap", "onboarding", "wizard", "first run", "getting started", "setup", "onboard", "initial", "new install", "fresh install", "how do I start", "where do I begin".

OpenClaw tools reference. Use when explaining, configuring, or troubleshooting tools: exec, browser, cron, sessions, subagents, ACP, Lobster, slash commands, /prose, OpenProse, thinking, tool permissions, sandbox, loop detection, LLM task, search providers, media generation. Triggers on: tools, exec, browser, cron, sessions, subagent, canvas, slash commands, /prose, openprose, prose workflow, loop detection, elevated, exec approvals, ACP, thinking, permissions, webhook, clawflow, code execution, auth monitoring, tool profile, search providers, image generation, music generation, video generation, media tools, creating skills, btw, steer, gmail, pubsub, gmail pubsub, poll, polling.

OpenClaw web UI. Use when configuring the web dashboard, TUI terminal interface, webchat, or control UI. Triggers on: "web", "dashboard", "TUI", "terminal", "webchat", "control UI", "web UI", "browser", "localhost:18789".

ClawHub public registry for OpenClaw skills and plugins. Use when discovering, installing, publishing, verifying, or updating ClawHub packages; using the clawhub CLI; understanding package scopes, owners, and reviews; or browsing the registry at clawhub.ai. Triggers on: clawhub, clawhub CLI, clawhub login, clawhub publish, publish skill, publish plugin, registry, browse skills, browse plugins, install from clawhub, clawhub transfer, clawhub sync, package scope, owner scope, clawhub review, clawhub install, clawhub update, clawhub verify, skill marketplace, plugin marketplace.

OpenClaw troubleshooting and fixes. Use when diagnosing gateway crashes, config errors that other skills can't resolve, plugin conflicts after config checks pass, ACP agent failures, pairing/device pairing, hook not firing, lock file issues, secret resolution failures, or queue/backpressure problems. For everyday FAQ-style questions use openclaw-help instead. Triggers on: config error, crash, debug, troubleshoot, diagnose, pairing failure, device pairing, hook failure, lock file, queue, backpressure, secret not resolving, plugin conflict, openclaw doctor, gateway locked, ACP agent won't start, channel silent, hook not firing, debugging tools, hooks, testing kit, troubleshooting flow, diagnostic flowchart.

OpenClaw logging configuration. Use when configuring log levels, log rotation, log destinations, log format, or debugging OpenClaw log output. Triggers on: "logging", "log level", "log rotation", "log format", "logs", "debug", "output", "logger", "syslog", "file logging".