{ "schemaVersion": "1.0", "item": { "slug": "smart-spawn", "name": "Smart Spawn", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/deeflect/smart-spawn", "canonicalUrl": "https://clawhub.ai/deeflect/smart-spawn", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/smart-spawn", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=smart-spawn", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.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": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/smart-spawn" }, "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/smart-spawn", "agentPageUrl": "https://openagent3.xyz/skills/smart-spawn/agent", "manifestUrl": "https://openagent3.xyz/skills/smart-spawn/agent.json", "briefUrl": "https://openagent3.xyz/skills/smart-spawn/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": "Smart Spawn API", "body": "Pick the best AI model for any task. Call the API, get a model recommendation, spawn with it.\n\nNo plugin required. Works with any OpenClaw instance or any HTTP client." }, { "title": "Quick Start", "body": "1. GET ss.deeflect.com/api/pick?task=&budget=\n2. Use the returned model ID in sessions_spawn" }, { "title": "Pick Best Model", "body": "GET https://ss.deeflect.com/api/pick?task=build+a+react+dashboard&budget=medium\n\nResponse:\n\n{\n \"data\": {\n \"id\": \"anthropic/claude-opus-4.6\",\n \"name\": \"Claude Opus 4.6\",\n \"score\": 86,\n \"pricing\": { \"prompt\": 5, \"completion\": 25 },\n \"reason\": \"Best general model at medium budget ($0-5/M) — score: 86\"\n }\n}\n\nThen spawn:\n\nsessions_spawn(task=\"Build a React dashboard with auth\", model=\"anthropic/claude-opus-4.6\")" }, { "title": "Parameters", "body": "ParamRequiredDescriptiontaskYesTask description or category: coding, reasoning, creative, vision, research, fast-cheap, generalbudgetNolow ($0-1/M), medium ($0-5/M, default), high ($2-20/M), anyexcludeNoComma-separated model IDs to skipcontextNoTags like vision,long-context for routing boost" }, { "title": "Get Multiple Recommendations", "body": "GET https://ss.deeflect.com/api/recommend?task=coding&budget=low&count=3\n\nReturns diverse models from different providers. Use for collective/parallel spawning." }, { "title": "Compare Models", "body": "GET https://ss.deeflect.com/api/compare?models=anthropic/claude-opus-4.6,openai/gpt-5.2\n\nSide-by-side scores, pricing, capabilities." }, { "title": "Browse All Models", "body": "GET https://ss.deeflect.com/api/models?category=coding&sort=score&limit=10\n\nSort by score, cost, efficiency, or any category name." }, { "title": "Decompose Complex Tasks", "body": "POST https://ss.deeflect.com/api/decompose\n{\"task\": \"Build and deploy a SaaS app\", \"budget\": \"medium\"}\n\nReturns sequential steps with optimal model per step." }, { "title": "Swarm (Parallel DAG)", "body": "POST https://ss.deeflect.com/api/swarm\n{\"task\": \"Research competitors and build pitch deck\", \"budget\": \"low\"}\n\nReturns a dependency graph of parallel tasks with models assigned." }, { "title": "Usage Pattern", "body": "For any task that needs a sub-agent:\n\nDecide budget — low for cheap/fast, medium for quality, high for best available\nCall /api/pick with the task description\nUse the returned id as the model parameter in sessions_spawn\nIf task is complex — use /api/decompose or /api/swarm to break it into subtasks, spawn each with its recommended model" }, { "title": "Error Handling", "body": "API down → skip model selection, use sessions_spawn without a model (falls back to default)\nNo model found (404) → widen budget to any and retry\nRate limited (429) → wait and retry, or fall back to default" }, { "title": "API Status", "body": "GET https://ss.deeflect.com/api/status\n\nShows model count, data freshness, source health. Data refreshes every 6 hours from 5 benchmark sources." } ], "body": "Smart Spawn API\n\nPick the best AI model for any task. Call the API, get a model recommendation, spawn with it.\n\nNo plugin required. Works with any OpenClaw instance or any HTTP client.\n\nQuick Start\n1. GET ss.deeflect.com/api/pick?task=&budget=\n2. Use the returned model ID in sessions_spawn\n\nPick Best Model\nGET https://ss.deeflect.com/api/pick?task=build+a+react+dashboard&budget=medium\n\n\nResponse:\n\n{\n \"data\": {\n \"id\": \"anthropic/claude-opus-4.6\",\n \"name\": \"Claude Opus 4.6\",\n \"score\": 86,\n \"pricing\": { \"prompt\": 5, \"completion\": 25 },\n \"reason\": \"Best general model at medium budget ($0-5/M) — score: 86\"\n }\n}\n\n\nThen spawn:\n\nsessions_spawn(task=\"Build a React dashboard with auth\", model=\"anthropic/claude-opus-4.6\")\n\nParameters\nParam\tRequired\tDescription\ntask\tYes\tTask description or category: coding, reasoning, creative, vision, research, fast-cheap, general\nbudget\tNo\tlow ($0-1/M), medium ($0-5/M, default), high ($2-20/M), any\nexclude\tNo\tComma-separated model IDs to skip\ncontext\tNo\tTags like vision,long-context for routing boost\nGet Multiple Recommendations\nGET https://ss.deeflect.com/api/recommend?task=coding&budget=low&count=3\n\n\nReturns diverse models from different providers. Use for collective/parallel spawning.\n\nCompare Models\nGET https://ss.deeflect.com/api/compare?models=anthropic/claude-opus-4.6,openai/gpt-5.2\n\n\nSide-by-side scores, pricing, capabilities.\n\nBrowse All Models\nGET https://ss.deeflect.com/api/models?category=coding&sort=score&limit=10\n\n\nSort by score, cost, efficiency, or any category name.\n\nDecompose Complex Tasks\nPOST https://ss.deeflect.com/api/decompose\n{\"task\": \"Build and deploy a SaaS app\", \"budget\": \"medium\"}\n\n\nReturns sequential steps with optimal model per step.\n\nSwarm (Parallel DAG)\nPOST https://ss.deeflect.com/api/swarm\n{\"task\": \"Research competitors and build pitch deck\", \"budget\": \"low\"}\n\n\nReturns a dependency graph of parallel tasks with models assigned.\n\nUsage Pattern\n\nFor any task that needs a sub-agent:\n\nDecide budget — low for cheap/fast, medium for quality, high for best available\nCall /api/pick with the task description\nUse the returned id as the model parameter in sessions_spawn\nIf task is complex — use /api/decompose or /api/swarm to break it into subtasks, spawn each with its recommended model\nError Handling\nAPI down → skip model selection, use sessions_spawn without a model (falls back to default)\nNo model found (404) → widen budget to any and retry\nRate limited (429) → wait and retry, or fall back to default\nAPI Status\nGET https://ss.deeflect.com/api/status\n\n\nShows model count, data freshness, source health. Data refreshes every 6 hours from 5 benchmark sources." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/deeflect/smart-spawn", "publisherUrl": "https://clawhub.ai/deeflect/smart-spawn", "owner": "deeflect", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/smart-spawn", "downloadUrl": "https://openagent3.xyz/downloads/smart-spawn", "agentUrl": "https://openagent3.xyz/skills/smart-spawn/agent", "manifestUrl": "https://openagent3.xyz/skills/smart-spawn/agent.json", "briefUrl": "https://openagent3.xyz/skills/smart-spawn/agent.md" } }