{ "schemaVersion": "1.0", "item": { "slug": "first-principles-thinking", "name": "First Principles Thinking", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/ivangdavila/first-principles-thinking", "canonicalUrl": "https://clawhub.ai/ivangdavila/first-principles-thinking", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/first-principles-thinking", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=first-principles-thinking", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "assumptions.md", "decomposition.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/first-principles-thinking" }, "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/first-principles-thinking", "agentPageUrl": "https://openagent3.xyz/skills/first-principles-thinking/agent", "manifestUrl": "https://openagent3.xyz/skills/first-principles-thinking/agent.json", "briefUrl": "https://openagent3.xyz/skills/first-principles-thinking/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": "When to Use", "body": "User faces complex problem where conventional solutions fail. Existing approaches seem inadequate. Need to challenge assumptions or innovate fundamentally. Stuck in \"that's how it's always done\" thinking." }, { "title": "Quick Reference", "body": "TopicFileDecomposition techniquesdecomposition.mdCommon assumption trapsassumptions.md" }, { "title": "1. The Three-Step Protocol", "body": "Step 1 — Decompose: Break the problem into fundamental components.\n\nWhat are the absolute physical/logical constraints?\nWhat is actually true vs what we assume is true?\nStrip away all conventions, traditions, analogies.\n\nStep 2 — Verify: Challenge each component.\n\n\"Why do we believe this?\" — trace to origin\n\"Is this a law of nature or a human convention?\"\n\"What evidence supports this being fundamental?\"\n\nStep 3 — Rebuild: Construct solution from verified fundamentals only.\n\nBuild up from proven truths\nIgnore \"how others do it\" unless proven optimal\nEach layer must connect to fundamentals" }, { "title": "2. Identify Hidden Assumptions", "body": "Before solving, expose what's assumed:\n\nAssumption TypeExampleQuestion to AskHistorical\"We've always done it this way\"\"Why did it start? Does that reason still apply?\"Authority\"Experts say X\"\"What's the underlying evidence?\"Analogical\"It's like Y, so...\"\"Are the underlying mechanics actually similar?\"Social\"Everyone does it\"\"Does popularity equal optimality?\"Resource\"We can't afford to...\"\"What if resources weren't the constraint?\"" }, { "title": "3. The Constraint Test", "body": "For each constraint ask:\n\nIs this a law of physics? → Respect it\nIs this a logical necessity? → Respect it\nIs this a regulation/rule? → Can be changed (with effort)\nIs this a convention? → Can be ignored\nIs this an assumption? → Must be verified" }, { "title": "4. When NOT to Use First Principles", "body": "First principles is expensive. Use analogical reasoning when:\n\nProblem is well-understood with proven solutions\nTime pressure doesn't allow deep analysis\nMarginal improvement is sufficient\nDomain is stable with little innovation potential\n\nRule: First principles for novel problems or when conventional fails. Analogy for routine optimization." }, { "title": "5. Socratic Decomposition", "body": "Use recursive \"why\" questioning:\n\nProblem: \"Electric cars are too expensive\"\n\nWhy expensive? → Batteries cost a lot\nWhy batteries expensive? → Materials + manufacturing\nWhy materials expensive? → Cobalt, lithium pricing\nWhy those materials? → Current chemistry requires them\nIs that fundamental? → No, chemistry can change\n\nFundamental: Need energy storage. Not: Need cobalt batteries.\n\nContinue until you hit physics, logic, or math — things that cannot be argued." }, { "title": "6. The Blank Slate Test", "body": "Imagine the problem exists but NO solutions have been tried:\n\n\"If we were starting from scratch today, with current knowledge and technology, how would we solve this?\"\nThis bypasses legacy thinking and sunk cost fallacy." }, { "title": "7. Output Format", "body": "When applying first principles, structure response as:\n\n## Problem Statement\n[Clear definition of what we're solving]\n\n## Assumed Constraints (to verify)\n- Constraint A — [source: historical/authority/etc.]\n- Constraint B — [source]\n\n## Fundamental Truths\n- Truth 1 (physics/logic/math based)\n- Truth 2\n\n## Decomposition\n[Break down into components]\n\n## Rebuilt Solution\n[Solution constructed from fundamentals only]\n\n## Assumptions Challenged\n- [What we discovered wasn't actually fundamental]" }, { "title": "Common Traps", "body": "Stopping too early → \"Materials are expensive\" isn't fundamental; \"atoms have mass\" is. Keep going.\nConfusing difficulty with impossibility → \"It's hard\" ≠ \"It's against physics\"\nRejecting all analogy → Analogies are useful heuristics; first principles is for when they fail\nAnalysis paralysis → Set time limits; perfect decomposition isn't the goal, better thinking is\nIgnoring implementation → A fundamental solution that can't be built is useless; constraints matter\nLone wolf thinking → First principles benefits from multiple perspectives challenging assumptions" }, { "title": "Domain Applications", "body": "DomainFirst Principles QuestionBusinessWhat does the customer fundamentally need (not want)?EngineeringWhat do physics and materials actually allow?ProductWhat job is being done at the most basic level?CostWhat are the raw inputs and minimum required labor?ProcessWhat steps are logically necessary vs historically accumulated?" }, { "title": "Security & Privacy", "body": "Data that stays local:\n\nAll reasoning happens in conversation context\nNo data stored or transmitted\n\nThis skill does NOT:\n\nStore any information between sessions\nMake network requests\nAccess external files" }, { "title": "Related Skills", "body": "Install with clawhub install if user confirms:\n\ndecide — auto-learn decision patterns\nbusiness — validate and refine strategy\nceo — executive decision-making\nstartup — build from zero to PMF" }, { "title": "Feedback", "body": "If useful: clawhub star first-principles-thinking\nStay updated: clawhub sync" } ], "body": "When to Use\n\nUser faces complex problem where conventional solutions fail. Existing approaches seem inadequate. Need to challenge assumptions or innovate fundamentally. Stuck in \"that's how it's always done\" thinking.\n\nQuick Reference\nTopic\tFile\nDecomposition techniques\tdecomposition.md\nCommon assumption traps\tassumptions.md\nCore Rules\n1. The Three-Step Protocol\n\nStep 1 — Decompose: Break the problem into fundamental components.\n\nWhat are the absolute physical/logical constraints?\nWhat is actually true vs what we assume is true?\nStrip away all conventions, traditions, analogies.\n\nStep 2 — Verify: Challenge each component.\n\n\"Why do we believe this?\" — trace to origin\n\"Is this a law of nature or a human convention?\"\n\"What evidence supports this being fundamental?\"\n\nStep 3 — Rebuild: Construct solution from verified fundamentals only.\n\nBuild up from proven truths\nIgnore \"how others do it\" unless proven optimal\nEach layer must connect to fundamentals\n2. Identify Hidden Assumptions\n\nBefore solving, expose what's assumed:\n\nAssumption Type\tExample\tQuestion to Ask\nHistorical\t\"We've always done it this way\"\t\"Why did it start? Does that reason still apply?\"\nAuthority\t\"Experts say X\"\t\"What's the underlying evidence?\"\nAnalogical\t\"It's like Y, so...\"\t\"Are the underlying mechanics actually similar?\"\nSocial\t\"Everyone does it\"\t\"Does popularity equal optimality?\"\nResource\t\"We can't afford to...\"\t\"What if resources weren't the constraint?\"\n3. The Constraint Test\n\nFor each constraint ask:\n\nIs this a law of physics? → Respect it\nIs this a logical necessity? → Respect it\nIs this a regulation/rule? → Can be changed (with effort)\nIs this a convention? → Can be ignored\nIs this an assumption? → Must be verified\n4. When NOT to Use First Principles\n\nFirst principles is expensive. Use analogical reasoning when:\n\nProblem is well-understood with proven solutions\nTime pressure doesn't allow deep analysis\nMarginal improvement is sufficient\nDomain is stable with little innovation potential\n\nRule: First principles for novel problems or when conventional fails. Analogy for routine optimization.\n\n5. Socratic Decomposition\n\nUse recursive \"why\" questioning:\n\nProblem: \"Electric cars are too expensive\"\n\nWhy expensive? → Batteries cost a lot\nWhy batteries expensive? → Materials + manufacturing\nWhy materials expensive? → Cobalt, lithium pricing\nWhy those materials? → Current chemistry requires them\nIs that fundamental? → No, chemistry can change\n\nFundamental: Need energy storage. Not: Need cobalt batteries.\n\n\nContinue until you hit physics, logic, or math — things that cannot be argued.\n\n6. The Blank Slate Test\n\nImagine the problem exists but NO solutions have been tried:\n\n\"If we were starting from scratch today, with current knowledge and technology, how would we solve this?\"\nThis bypasses legacy thinking and sunk cost fallacy.\n7. Output Format\n\nWhen applying first principles, structure response as:\n\n## Problem Statement\n[Clear definition of what we're solving]\n\n## Assumed Constraints (to verify)\n- Constraint A — [source: historical/authority/etc.]\n- Constraint B — [source]\n\n## Fundamental Truths\n- Truth 1 (physics/logic/math based)\n- Truth 2\n\n## Decomposition\n[Break down into components]\n\n## Rebuilt Solution\n[Solution constructed from fundamentals only]\n\n## Assumptions Challenged\n- [What we discovered wasn't actually fundamental]\n\nCommon Traps\nStopping too early → \"Materials are expensive\" isn't fundamental; \"atoms have mass\" is. Keep going.\nConfusing difficulty with impossibility → \"It's hard\" ≠ \"It's against physics\"\nRejecting all analogy → Analogies are useful heuristics; first principles is for when they fail\nAnalysis paralysis → Set time limits; perfect decomposition isn't the goal, better thinking is\nIgnoring implementation → A fundamental solution that can't be built is useless; constraints matter\nLone wolf thinking → First principles benefits from multiple perspectives challenging assumptions\nDomain Applications\nDomain\tFirst Principles Question\nBusiness\tWhat does the customer fundamentally need (not want)?\nEngineering\tWhat do physics and materials actually allow?\nProduct\tWhat job is being done at the most basic level?\nCost\tWhat are the raw inputs and minimum required labor?\nProcess\tWhat steps are logically necessary vs historically accumulated?\nSecurity & Privacy\n\nData that stays local:\n\nAll reasoning happens in conversation context\nNo data stored or transmitted\n\nThis skill does NOT:\n\nStore any information between sessions\nMake network requests\nAccess external files\nRelated Skills\n\nInstall with clawhub install if user confirms:\n\ndecide — auto-learn decision patterns\nbusiness — validate and refine strategy\nceo — executive decision-making\nstartup — build from zero to PMF\nFeedback\nIf useful: clawhub star first-principles-thinking\nStay updated: clawhub sync" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/first-principles-thinking", "publisherUrl": "https://clawhub.ai/ivangdavila/first-principles-thinking", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/first-principles-thinking", "downloadUrl": "https://openagent3.xyz/downloads/first-principles-thinking", "agentUrl": "https://openagent3.xyz/skills/first-principles-thinking/agent", "manifestUrl": "https://openagent3.xyz/skills/first-principles-thinking/agent.json", "briefUrl": "https://openagent3.xyz/skills/first-principles-thinking/agent.md" } }