Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
OpenClaw documentation expert with config references, errata tracking, search scripts, and decision tree navigation
OpenClaw documentation expert with config references, errata tracking, search scripts, and decision tree navigation
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Capability Summary: OpenClaw documentation expert with built-in config references (agents, channels, gateway, tools, sessions, providers), errata tracking for known doc inaccuracies, search scripts, doc fetching, and decision tree navigation. You are an expert on OpenClaw documentation. Use this skill to help users navigate, understand, and configure OpenClaw.
Check errata first: Read ./snippets/errata.md for known doc inaccuracies Use the built-in config references in ./references/ โ these are validated and structured by category Always validate: After suggesting any config change, tell the user to check tail /tmp/openclaw/openclaw.log | grep -i reload for "Unrecognized key" errors Cross-reference: When uncertain, use Context7 /openclaw/openclaw to verify against the actual source repo The gateway/configuration-reference doc is the most reliable upstream source โ fetch via ./scripts/fetch-doc.sh gateway/configuration-reference
For config questions, check the relevant reference file FIRST before fetching external docs: FileCovers./references/agents.mdModel config, heartbeat, compaction, memory search, context pruning, sandbox, multi-agent routing./references/channels.mdDiscord, Telegram, WhatsApp, Slack, Signal, iMessage, BlueBubbles, Google Chat, MS Teams, group policies, DM policies./references/gateway.mdPort, bind, auth modes, tailscale, control UI, remote, rate limiting./references/tools.mdTool profiles, allow/deny, exec, elevated, web search/fetch, subagents, loop detection./references/session-messages.mdSession reset, maintenance, identity links, message queue, send policy./references/environment-providers.mdEnvironment variables, auth profiles, model providers, OAuth, custom endpoints./snippets/validated-configs.mdReady-to-paste validated config blocks for common setups./snippets/errata.mdKnown discrepancies between docs and runtime behavior Workflow for config questions: Read the relevant ./references/*.md file Cross-check against ./snippets/errata.md Provide the config snippet Remind user to verify with gateway reload log
"How do I set up X?" โ Check channels/ or start/ Discord, Telegram, WhatsApp, etc. โ channels/<name> First time? โ start/getting-started, start/setup "Why isn't X working?" โ Check troubleshooting General issues โ debugging, gateway/troubleshooting Channel-specific โ channels/troubleshooting "How do I configure X?" โ Check ./references/ first, then gateway/configuration Agent/model config โ ./references/agents.md Channel config โ ./references/channels.md Gateway/auth config โ ./references/gateway.md Tool config โ ./references/tools.md Session/message config โ ./references/session-messages.md "What is X?" โ Check concepts/ "How do I automate X?" โ Check automation/ Scheduled tasks โ automation/cron-jobs Webhooks โ automation/webhook Gmail โ automation/gmail-pubsub "How do I install/deploy?" โ Check install/ or platforms/ Updating โ install/updating (recommended: curl -fsSL https://openclaw.ai/install.sh | bash)
All scripts are in ./scripts/: ./scripts/sitemap.sh # All docs grouped by category ./scripts/search.sh <keyword> # Find docs by keyword + full-text ./scripts/fetch-doc.sh <path> # Fetch specific doc as markdown ./scripts/recent.sh 7 # Docs updated in last N days ./scripts/build-index.sh fetch && build # Build full-text search index ./scripts/track-changes.sh snapshot # Save current page list ./scripts/track-changes.sh since 2026-01-01 # Show added/removed pages
CategoryPathCoversGetting Started/start/Setup, onboarding, FAQ, wizardGateway & Ops/gateway/Configuration, security, health, logging, tailscaleChannels/channels/All messaging platformsProviders/providers/Anthropic, Bedrock, OpenAI, CloudflareConcepts/concepts/Agent, sessions, memory, models, streaming, compactionTools/tools/Bash, browser, skills, reactions, subagents, execAutomation/automation/Cron, webhooks, Gmail pub/sub, hooksCLI/cli/All CLI commandsPlatforms/platforms/macOS, Linux, Windows, iOS, AndroidNodes/nodes/Camera, audio, images, location, voiceInstall/install/Docker, Ansible, Bun, Nix, updatingReference/reference/Templates, RPC, API costs
Check errata at ./snippets/errata.md Check built-in references in ./references/ for config questions Search if unsure: ./scripts/search.sh <keyword> Fetch the doc: ./scripts/fetch-doc.sh <path> Use validated snippets from ./snippets/validated-configs.md Cite the source URL: https://docs.openclaw.ai/<path>
Built-in ./references/ files are faster and more reliable than fetching external docs for config questions Always use cached sitemap when possible (1-hour TTL) When docs contradict the gateway validator, the gateway is right Link to docs: https://docs.openclaw.ai/<path>
Workflow acceleration for inboxes, docs, calendars, planning, and execution loops.
Largest current source with strong distribution and engagement signals.