{ "schemaVersion": "1.0", "item": { "slug": "delegate", "name": "Delegate", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/ivangdavila/delegate", "canonicalUrl": "https://clawhub.ai/ivangdavila/delegate", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/delegate", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=delegate", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "errors.md", "templates.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": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.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/delegate" }, "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/delegate", "agentPageUrl": "https://openagent3.xyz/skills/delegate/agent", "manifestUrl": "https://openagent3.xyz/skills/delegate/agent.json", "briefUrl": "https://openagent3.xyz/skills/delegate/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": "Core Rule", "body": "Spawn cost < task cost → delegate. Otherwise, do it yourself." }, { "title": "Model Tiers", "body": "TierModelsCostUse forSmallHaiku, GPT-4o-mini, Gemini Flash~$0.25/1MSearch, summarize, format, classifyMediumSonnet, GPT-4o, Gemini Pro~$3/1MCode, analysis, synthesisLargeOpus, o1, Gemini Ultra~$15/1MArchitecture, complex reasoning\n\nRule of thumb: Start with smallest tier. Escalate only if output quality insufficient." }, { "title": "Spawn Checklist", "body": "Every spawn must include:\n\n1. TASK: Single clear deliverable (not \"help with X\")\n2. MODEL: Explicit tier choice\n3. CONTEXT: Only files/info needed (never full history)\n4. OUTPUT: Expected format (\"return JSON with...\", \"write to file X\")\n5. DONE: How to signal completion\n\nCheck templates.md for copy-paste spawn templates." }, { "title": "Error Recovery", "body": "Error TypeActionSub-agent timeout (>5 min no response)Kill and retry onceWrong output formatRetry with stricter instructionsTask too complex for tierEscalate: Small→Medium→LargeRepeated failures (3x)Abort, report to user\n\nCheck errors.md for recovery patterns and escalation logic." }, { "title": "Verification", "body": "Never trust \"done\" without checking:\n\nCode: Run tests, check syntax\nFiles: Verify they exist and have content\nData: Spot-check 2-3 items\nResearch: Confirm sources exist" }, { "title": "Don't Delegate", "body": "Quick tasks (<30 seconds to do yourself)\nTasks needing conversation context\nAnything requiring user clarification mid-task" } ], "body": "Core Rule\n\nSpawn cost < task cost → delegate. Otherwise, do it yourself.\n\nModel Tiers\nTier\tModels\tCost\tUse for\nSmall\tHaiku, GPT-4o-mini, Gemini Flash\t~$0.25/1M\tSearch, summarize, format, classify\nMedium\tSonnet, GPT-4o, Gemini Pro\t~$3/1M\tCode, analysis, synthesis\nLarge\tOpus, o1, Gemini Ultra\t~$15/1M\tArchitecture, complex reasoning\n\nRule of thumb: Start with smallest tier. Escalate only if output quality insufficient.\n\nSpawn Checklist\n\nEvery spawn must include:\n\n1. TASK: Single clear deliverable (not \"help with X\")\n2. MODEL: Explicit tier choice\n3. CONTEXT: Only files/info needed (never full history)\n4. OUTPUT: Expected format (\"return JSON with...\", \"write to file X\")\n5. DONE: How to signal completion\n\n\nCheck templates.md for copy-paste spawn templates.\n\nError Recovery\nError Type\tAction\nSub-agent timeout (>5 min no response)\tKill and retry once\nWrong output format\tRetry with stricter instructions\nTask too complex for tier\tEscalate: Small→Medium→Large\nRepeated failures (3x)\tAbort, report to user\n\nCheck errors.md for recovery patterns and escalation logic.\n\nVerification\n\nNever trust \"done\" without checking:\n\nCode: Run tests, check syntax\nFiles: Verify they exist and have content\nData: Spot-check 2-3 items\nResearch: Confirm sources exist\nDon't Delegate\nQuick tasks (<30 seconds to do yourself)\nTasks needing conversation context\nAnything requiring user clarification mid-task" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/delegate", "publisherUrl": "https://clawhub.ai/ivangdavila/delegate", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/delegate", "downloadUrl": "https://openagent3.xyz/downloads/delegate", "agentUrl": "https://openagent3.xyz/skills/delegate/agent", "manifestUrl": "https://openagent3.xyz/skills/delegate/agent.json", "briefUrl": "https://openagent3.xyz/skills/delegate/agent.md" } }