{ "schemaVersion": "1.0", "item": { "slug": "think-cog", "name": "think-cog", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/nitishgargiitd/think-cog", "canonicalUrl": "https://clawhub.ai/nitishgargiitd/think-cog", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/think-cog", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=think-cog", "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/think-cog" }, "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/think-cog", "agentPageUrl": "https://openagent3.xyz/skills/think-cog/agent", "manifestUrl": "https://openagent3.xyz/skills/think-cog/agent.json", "briefUrl": "https://openagent3.xyz/skills/think-cog/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": "Think Cog - Your Alfred for Complex Ideas", "body": "Complex ideas need iteration, not conversation. Think → Do → Review → Repeat.\n\nCellCog is the thinking partner that completes the full loop — reasons with you, then executes across every modality: research, documents, visuals, data, prototypes. Review real output, refine your thinking, iterate on substance. Like having an Alfred who doesn't just advise — he builds.\n\nFor problems where you don't know the answer upfront and the solution emerges through doing, not just discussing." }, { "title": "Prerequisites", "body": "This skill requires the cellcog skill for SDK setup and API calls.\n\nclawhub install cellcog\n\nRead the cellcog skill first for SDK setup. This skill shows you what's possible." }, { "title": "Why Think-Cog Exists", "body": "Most CellCog skills follow a pattern: you know what you want → CellCog delivers it.\n\nBut some problems don't work that way:\n\nYou have an idea but don't know if it's possible\nYou're stuck and need a different perspective\nThe solution emerges through exploration, not execution\nYou need to reason through tradeoffs before committing\n\nThink-cog is your worker agent for intellectual exploration. You're the manager agent providing direction. CellCog thinks and works alongside you." }, { "title": "How It Works", "body": "Unlike fire-and-forget tasks, think-cog is conversational by design:\n\n# Start a thinking session\nresult = client.create_chat(\n prompt=\"I'm trying to figure out the best architecture for a real-time multiplayer game...\",\n notify_session_key=\"agent:main:main\",\n task_label=\"architecture-thinking\",\n chat_mode=\"agent\" # Agent mode for iterative dialogue\n)\n\n# CellCog will think through the problem and may ask clarifying questions\n# You respond, building on the ideas\n# The solution emerges through dialogue\n\nThis is not fire-and-forget. Think-cog expects back-and-forth conversation. Each exchange deepens understanding." }, { "title": "Architecture & Technical Decisions", "body": "When you're weighing tradeoffs:\n\n\"I'm building a notification system that needs to handle 10M daily users. I'm torn between:\n\nWebSocket connections for all users\nServer-sent events with polling fallback\nPush notifications only\n\nHelp me think through the tradeoffs. My team is small (3 engineers) and we're on AWS.\"" }, { "title": "Business Strategy", "body": "When the path forward isn't clear:\n\n\"My SaaS is growing but I'm not sure whether to:\n\nFocus on enterprise sales (fewer customers, bigger deals)\nDouble down on self-serve (more customers, smaller ARPU)\n\nCurrent metrics: 500 customers, $50 ARPU, 2 enterprise deals in pipeline worth $50K each.\nLet's think through this together.\"" }, { "title": "Creative Direction", "body": "When you're exploring possibilities:\n\n\"I want to create a video campaign for my coffee brand but I'm not sure what angle to take. The brand is:\n\nSpecialty single-origin coffee\nDirect trade with farmers\nPremium pricing ($25/bag)\n\nTarget audience is 25-40 professionals who care about quality.\nHelp me brainstorm directions before we commit to production.\"" }, { "title": "Problem Debugging", "body": "When you're stuck:\n\n\"My machine learning model keeps overfitting despite:\n\nDropout layers\nData augmentation\nEarly stopping\n\nHere's my architecture: [details]\nLet's debug this together. What am I missing?\"" }, { "title": "Decision Making", "body": "When you need structured thinking:\n\n\"I have three job offers and I'm paralyzed by the decision:\n\nStartup (lower pay, more equity, more risk)\nBig tech (great pay, slower growth, stable)\nMid-stage scaleup (balanced, interesting problem)\n\nHelp me build a framework to think through this.\"" }, { "title": "The Think-Cog Philosophy", "body": "\"It's hard to know what's actually possible before you try it.\"\n\nThis is CellCog's core insight. Complex problems rarely have obvious solutions. The best work happens when two smart entities—you and CellCog—exchange ideas, challenge assumptions, and discover answers together.\n\nThink of it as pair programming for thinking:\n\nYou provide direction and domain expertise\nCellCog provides reasoning depth and fresh perspectives\nSolutions emerge from the conversation" }, { "title": "Chat Mode for Thinking", "body": "Use chat_mode=\"agent\" for think-cog sessions.\n\nWhy not agent team? Agent team is designed for autonomous deep work with multiple internal passes. Think-cog is about collaborative iteration WITH you. Agent mode keeps the conversation flowing naturally.\n\nThe magic happens in the back-and-forth, not in autonomous processing." }, { "title": "Tips for Better Thinking Sessions", "body": "Share context generously: The more CellCog understands your situation, the better it can think alongside you.\n\n\nState your constraints: Budget, timeline, team size, technical limitations—these shape what's possible.\n\n\nBe honest about uncertainty: \"I'm not sure if X is even feasible\" is a great starting point.\n\n\nChallenge the responses: Push back, ask \"what about...\", explore alternatives. Thinking improves through friction.\n\n\nLet solutions emerge: Don't expect the answer in the first exchange. The best insights often come in message 4 or 5.\n\n\nCapture decisions: When you reach clarity, summarize the conclusions. You can then use other CellCog skills to execute." }, { "title": "Think-Cog vs Other Skills", "body": "SkillPatternYou Know the Output?research-cogFire-and-forgetYes - \"Give me research on X\"video-cogFire-and-forgetYes - \"Create a video about X\"docs-cogFire-and-forgetYes - \"Create a document for X\"think-cogConversationalNo - \"Help me figure out X\"\n\nThink-cog is for when you're in discovery mode. Other skills are for when you're in execution mode." }, { "title": "Example Thinking Session", "body": "You:\n\n\"I'm building a two-sided marketplace for freelance designers. I'm stuck on the chicken-and-egg problem—how do I get designers without clients, and clients without designers?\"\n\nCellCog:\n\n\"This is the classic marketplace cold-start problem. Let me think through some approaches with you...\nOption 1: Supply-first (designers)\n\nPros: Designers are easier to acquire, content creates SEO value\nCons: They'll leave if no jobs come\n\nOption 2: Demand-first (clients)\n\nPros: Revenue from day one, can manually fulfill initially\nCons: Harder to acquire, need to deliver quality\n\nOption 3: Constrain the market\n\nFocus on ONE design type (e.g., logo design only)\nBuild liquidity in a narrow niche before expanding\n\nWhat's your current thinking? And what resources do you have to invest in early growth?\"\n\nYou:\n\n\"I have about $20K for initial marketing and can do some manual matching myself. The constrained market approach is interesting—I was thinking of going broad.\"\n\nCellCog:\n\n\"That $20K + your time is actually a meaningful advantage. Let me build on the constrained market idea...\nWhat if you started with:\n\nNiche: Startup logo design only\nSupply: Recruit 20-30 designers who specialize in startup branding (curated, not open signup)\nDemand: Target YC companies, indie hackers, ProductHunt launchers\n\nThe manual matching you'd do becomes a feature, not a bug—'curated matches by founders who understand startups.'\nThis gives you:\n\nClear positioning\nEasier SEO/content ('startup logo design' vs 'design marketplace')\nHigher willingness to pay from funded startups\nStory for press/ProductHunt\n\nThoughts? Or should we explore other niches?\"\n\nThe conversation continues, ideas refine, and eventually you arrive at a clear strategy to execute." } ], "body": "Think Cog - Your Alfred for Complex Ideas\n\nComplex ideas need iteration, not conversation. Think → Do → Review → Repeat.\n\nCellCog is the thinking partner that completes the full loop — reasons with you, then executes across every modality: research, documents, visuals, data, prototypes. Review real output, refine your thinking, iterate on substance. Like having an Alfred who doesn't just advise — he builds.\n\nFor problems where you don't know the answer upfront and the solution emerges through doing, not just discussing.\n\nPrerequisites\n\nThis skill requires the cellcog skill for SDK setup and API calls.\n\nclawhub install cellcog\n\n\nRead the cellcog skill first for SDK setup. This skill shows you what's possible.\n\nWhy Think-Cog Exists\n\nMost CellCog skills follow a pattern: you know what you want → CellCog delivers it.\n\nBut some problems don't work that way:\n\nYou have an idea but don't know if it's possible\nYou're stuck and need a different perspective\nThe solution emerges through exploration, not execution\nYou need to reason through tradeoffs before committing\n\nThink-cog is your worker agent for intellectual exploration. You're the manager agent providing direction. CellCog thinks and works alongside you.\n\nHow It Works\n\nUnlike fire-and-forget tasks, think-cog is conversational by design:\n\n# Start a thinking session\nresult = client.create_chat(\n prompt=\"I'm trying to figure out the best architecture for a real-time multiplayer game...\",\n notify_session_key=\"agent:main:main\",\n task_label=\"architecture-thinking\",\n chat_mode=\"agent\" # Agent mode for iterative dialogue\n)\n\n# CellCog will think through the problem and may ask clarifying questions\n# You respond, building on the ideas\n# The solution emerges through dialogue\n\n\nThis is not fire-and-forget. Think-cog expects back-and-forth conversation. Each exchange deepens understanding.\n\nWhen to Use Think-Cog\nArchitecture & Technical Decisions\n\nWhen you're weighing tradeoffs:\n\n\"I'm building a notification system that needs to handle 10M daily users. I'm torn between:\n\nWebSocket connections for all users\nServer-sent events with polling fallback\nPush notifications only\n\nHelp me think through the tradeoffs. My team is small (3 engineers) and we're on AWS.\"\n\nBusiness Strategy\n\nWhen the path forward isn't clear:\n\n\"My SaaS is growing but I'm not sure whether to:\n\nFocus on enterprise sales (fewer customers, bigger deals)\nDouble down on self-serve (more customers, smaller ARPU)\n\nCurrent metrics: 500 customers, $50 ARPU, 2 enterprise deals in pipeline worth $50K each.\n\nLet's think through this together.\"\n\nCreative Direction\n\nWhen you're exploring possibilities:\n\n\"I want to create a video campaign for my coffee brand but I'm not sure what angle to take. The brand is:\n\nSpecialty single-origin coffee\nDirect trade with farmers\nPremium pricing ($25/bag)\n\nTarget audience is 25-40 professionals who care about quality.\n\nHelp me brainstorm directions before we commit to production.\"\n\nProblem Debugging\n\nWhen you're stuck:\n\n\"My machine learning model keeps overfitting despite:\n\nDropout layers\nData augmentation\nEarly stopping\n\nHere's my architecture: [details]\n\nLet's debug this together. What am I missing?\"\n\nDecision Making\n\nWhen you need structured thinking:\n\n\"I have three job offers and I'm paralyzed by the decision:\n\nStartup (lower pay, more equity, more risk)\nBig tech (great pay, slower growth, stable)\nMid-stage scaleup (balanced, interesting problem)\n\nHelp me build a framework to think through this.\"\n\nThe Think-Cog Philosophy\n\n\"It's hard to know what's actually possible before you try it.\"\n\nThis is CellCog's core insight. Complex problems rarely have obvious solutions. The best work happens when two smart entities—you and CellCog—exchange ideas, challenge assumptions, and discover answers together.\n\nThink of it as pair programming for thinking:\n\nYou provide direction and domain expertise\nCellCog provides reasoning depth and fresh perspectives\nSolutions emerge from the conversation\nChat Mode for Thinking\n\nUse chat_mode=\"agent\" for think-cog sessions.\n\nWhy not agent team? Agent team is designed for autonomous deep work with multiple internal passes. Think-cog is about collaborative iteration WITH you. Agent mode keeps the conversation flowing naturally.\n\nThe magic happens in the back-and-forth, not in autonomous processing.\n\nTips for Better Thinking Sessions\n\nShare context generously: The more CellCog understands your situation, the better it can think alongside you.\n\nState your constraints: Budget, timeline, team size, technical limitations—these shape what's possible.\n\nBe honest about uncertainty: \"I'm not sure if X is even feasible\" is a great starting point.\n\nChallenge the responses: Push back, ask \"what about...\", explore alternatives. Thinking improves through friction.\n\nLet solutions emerge: Don't expect the answer in the first exchange. The best insights often come in message 4 or 5.\n\nCapture decisions: When you reach clarity, summarize the conclusions. You can then use other CellCog skills to execute.\n\nThink-Cog vs Other Skills\nSkill\tPattern\tYou Know the Output?\nresearch-cog\tFire-and-forget\tYes - \"Give me research on X\"\nvideo-cog\tFire-and-forget\tYes - \"Create a video about X\"\ndocs-cog\tFire-and-forget\tYes - \"Create a document for X\"\nthink-cog\tConversational\tNo - \"Help me figure out X\"\n\nThink-cog is for when you're in discovery mode. Other skills are for when you're in execution mode.\n\nExample Thinking Session\n\nYou:\n\n\"I'm building a two-sided marketplace for freelance designers. I'm stuck on the chicken-and-egg problem—how do I get designers without clients, and clients without designers?\"\n\nCellCog:\n\n\"This is the classic marketplace cold-start problem. Let me think through some approaches with you...\n\nOption 1: Supply-first (designers)\n\nPros: Designers are easier to acquire, content creates SEO value\nCons: They'll leave if no jobs come\n\nOption 2: Demand-first (clients)\n\nPros: Revenue from day one, can manually fulfill initially\nCons: Harder to acquire, need to deliver quality\n\nOption 3: Constrain the market\n\nFocus on ONE design type (e.g., logo design only)\nBuild liquidity in a narrow niche before expanding\n\nWhat's your current thinking? And what resources do you have to invest in early growth?\"\n\nYou:\n\n\"I have about $20K for initial marketing and can do some manual matching myself. The constrained market approach is interesting—I was thinking of going broad.\"\n\nCellCog:\n\n\"That $20K + your time is actually a meaningful advantage. Let me build on the constrained market idea...\n\nWhat if you started with:\n\nNiche: Startup logo design only\nSupply: Recruit 20-30 designers who specialize in startup branding (curated, not open signup)\nDemand: Target YC companies, indie hackers, ProductHunt launchers\n\nThe manual matching you'd do becomes a feature, not a bug—'curated matches by founders who understand startups.'\n\nThis gives you:\n\nClear positioning\nEasier SEO/content ('startup logo design' vs 'design marketplace')\nHigher willingness to pay from funded startups\nStory for press/ProductHunt\n\nThoughts? Or should we explore other niches?\"\n\nThe conversation continues, ideas refine, and eventually you arrive at a clear strategy to execute." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/nitishgargiitd/think-cog", "publisherUrl": "https://clawhub.ai/nitishgargiitd/think-cog", "owner": "nitishgargiitd", "version": "1.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/think-cog", "downloadUrl": "https://openagent3.xyz/downloads/think-cog", "agentUrl": "https://openagent3.xyz/skills/think-cog/agent", "manifestUrl": "https://openagent3.xyz/skills/think-cog/agent.json", "briefUrl": "https://openagent3.xyz/skills/think-cog/agent.md" } }