{
  "schemaVersion": "1.0",
  "item": {
    "slug": "extraction",
    "name": "Skill Extraction",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/wpank/extraction",
    "canonicalUrl": "https://clawhub.ai/wpank/extraction",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/extraction",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=extraction",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "COMMAND.md",
      "SKILL.md",
      "references/validation-checklist.md",
      "references/methodology-values.md",
      "references/extraction-categories.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/extraction"
    },
    "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/extraction",
    "agentPageUrl": "https://openagent3.xyz/skills/extraction/agent",
    "manifestUrl": "https://openagent3.xyz/skills/extraction/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/extraction/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Pattern Extraction",
        "body": "Extract reusable patterns, skills, and methodology documentation from existing codebases."
      },
      {
        "title": "OpenClaw / Moltbot / Clawbot",
        "body": "npx clawhub@latest install extraction"
      },
      {
        "title": "Before Starting",
        "body": "MANDATORY: Read these reference files based on what you're extracting:\n\nExtractingRead FirstAny extractionmethodology-values.md — priority order and what to look forSpecific categoriesextraction-categories.md — detailed patterns per categoryGenerating skillsskill-quality-criteria.md — quality checklist"
      },
      {
        "title": "Phase 1: Discovery",
        "body": "Analyze the project to understand what exists.\n\nScan for project structure:\n\n- Root directory layout\n- Key config files (package.json, tailwind.config.*, etc.)\n- Documentation (README, docs/, etc.)\n- Source organization (src/, app/, components/, etc.)\n\nIdentify tech stack:\n\nIndicatorTechnologypackage.json with reactReacttailwind.config.*Tailwind CSScomponents.jsonshadcn/uigo.modGoDockerfileDockerk8s/ or .yaml manifestsKubernetesturbo.jsonTurborepoMakefileMake automation\n\nLook for design system signals:\n\nCustom Tailwind config (not defaults)\nCSS variables / custom properties\nTheme files\nDesign documentation\nMood boards or reference lists\n\nCapture key findings:\n\nWhat's the tech stack?\nWhat's the folder structure?\nIs there a documented design direction?\nWhat workflows exist (Makefile, scripts)?"
      },
      {
        "title": "Phase 2: Categorization",
        "body": "Map discoveries to extraction categories, prioritized:\n\nPriority order:\n\nDesign Systems — Color tokens, typography, spacing, motion, aesthetic documentation\nUI Patterns — Component organization, layouts, interactions\nArchitecture — Folder structure, data flow, API patterns\nWorkflows — Build, dev, deploy, CI/CD\nDomain-Specific — Patterns unique to this application type\n\nFor each category found, note:\n\nWhat specific patterns exist?\nWhere are they defined? (file paths)\nAre they documented? (comments, docs)\nAre they worth extracting? (used in multiple places, well-designed)\n\nFilter by value:\n\nExtractSkipPatterns used across multiple componentsOne-off solutionsCustomized configs with intentionDefault configurationsDocumented design decisionsArbitrary choicesReusable infrastructureProject-specific hacks"
      },
      {
        "title": "Phase 3: Extraction",
        "body": "For each valuable pattern, generate outputs.\n\nDesign Systems → Design System Doc + Skill\n\nRead the Tailwind config, CSS files, theme files\nExtract actual token values (colors, typography, spacing)\nDocument the aesthetic direction\nCreate:\n\ndocs/extracted/[project]-design-system.md using design-system.md template\nai/skills/[project]-design-system/SKILL.md if patterns are reusable\n\nArchitecture → Methodology Doc\n\nDocument folder structure with reasoning\nCapture data flow patterns\nNote key technical decisions\nCreate docs/extracted/[project]-summary.md using project-summary.md template\n\nPatterns → Skills\n\nFor each pattern worth a skill:\n\nLoad skill-quality-criteria.md\nUse skill-template.md template\nVerify the quality checklist:\n\nDescription has WHAT, WHEN, KEYWORDS\nNo explanations of basics Claude knows\nHas specific NEVER list\n< 300 lines ideal\n\n\nCreate ai/skills/[project]-[pattern]/SKILL.md"
      },
      {
        "title": "Phase 4: Validation",
        "body": "Before writing output, validate extracted content.\n\nFor each skill, verify:\n\nDescription has WHAT, WHEN, and trigger KEYWORDS\n >70% expert knowledge (not in base Claude model)\n <300 lines (max 500)\n Has \"When to Use\" section with clear triggers\n Has code examples (if applicable)\n Has NEVER Do section with anti-patterns\n Project-agnostic (no hardcoded project names)\n\nFor documentation, verify:\n\nActual values extracted (not placeholders)\n Templates fully filled out\n Aesthetic direction documented (for design systems)\n File paths are correct\n\nConflict detection:\nBefore creating a new skill, check if similar skills exist:\n\n# Check existing skills in the target repo\nls ai/skills/*/\n\nSituationActionSimilar skill existsEnhance existing skill insteadOverlapping patternsNote overlap, may merge in refinementUnique patternProceed with new skill"
      },
      {
        "title": "Phase 5: Output",
        "body": "Write extracted content to target locations.\n\nMethodology Documentation:\n\ndocs/extracted/\n├── [project]-summary.md       # Overall methodology\n├── [project]-design-system.md # Design tokens and aesthetic\n└── [project]-architecture.md  # Code patterns (if complex)\n\nSkills:\n\nai/skills/\n└── [project]-[category]/\n    ├── SKILL.md\n    └── references/  # (if needed for detailed content)\n\nCreate docs/extracted/ directory if it doesn't exist."
      },
      {
        "title": "Design System Extraction (Highest Priority)",
        "body": "When a project has intentional design work, extract thoroughly:\n\nMust capture:\n\nColor palette (primary, secondary, accent, semantic)\nTypography (fonts, scale, weights)\nSpacing scale\nMotion/animation patterns\nThe \"vibe\" or aesthetic direction\n\nLook in:\n\ntailwind.config.js / tailwind.config.ts\nglobals.css / app.css / root CSS files\ntheme.ts / theme.js\nAny design documentation\n\nGenerate:\n\nDesign system documentation with actual values\nSkill capturing the aesthetic philosophy (if distinctive)"
      },
      {
        "title": "Workflow Extraction",
        "body": "Look for:\n\nMakefile targets\npackage.json scripts\nDocker configurations\nCI/CD workflows\n\nExtract:\n\nDev setup commands\nBuild processes\nDeployment patterns"
      },
      {
        "title": "Error Handling",
        "body": "SituationResolutionNo patterns foundCreate project summary only; document why extraction failedPattern too project-specificSkip or generalize by removing project namesIncomplete patternExtract what exists, note gaps in skillQuality criteria not metRevise skill or skip patternSimilar skill already existsUpdate existing skill instead of creating newCan't find source filesNote in extraction log, skip that category\n\nWhen extraction fails partially:\n\nComplete what can be extracted\nDocument gaps in the project summary\nNote \"Incomplete extraction\" in output\nSuggest what additional information would be needed"
      },
      {
        "title": "NEVER Do",
        "body": "NEVER extract default configurations — Only extract customized, intentional patterns\nNEVER create skills for basic concepts — Claude already knows React, Tailwind basics\nNEVER skip the aesthetic — Design philosophy is highest priority\nNEVER generate skills > 500 lines — Use references/ for detailed content\nNEVER create skills without good descriptions — Description determines if skill activates\nNEVER extract one-off solutions — Focus on patterns used in multiple places\nNEVER skip validation phase — Quality check before writing output\nNEVER leave project names in skills — Make patterns project-agnostic\nNEVER create duplicate skills — Check for existing similar skills first"
      },
      {
        "title": "Quality Check Before Finishing",
        "body": "Design system captured (if one exists)?\n Methodology summary created?\n Skills have proper descriptions (WHAT, WHEN, KEYWORDS)?\n Skills pass the expert knowledge test?\n Anti-patterns documented in skills?\n Output files created in correct locations?"
      },
      {
        "title": "After Extraction: Staging for Refinement",
        "body": "If you're extracting to later consolidate patterns across multiple projects:\n\nCopy results to the skills toolkit repo for staging:\n\n# From this project, copy to the skills repo staging area\ncp -r ai/skills/[project]-* /path/to/skills-repo/ai/staging/skills/\ncp -r docs/extracted/* /path/to/skills-repo/ai/staging/docs/\n\nStaging folder structure:\n\nai/staging/\n├── skills/           # Extracted skills from multiple projects\n│   ├── project-a-design-system/\n│   ├── project-b-ui-patterns/\n│   └── ...\n└── docs/             # Extracted methodology docs\n    ├── project-a-summary.md\n    ├── project-b-design-system.md\n    └── ...\n\nAfter staging content from multiple projects:\n\nSay \"refine staged content\" or \"consolidate staged skills\"\nThe refinement process will:\n\nIdentify patterns across projects\nConsolidate into project-agnostic skills\nUpdate methodology docs with insights\nPromote refined skills to active locations"
      },
      {
        "title": "Related Skills",
        "body": "Agent: ai/agents/extraction/ — Autonomous extraction workflow\nCommand: /extract-patterns — Quick extraction command\nNext step: ai/skills/refinement/ — Consolidate extracted patterns\nQuality criteria: references/skill-quality-criteria.md"
      }
    ],
    "body": "Pattern Extraction\n\nExtract reusable patterns, skills, and methodology documentation from existing codebases.\n\nInstallation\nOpenClaw / Moltbot / Clawbot\nnpx clawhub@latest install extraction\n\nBefore Starting\n\nMANDATORY: Read these reference files based on what you're extracting:\n\nExtracting\tRead First\nAny extraction\tmethodology-values.md — priority order and what to look for\nSpecific categories\textraction-categories.md — detailed patterns per category\nGenerating skills\tskill-quality-criteria.md — quality checklist\nExtraction Process\nPhase 1: Discovery\n\nAnalyze the project to understand what exists.\n\nScan for project structure:\n\n- Root directory layout\n- Key config files (package.json, tailwind.config.*, etc.)\n- Documentation (README, docs/, etc.)\n- Source organization (src/, app/, components/, etc.)\n\n\nIdentify tech stack:\n\nIndicator\tTechnology\npackage.json with react\tReact\ntailwind.config.*\tTailwind CSS\ncomponents.json\tshadcn/ui\ngo.mod\tGo\nDockerfile\tDocker\nk8s/ or .yaml manifests\tKubernetes\nturbo.json\tTurborepo\nMakefile\tMake automation\n\nLook for design system signals:\n\nCustom Tailwind config (not defaults)\nCSS variables / custom properties\nTheme files\nDesign documentation\nMood boards or reference lists\n\nCapture key findings:\n\nWhat's the tech stack?\nWhat's the folder structure?\nIs there a documented design direction?\nWhat workflows exist (Makefile, scripts)?\nPhase 2: Categorization\n\nMap discoveries to extraction categories, prioritized:\n\nPriority order:\n\nDesign Systems — Color tokens, typography, spacing, motion, aesthetic documentation\nUI Patterns — Component organization, layouts, interactions\nArchitecture — Folder structure, data flow, API patterns\nWorkflows — Build, dev, deploy, CI/CD\nDomain-Specific — Patterns unique to this application type\n\nFor each category found, note:\n\nWhat specific patterns exist?\nWhere are they defined? (file paths)\nAre they documented? (comments, docs)\nAre they worth extracting? (used in multiple places, well-designed)\n\nFilter by value:\n\nExtract\tSkip\nPatterns used across multiple components\tOne-off solutions\nCustomized configs with intention\tDefault configurations\nDocumented design decisions\tArbitrary choices\nReusable infrastructure\tProject-specific hacks\nPhase 3: Extraction\n\nFor each valuable pattern, generate outputs.\n\nDesign Systems → Design System Doc + Skill\n\nRead the Tailwind config, CSS files, theme files\nExtract actual token values (colors, typography, spacing)\nDocument the aesthetic direction\nCreate:\ndocs/extracted/[project]-design-system.md using design-system.md template\nai/skills/[project]-design-system/SKILL.md if patterns are reusable\n\nArchitecture → Methodology Doc\n\nDocument folder structure with reasoning\nCapture data flow patterns\nNote key technical decisions\nCreate docs/extracted/[project]-summary.md using project-summary.md template\n\nPatterns → Skills\n\nFor each pattern worth a skill:\n\nLoad skill-quality-criteria.md\nUse skill-template.md template\nVerify the quality checklist:\nDescription has WHAT, WHEN, KEYWORDS\nNo explanations of basics Claude knows\nHas specific NEVER list\n< 300 lines ideal\nCreate ai/skills/[project]-[pattern]/SKILL.md\nPhase 4: Validation\n\nBefore writing output, validate extracted content.\n\nFor each skill, verify:\n\n Description has WHAT, WHEN, and trigger KEYWORDS\n >70% expert knowledge (not in base Claude model)\n <300 lines (max 500)\n Has \"When to Use\" section with clear triggers\n Has code examples (if applicable)\n Has NEVER Do section with anti-patterns\n Project-agnostic (no hardcoded project names)\n\nFor documentation, verify:\n\n Actual values extracted (not placeholders)\n Templates fully filled out\n Aesthetic direction documented (for design systems)\n File paths are correct\n\nConflict detection: Before creating a new skill, check if similar skills exist:\n\n# Check existing skills in the target repo\nls ai/skills/*/\n\nSituation\tAction\nSimilar skill exists\tEnhance existing skill instead\nOverlapping patterns\tNote overlap, may merge in refinement\nUnique pattern\tProceed with new skill\nPhase 5: Output\n\nWrite extracted content to target locations.\n\nMethodology Documentation:\n\ndocs/extracted/\n├── [project]-summary.md       # Overall methodology\n├── [project]-design-system.md # Design tokens and aesthetic\n└── [project]-architecture.md  # Code patterns (if complex)\n\n\nSkills:\n\nai/skills/\n└── [project]-[category]/\n    ├── SKILL.md\n    └── references/  # (if needed for detailed content)\n\n\nCreate docs/extracted/ directory if it doesn't exist.\n\nExtraction Focus Areas\nDesign System Extraction (Highest Priority)\n\nWhen a project has intentional design work, extract thoroughly:\n\nMust capture:\n\nColor palette (primary, secondary, accent, semantic)\nTypography (fonts, scale, weights)\nSpacing scale\nMotion/animation patterns\nThe \"vibe\" or aesthetic direction\n\nLook in:\n\ntailwind.config.js / tailwind.config.ts\nglobals.css / app.css / root CSS files\ntheme.ts / theme.js\nAny design documentation\n\nGenerate:\n\nDesign system documentation with actual values\nSkill capturing the aesthetic philosophy (if distinctive)\nWorkflow Extraction\n\nLook for:\n\nMakefile targets\npackage.json scripts\nDocker configurations\nCI/CD workflows\n\nExtract:\n\nDev setup commands\nBuild processes\nDeployment patterns\nError Handling\nSituation\tResolution\nNo patterns found\tCreate project summary only; document why extraction failed\nPattern too project-specific\tSkip or generalize by removing project names\nIncomplete pattern\tExtract what exists, note gaps in skill\nQuality criteria not met\tRevise skill or skip pattern\nSimilar skill already exists\tUpdate existing skill instead of creating new\nCan't find source files\tNote in extraction log, skip that category\n\nWhen extraction fails partially:\n\nComplete what can be extracted\nDocument gaps in the project summary\nNote \"Incomplete extraction\" in output\nSuggest what additional information would be needed\nNEVER Do\nNEVER extract default configurations — Only extract customized, intentional patterns\nNEVER create skills for basic concepts — Claude already knows React, Tailwind basics\nNEVER skip the aesthetic — Design philosophy is highest priority\nNEVER generate skills > 500 lines — Use references/ for detailed content\nNEVER create skills without good descriptions — Description determines if skill activates\nNEVER extract one-off solutions — Focus on patterns used in multiple places\nNEVER skip validation phase — Quality check before writing output\nNEVER leave project names in skills — Make patterns project-agnostic\nNEVER create duplicate skills — Check for existing similar skills first\nQuality Check Before Finishing\n Design system captured (if one exists)?\n Methodology summary created?\n Skills have proper descriptions (WHAT, WHEN, KEYWORDS)?\n Skills pass the expert knowledge test?\n Anti-patterns documented in skills?\n Output files created in correct locations?\nAfter Extraction: Staging for Refinement\n\nIf you're extracting to later consolidate patterns across multiple projects:\n\nCopy results to the skills toolkit repo for staging:\n\n# From this project, copy to the skills repo staging area\ncp -r ai/skills/[project]-* /path/to/skills-repo/ai/staging/skills/\ncp -r docs/extracted/* /path/to/skills-repo/ai/staging/docs/\n\n\nStaging folder structure:\n\nai/staging/\n├── skills/           # Extracted skills from multiple projects\n│   ├── project-a-design-system/\n│   ├── project-b-ui-patterns/\n│   └── ...\n└── docs/             # Extracted methodology docs\n    ├── project-a-summary.md\n    ├── project-b-design-system.md\n    └── ...\n\n\nAfter staging content from multiple projects:\n\nSay \"refine staged content\" or \"consolidate staged skills\"\nThe refinement process will:\nIdentify patterns across projects\nConsolidate into project-agnostic skills\nUpdate methodology docs with insights\nPromote refined skills to active locations\nRelated Skills\nAgent: ai/agents/extraction/ — Autonomous extraction workflow\nCommand: /extract-patterns — Quick extraction command\nNext step: ai/skills/refinement/ — Consolidate extracted patterns\nQuality criteria: references/skill-quality-criteria.md"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wpank/extraction",
    "publisherUrl": "https://clawhub.ai/wpank/extraction",
    "owner": "wpank",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/extraction",
    "downloadUrl": "https://openagent3.xyz/downloads/extraction",
    "agentUrl": "https://openagent3.xyz/skills/extraction/agent",
    "manifestUrl": "https://openagent3.xyz/skills/extraction/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/extraction/agent.md"
  }
}