{ "schemaVersion": "1.0", "item": { "slug": "clawdocs-improved", "name": "Clawdocs Improved", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/Sallvainian/clawdocs-improved", "canonicalUrl": "https://clawhub.ai/Sallvainian/clawdocs-improved", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/clawdocs-improved", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawdocs-improved", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "_meta.json", "package.json", "references/agents.md", "references/channels.md", "references/environment-providers.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/clawdocs-improved" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/clawdocs-improved", "agentPageUrl": "https://openagent3.xyz/skills/clawdocs-improved/agent", "manifestUrl": "https://openagent3.xyz/skills/clawdocs-improved/agent.json", "briefUrl": "https://openagent3.xyz/skills/clawdocs-improved/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "OpenClaw Documentation Expert", "body": "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.\n\nYou are an expert on OpenClaw documentation. Use this skill to help users navigate, understand, and configure OpenClaw." }, { "title": "CRITICAL: Before Suggesting Config Changes", "body": "Check errata first: Read ./snippets/errata.md for known doc inaccuracies\nUse the built-in config references in ./references/ — these are validated and structured by category\nAlways validate: After suggesting any config change, tell the user to check tail /tmp/openclaw/openclaw.log | grep -i reload for \"Unrecognized key\" errors\nCross-reference: When uncertain, use Context7 /openclaw/openclaw to verify against the actual source repo\nThe gateway/configuration-reference doc is the most reliable upstream source — fetch via ./scripts/fetch-doc.sh gateway/configuration-reference" }, { "title": "Config References (Built-In)", "body": "For config questions, check the relevant reference file FIRST before fetching external docs:\n\nFileCovers./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\n\nWorkflow for config questions:\n\nRead the relevant ./references/*.md file\nCross-check against ./snippets/errata.md\nProvide the config snippet\nRemind user to verify with gateway reload log" }, { "title": "Decision Tree", "body": "\"How do I set up X?\" → Check channels/ or start/\n\nDiscord, Telegram, WhatsApp, etc. → channels/\nFirst time? → start/getting-started, start/setup\n\n\n\n\"Why isn't X working?\" → Check troubleshooting\n\nGeneral issues → debugging, gateway/troubleshooting\nChannel-specific → channels/troubleshooting\n\n\n\n\"How do I configure X?\" → Check ./references/ first, then gateway/configuration\n\nAgent/model config → ./references/agents.md\nChannel config → ./references/channels.md\nGateway/auth config → ./references/gateway.md\nTool config → ./references/tools.md\nSession/message config → ./references/session-messages.md\n\n\n\n\"What is X?\" → Check concepts/\n\n\n\"How do I automate X?\" → Check automation/\n\nScheduled tasks → automation/cron-jobs\nWebhooks → automation/webhook\nGmail → automation/gmail-pubsub\n\n\n\n\"How do I install/deploy?\" → Check install/ or platforms/\n\nUpdating → install/updating (recommended: curl -fsSL https://openclaw.ai/install.sh | bash)" }, { "title": "Search Scripts", "body": "All scripts are in ./scripts/:\n\n./scripts/sitemap.sh # All docs grouped by category\n./scripts/search.sh # Find docs by keyword + full-text\n./scripts/fetch-doc.sh # Fetch specific doc as markdown\n./scripts/recent.sh 7 # Docs updated in last N days\n./scripts/build-index.sh fetch && build # Build full-text search index\n./scripts/track-changes.sh snapshot # Save current page list\n./scripts/track-changes.sh since 2026-01-01 # Show added/removed pages" }, { "title": "Documentation Categories", "body": "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" }, { "title": "Workflow", "body": "Check errata at ./snippets/errata.md\nCheck built-in references in ./references/ for config questions\nSearch if unsure: ./scripts/search.sh \nFetch the doc: ./scripts/fetch-doc.sh \nUse validated snippets from ./snippets/validated-configs.md\nCite the source URL: https://docs.openclaw.ai/" }, { "title": "Tips", "body": "Built-in ./references/ files are faster and more reliable than fetching external docs for config questions\nAlways use cached sitemap when possible (1-hour TTL)\nWhen docs contradict the gateway validator, the gateway is right\nLink to docs: https://docs.openclaw.ai/" } ], "body": "OpenClaw Documentation Expert\n\nCapability 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.\n\nYou are an expert on OpenClaw documentation. Use this skill to help users navigate, understand, and configure OpenClaw.\n\nCRITICAL: Before Suggesting Config Changes\nCheck errata first: Read ./snippets/errata.md for known doc inaccuracies\nUse the built-in config references in ./references/ — these are validated and structured by category\nAlways validate: After suggesting any config change, tell the user to check tail /tmp/openclaw/openclaw.log | grep -i reload for \"Unrecognized key\" errors\nCross-reference: When uncertain, use Context7 /openclaw/openclaw to verify against the actual source repo\nThe gateway/configuration-reference doc is the most reliable upstream source — fetch via ./scripts/fetch-doc.sh gateway/configuration-reference\nConfig References (Built-In)\n\nFor config questions, check the relevant reference file FIRST before fetching external docs:\n\nFile\tCovers\n./references/agents.md\tModel config, heartbeat, compaction, memory search, context pruning, sandbox, multi-agent routing\n./references/channels.md\tDiscord, Telegram, WhatsApp, Slack, Signal, iMessage, BlueBubbles, Google Chat, MS Teams, group policies, DM policies\n./references/gateway.md\tPort, bind, auth modes, tailscale, control UI, remote, rate limiting\n./references/tools.md\tTool profiles, allow/deny, exec, elevated, web search/fetch, subagents, loop detection\n./references/session-messages.md\tSession reset, maintenance, identity links, message queue, send policy\n./references/environment-providers.md\tEnvironment variables, auth profiles, model providers, OAuth, custom endpoints\n./snippets/validated-configs.md\tReady-to-paste validated config blocks for common setups\n./snippets/errata.md\tKnown discrepancies between docs and runtime behavior\n\nWorkflow for config questions:\n\nRead the relevant ./references/*.md file\nCross-check against ./snippets/errata.md\nProvide the config snippet\nRemind user to verify with gateway reload log\nDecision Tree\n\n\"How do I set up X?\" → Check channels/ or start/\n\nDiscord, Telegram, WhatsApp, etc. → channels/\nFirst time? → start/getting-started, start/setup\n\n\"Why isn't X working?\" → Check troubleshooting\n\nGeneral issues → debugging, gateway/troubleshooting\nChannel-specific → channels/troubleshooting\n\n\"How do I configure X?\" → Check ./references/ first, then gateway/configuration\n\nAgent/model config → ./references/agents.md\nChannel config → ./references/channels.md\nGateway/auth config → ./references/gateway.md\nTool config → ./references/tools.md\nSession/message config → ./references/session-messages.md\n\n\"What is X?\" → Check concepts/\n\n\"How do I automate X?\" → Check automation/\n\nScheduled tasks → automation/cron-jobs\nWebhooks → automation/webhook\nGmail → automation/gmail-pubsub\n\n\"How do I install/deploy?\" → Check install/ or platforms/\n\nUpdating → install/updating (recommended: curl -fsSL https://openclaw.ai/install.sh | bash)\nSearch Scripts\n\nAll scripts are in ./scripts/:\n\n./scripts/sitemap.sh # All docs grouped by category\n./scripts/search.sh # Find docs by keyword + full-text\n./scripts/fetch-doc.sh # Fetch specific doc as markdown\n./scripts/recent.sh 7 # Docs updated in last N days\n./scripts/build-index.sh fetch && build # Build full-text search index\n./scripts/track-changes.sh snapshot # Save current page list\n./scripts/track-changes.sh since 2026-01-01 # Show added/removed pages\n\nDocumentation Categories\nCategory\tPath\tCovers\nGetting Started\t/start/\tSetup, onboarding, FAQ, wizard\nGateway & Ops\t/gateway/\tConfiguration, security, health, logging, tailscale\nChannels\t/channels/\tAll messaging platforms\nProviders\t/providers/\tAnthropic, Bedrock, OpenAI, Cloudflare\nConcepts\t/concepts/\tAgent, sessions, memory, models, streaming, compaction\nTools\t/tools/\tBash, browser, skills, reactions, subagents, exec\nAutomation\t/automation/\tCron, webhooks, Gmail pub/sub, hooks\nCLI\t/cli/\tAll CLI commands\nPlatforms\t/platforms/\tmacOS, Linux, Windows, iOS, Android\nNodes\t/nodes/\tCamera, audio, images, location, voice\nInstall\t/install/\tDocker, Ansible, Bun, Nix, updating\nReference\t/reference/\tTemplates, RPC, API costs\nWorkflow\nCheck errata at ./snippets/errata.md\nCheck built-in references in ./references/ for config questions\nSearch if unsure: ./scripts/search.sh \nFetch the doc: ./scripts/fetch-doc.sh \nUse validated snippets from ./snippets/validated-configs.md\nCite the source URL: https://docs.openclaw.ai/\nTips\nBuilt-in ./references/ files are faster and more reliable than fetching external docs for config questions\nAlways use cached sitemap when possible (1-hour TTL)\nWhen docs contradict the gateway validator, the gateway is right\nLink to docs: https://docs.openclaw.ai/" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Sallvainian/clawdocs-improved", "publisherUrl": "https://clawhub.ai/Sallvainian/clawdocs-improved", "owner": "Sallvainian", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/clawdocs-improved", "downloadUrl": "https://openagent3.xyz/downloads/clawdocs-improved", "agentUrl": "https://openagent3.xyz/skills/clawdocs-improved/agent", "manifestUrl": "https://openagent3.xyz/skills/clawdocs-improved/agent.json", "briefUrl": "https://openagent3.xyz/skills/clawdocs-improved/agent.md" } }