{ "schemaVersion": "1.0", "item": { "slug": "openclaw-skill-ideation", "name": "openclaw-skill-ideation", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/skidvis/openclaw-skill-ideation", "canonicalUrl": "https://clawhub.ai/skidvis/openclaw-skill-ideation", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/openclaw-skill-ideation", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-skill-ideation", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/confidence-rubric.md", "references/contract-template.md", "references/prd-template.md", "references/spec-template.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/openclaw-skill-ideation" }, "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/openclaw-skill-ideation", "agentPageUrl": "https://openagent3.xyz/skills/openclaw-skill-ideation/agent", "manifestUrl": "https://openagent3.xyz/skills/openclaw-skill-ideation/agent.json", "briefUrl": "https://openagent3.xyz/skills/openclaw-skill-ideation/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": "Ideation", "body": "Transform unstructured brain dumps into structured, actionable implementation artifacts through a confidence-gated workflow." }, { "title": "Workflow Pipeline", "body": "INTAKE → CODEBASE EXPLORATION → CONTRACT FORMATION → PHASING → SPEC GENERATION → HANDOFF\n ↓ ↓ ↓ ↓ ↓\n Understand confidence < 95%? PRDs or Repeatable? Analyze deps\n existing code ↓ straight ↓ ↓\n ASK QUESTIONS to specs? Template + Sequential?\n ↓ per-phase Parallel?\n (loop until ≥95%) deltas" }, { "title": "Phase 1: Intake", "body": "Accept whatever the user provides:\n\nScattered thoughts and half-formed ideas\nVoice dictation transcripts (messy, stream-of-consciousness)\nBullet points mixed with rambling\nTopic jumping and tangents\nContradictions and unclear statements\nTechnical jargon mixed with vague descriptions\n\nDon't require organization. The mess is the input.\n\nAcknowledge receipt and begin analysis. Do not ask for clarification yet." }, { "title": "Phase 2: Codebase Exploration", "body": "Before scoring confidence or generating any artifacts, understand the existing codebase. This is critical — specs written without understanding existing patterns, architecture, and conventions will be generic and wrong." }, { "title": "When to Explore", "body": "Exploration is needed when:\n\nThe brain dump references existing code, features, or systems\nThe project directory contains source code (not a greenfield project)\nThe user mentions extending, modifying, or integrating with existing functionality\n\nSkip exploration for greenfield projects with no existing code." }, { "title": "What to Explore", "body": "Use file reading and search to understand:\n\nProject structure — What frameworks, languages, and patterns are in use?\nRelevant existing code — What modules/files relate to the brain dump's scope?\nConventions and patterns — How are similar features implemented? What abstractions exist?\nTesting patterns — How is the codebase tested? What infrastructure exists?\nConfiguration and build — What tools, package managers, and CI/CD are in use?\n\nDo not write exploration findings to files. They're context for the ideation process, not an artifact." }, { "title": "3.1 Analyze the Brain Dump", "body": "Extract from the raw input + codebase exploration:\n\nProblem signals: What pain point or need is being described?\nGoal signals: What does the user want to achieve?\nSuccess signals: How will they know it worked?\nScope signals: What's included? What's explicitly excluded?\nContradictions: Note any conflicting statements\nCodebase constraints: What does the existing architecture enable or limit?" }, { "title": "3.2 Calculate Confidence Score", "body": "Score each dimension (0-20 points):\n\nDimensionQuestionProblem ClarityDo I understand what problem we're solving and why it matters?Goal DefinitionAre the goals specific and measurable?Success CriteriaCan I write tests or validation steps for \"done\"?Scope BoundariesDo I know what's in and out of scope?ConsistencyAre there contradictions I need resolved?\n\nTotal: /100 points\n\nSee references/confidence-rubric.md for detailed scoring criteria." }, { "title": "3.3 Confidence Thresholds", "body": "ScoreAction< 70Major gaps. Ask 5+ questions targeting lowest dimensions.70-84Moderate gaps. Ask 3-5 targeted questions.85-94Minor gaps. Ask 1-2 specific questions.≥ 95Ready to generate contract." }, { "title": "3.4 Ask Clarifying Questions", "body": "When confidence < 95%, ask clarifying questions:\n\nQuestion strategy:\n\nTarget the lowest-scoring dimension first\nBe specific, not open-ended\nOffer options when possible (\"Is it A, B, or C?\")\nReference what was stated (\"You mentioned X, did you mean...?\")\nLimit to 3-5 questions per round\nAfter each round, recalculate confidence" }, { "title": "3.5 Generate Contract", "body": "When confidence ≥ 95%:\n\nConfirm project name with user\nConvert to kebab-case for directory name\nCreate output directory: ./docs/ideation/{project-name}/\nWrite contract.md using references/contract-template.md\nGet explicit approval before proceeding\n\nDo not proceed until contract is explicitly approved." }, { "title": "4.1 Choose Workflow", "body": "Ask the user:\n\nStraight to specs — Recommended for technical projects. Faster.\nPRDs then specs — Recommended for large scope or cross-functional teams." }, { "title": "4.2 Determine Phases", "body": "Small-project shortcut: If the scope is small enough to implement in a single phase (1-3 components, touches fewer than ~10 files), skip phasing entirely. Generate a single spec.md.\n\nPhasing criteria (for multi-phase projects):\n\nDependencies (what must be built first?)\nRisk (tackle high-risk items early)\nValue delivery (can users benefit after each phase?)\nComplexity (balance phases for consistent effort)" }, { "title": "4.3 Generate PRDs (if chosen)", "body": "For each phase, generate prd-phase-{n}.md using references/prd-template.md." }, { "title": "4.4 Generate Implementation Specs", "body": "Generate specs using references/spec-template.md:\n\nTechnical approach\nFile changes (new and modified)\nImplementation details with code patterns\nTesting requirements\nError handling\nValidation commands\nPer-component feedback loops\n\nReference existing code: Include \"Pattern to follow: path/to/similar/file.ts\" when relevant patterns exist." }, { "title": "4.5 Present for Review", "body": "Before presenting specs, evaluate feedback loop quality. Present all specs for user approval." }, { "title": "Phase 5: Execution Handoff", "body": "Present the execution strategy:\n\nIdeation complete. Artifacts written to `./docs/ideation/{project-name}/`.\n\n## To start implementation\n\nStart a fresh session and work through the specs in order:\n1. Read the contract for context\n2. Read spec-phase-1.md \n3. Implement following the spec\n4. Validate using the commands in the spec\n5. Commit and move to next phase" }, { "title": "Output Artifacts", "body": "All artifacts written to ./docs/ideation/{project-name}/:\n\ncontract.md # Problem, goals, success, scope\nprd-phase-1.md # Phase 1 requirements (only if PRDs chosen)\nspec-phase-1.md # Phase 1 implementation spec\nspec-template-{pattern}.md # Shared template for repeatable phases (if applicable)\nspec-phase-{n}.md # Per-phase specs" }, { "title": "Important Notes", "body": "Explore the codebase before scoring confidence (unless greenfield).\nScore confidence conservatively. When uncertain, score lower.\nNever skip the confidence check. Don't assume understanding.\nAlways write artifacts to files. Don't just display them.\nEach phase should be independently valuable.\nSpecs should be detailed enough to implement without re-reading PRDs or the contract.\nKeep contracts lean. Heavy docs slow iteration.\nReference existing code patterns in specs.\nSmall projects don't need phases. If scope is 1-3 components, generate a single spec." } ], "body": "Ideation\n\nTransform unstructured brain dumps into structured, actionable implementation artifacts through a confidence-gated workflow.\n\nWorkflow Pipeline\nINTAKE → CODEBASE EXPLORATION → CONTRACT FORMATION → PHASING → SPEC GENERATION → HANDOFF\n ↓ ↓ ↓ ↓ ↓\n Understand confidence < 95%? PRDs or Repeatable? Analyze deps\n existing code ↓ straight ↓ ↓\n ASK QUESTIONS to specs? Template + Sequential?\n ↓ per-phase Parallel?\n (loop until ≥95%) deltas \n\nPhase 1: Intake\n\nAccept whatever the user provides:\n\nScattered thoughts and half-formed ideas\nVoice dictation transcripts (messy, stream-of-consciousness)\nBullet points mixed with rambling\nTopic jumping and tangents\nContradictions and unclear statements\nTechnical jargon mixed with vague descriptions\n\nDon't require organization. The mess is the input.\n\nAcknowledge receipt and begin analysis. Do not ask for clarification yet.\n\nPhase 2: Codebase Exploration\n\nBefore scoring confidence or generating any artifacts, understand the existing codebase. This is critical — specs written without understanding existing patterns, architecture, and conventions will be generic and wrong.\n\nWhen to Explore\n\nExploration is needed when:\n\nThe brain dump references existing code, features, or systems\nThe project directory contains source code (not a greenfield project)\nThe user mentions extending, modifying, or integrating with existing functionality\n\nSkip exploration for greenfield projects with no existing code.\n\nWhat to Explore\n\nUse file reading and search to understand:\n\nProject structure — What frameworks, languages, and patterns are in use?\nRelevant existing code — What modules/files relate to the brain dump's scope?\nConventions and patterns — How are similar features implemented? What abstractions exist?\nTesting patterns — How is the codebase tested? What infrastructure exists?\nConfiguration and build — What tools, package managers, and CI/CD are in use?\n\nDo not write exploration findings to files. They're context for the ideation process, not an artifact.\n\nPhase 3: Contract Formation\n3.1 Analyze the Brain Dump\n\nExtract from the raw input + codebase exploration:\n\nProblem signals: What pain point or need is being described?\nGoal signals: What does the user want to achieve?\nSuccess signals: How will they know it worked?\nScope signals: What's included? What's explicitly excluded?\nContradictions: Note any conflicting statements\nCodebase constraints: What does the existing architecture enable or limit?\n3.2 Calculate Confidence Score\n\nScore each dimension (0-20 points):\n\nDimension\tQuestion\nProblem Clarity\tDo I understand what problem we're solving and why it matters?\nGoal Definition\tAre the goals specific and measurable?\nSuccess Criteria\tCan I write tests or validation steps for \"done\"?\nScope Boundaries\tDo I know what's in and out of scope?\nConsistency\tAre there contradictions I need resolved?\n\nTotal: /100 points\n\nSee references/confidence-rubric.md for detailed scoring criteria.\n\n3.3 Confidence Thresholds\nScore\tAction\n< 70\tMajor gaps. Ask 5+ questions targeting lowest dimensions.\n70-84\tModerate gaps. Ask 3-5 targeted questions.\n85-94\tMinor gaps. Ask 1-2 specific questions.\n≥ 95\tReady to generate contract.\n3.4 Ask Clarifying Questions\n\nWhen confidence < 95%, ask clarifying questions:\n\nQuestion strategy:\n\nTarget the lowest-scoring dimension first\nBe specific, not open-ended\nOffer options when possible (\"Is it A, B, or C?\")\nReference what was stated (\"You mentioned X, did you mean...?\")\nLimit to 3-5 questions per round\nAfter each round, recalculate confidence\n3.5 Generate Contract\n\nWhen confidence ≥ 95%:\n\nConfirm project name with user\nConvert to kebab-case for directory name\nCreate output directory: ./docs/ideation/{project-name}/\nWrite contract.md using references/contract-template.md\nGet explicit approval before proceeding\n\nDo not proceed until contract is explicitly approved.\n\nPhase 4: Phasing & Specification\n4.1 Choose Workflow\n\nAsk the user:\n\nStraight to specs — Recommended for technical projects. Faster.\nPRDs then specs — Recommended for large scope or cross-functional teams.\n4.2 Determine Phases\n\nSmall-project shortcut: If the scope is small enough to implement in a single phase (1-3 components, touches fewer than ~10 files), skip phasing entirely. Generate a single spec.md.\n\nPhasing criteria (for multi-phase projects):\n\nDependencies (what must be built first?)\nRisk (tackle high-risk items early)\nValue delivery (can users benefit after each phase?)\nComplexity (balance phases for consistent effort)\n4.3 Generate PRDs (if chosen)\n\nFor each phase, generate prd-phase-{n}.md using references/prd-template.md.\n\n4.4 Generate Implementation Specs\n\nGenerate specs using references/spec-template.md:\n\nTechnical approach\nFile changes (new and modified)\nImplementation details with code patterns\nTesting requirements\nError handling\nValidation commands\nPer-component feedback loops\n\nReference existing code: Include \"Pattern to follow: path/to/similar/file.ts\" when relevant patterns exist.\n\n4.5 Present for Review\n\nBefore presenting specs, evaluate feedback loop quality. Present all specs for user approval.\n\nPhase 5: Execution Handoff\n\nPresent the execution strategy:\n\nIdeation complete. Artifacts written to `./docs/ideation/{project-name}/`.\n\n## To start implementation\n\nStart a fresh session and work through the specs in order:\n1. Read the contract for context\n2. Read spec-phase-1.md \n3. Implement following the spec\n4. Validate using the commands in the spec\n5. Commit and move to next phase\n\nOutput Artifacts\n\nAll artifacts written to ./docs/ideation/{project-name}/:\n\ncontract.md # Problem, goals, success, scope\nprd-phase-1.md # Phase 1 requirements (only if PRDs chosen)\nspec-phase-1.md # Phase 1 implementation spec\nspec-template-{pattern}.md # Shared template for repeatable phases (if applicable)\nspec-phase-{n}.md # Per-phase specs\n\nImportant Notes\nExplore the codebase before scoring confidence (unless greenfield).\nScore confidence conservatively. When uncertain, score lower.\nNever skip the confidence check. Don't assume understanding.\nAlways write artifacts to files. Don't just display them.\nEach phase should be independently valuable.\nSpecs should be detailed enough to implement without re-reading PRDs or the contract.\nKeep contracts lean. Heavy docs slow iteration.\nReference existing code patterns in specs.\nSmall projects don't need phases. If scope is 1-3 components, generate a single spec." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/skidvis/openclaw-skill-ideation", "publisherUrl": "https://clawhub.ai/skidvis/openclaw-skill-ideation", "owner": "skidvis", "version": "0.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/openclaw-skill-ideation", "downloadUrl": "https://openagent3.xyz/downloads/openclaw-skill-ideation", "agentUrl": "https://openagent3.xyz/skills/openclaw-skill-ideation/agent", "manifestUrl": "https://openagent3.xyz/skills/openclaw-skill-ideation/agent.json", "briefUrl": "https://openagent3.xyz/skills/openclaw-skill-ideation/agent.md" } }