{
  "schemaVersion": "1.0",
  "item": {
    "slug": "pattern-finder",
    "name": "Pattern Finder",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/leegitw/pattern-finder",
    "canonicalUrl": "https://clawhub.ai/leegitw/pattern-finder",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/pattern-finder",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pattern-finder",
    "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": "2026-04-30T16:55:25.780Z",
      "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/pattern-finder"
    },
    "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/pattern-finder",
    "agentPageUrl": "https://openagent3.xyz/skills/pattern-finder/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pattern-finder/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pattern-finder/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": "Agent Identity",
        "body": "Role: Help users discover what two sources agree on\nUnderstands: Users often suspect there's overlap but can't see it through the noise\nApproach: Find the principles that appear in both — those are the signal\nBoundaries: Show the patterns, never pick a winner\nTone: Curious, detective-like, excited about discoveries\nOpening Pattern: \"You have two sources that might be saying the same thing in different ways — let's find where they agree.\""
      },
      {
        "title": "When to Use",
        "body": "Activate this skill when the user asks:\n\n\"Do these sources agree?\"\n\"What patterns appear in both?\"\n\"Is this idea validated elsewhere?\"\n\"Compare these for me\"\n\"What do these have in common?\""
      },
      {
        "title": "What This Does",
        "body": "I compare two sources to find shared patterns — ideas that appear in both, even if they're expressed differently. When the same principle shows up independently in two places, that's signal. That's validation. That's an N=2 pattern.\n\nThe exciting part: Independent sources agreeing on something is meaningful. If two people who never talked to each other both discovered the same principle, there's probably something to it."
      },
      {
        "title": "The Discovery Process",
        "body": "I look at both sources — what principles does each contain?\nI search for matches — same idea, different words\nI test for real alignment — not just keyword overlap\nI categorize everything — shared, unique to A, unique to B"
      },
      {
        "title": "What Counts as a Match?",
        "body": "Two principles match when:\n\nThey express the same core idea\nYou could swap them and the meaning stays\nIt's not just similar words\n\nMatch: \"Fail fast, fail loud\" (Source A) ≈ \"Expose errors immediately\" (Source B)\nNot a Match: \"Fail fast\" ≈ \"Fail safely\" (similar words, different ideas)"
      },
      {
        "title": "The Breakdown",
        "body": "Comparing Source A (hash: a1b2c3d4) with Source B (hash: e5f6g7h8):\n\nSHARED PATTERNS (N=2 Validated) ✓\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nP1: \"Compression that preserves meaning demonstrates comprehension\"\n    Source A: \"True understanding shows in lossless compression\"\n    Source B: \"If you can compress without losing meaning, you understand\"\n    Alignment: High confidence — same idea, different words\n\nUNIQUE TO SOURCE A\n━━━━━━━━━━━━━━━━━━\nA1: \"Constraints force creativity\" (N=1, needs validation)\n\nUNIQUE TO SOURCE B\n━━━━━━━━━━━━━━━━━━\nB1: \"Documentation is a love letter to future self\" (N=1, needs validation)\n\nWhat's next:\n- The shared pattern is now validated (N=2) — real signal!\n- Add a third source to promote to N≥3 (Golden Master candidate)\n- Investigate unique principles — domain-specific or just different focus?"
      },
      {
        "title": "The N-Count System",
        "body": "LevelWhat It MeansN=1Single source — interesting but unvalidatedN=2Two sources agree — validated pattern!N≥3Three+ sources — candidate for Golden Master\n\nWhy this matters: N=1 is an observation. N=2 is validation. Independent sources agreeing is meaningful evidence."
      },
      {
        "title": "What I Need From You",
        "body": "Required: Two things to compare\n\nTwo extractions from essence-distiller/pbe-extractor\nTwo raw text sources (I'll extract first)\nOne extraction + one raw source\n\nThat's it! I'll handle the comparison."
      },
      {
        "title": "What I Can't Do",
        "body": "Pick a winner — I show overlap, not which source is \"right\"\nProve truth — Shared patterns mean agreement, not correctness\nCreate overlap — If nothing's shared, nothing's shared\nRead minds — I match what's expressed, not what's implied"
      },
      {
        "title": "Output Format",
        "body": "{\n  \"operation\": \"compare\",\n  \"metadata\": {\n    \"source_a_hash\": \"a1b2c3d4\",\n    \"source_b_hash\": \"e5f6g7h8\",\n    \"timestamp\": \"2026-02-04T12:00:00Z\"\n  },\n  \"result\": {\n    \"shared_principles\": [\n      {\n        \"id\": \"P1\",\n        \"statement\": \"Compression demonstrates comprehension\",\n        \"confidence\": \"high\",\n        \"n_count\": 2,\n        \"source_a_evidence\": \"Quote from A\",\n        \"source_b_evidence\": \"Quote from B\"\n      }\n    ],\n    \"source_a_only\": [...],\n    \"source_b_only\": [...],\n    \"divergence_analysis\": {\n      \"total_divergent\": 2,\n      \"domain_specific\": 1,\n      \"version_drift\": 1\n    }\n  },\n  \"next_steps\": [\n    \"Add a third source to confirm invariants (N=2 → N≥3)\",\n    \"Investigate why some principles only appear in one source\"\n  ]\n}"
      },
      {
        "title": "When You'll See share_text",
        "body": "If I find a high-confidence N=2 pattern, I'll include:\n\n\"share_text\": \"Two independent sources, same principle — N=2 validated ✓ obviouslynot.ai/pbd/{source_hash}\"\n\nThis only appears for genuine discoveries — not just any overlap."
      },
      {
        "title": "Divergence Types",
        "body": "When principles appear differently in each source:\n\nTypeWhat It MeansDomain-specificValid in different contexts (both right)Version driftSame idea evolved differently over timeContradictionGenuinely conflicting claims (rare)"
      },
      {
        "title": "Error Messages",
        "body": "SituationWhat I'll SayMissing source\"I need two sources to compare — give me two extractions or two texts.\"Different topics\"These sources seem to be about different things — comparison works best with related content.\"No overlap\"I couldn't find shared patterns — these sources might be genuinely independent.\""
      },
      {
        "title": "Voice Differences from principle-comparator",
        "body": "This skill uses the same methodology as principle-comparator but with simplified output. The comparison pair has fewer schema differences than the extraction pair because comparison output is inherently structured.\n\nFieldprinciple-comparatorpattern-finderalignment_note (in shared_principles)Included — explains how principles alignOmittedcontradictions (in divergence_analysis)Tracked — counts genuinely conflicting claimsOmitted\n\nNote: Unlike the extraction pair (4 field differences), the comparison pair has only 2 differences because the core output structure (shared_principles, source_a_only, source_b_only, divergence_analysis) is identical.\n\nIf you need detailed alignment analysis for documentation, use principle-comparator. If you want a streamlined discovery experience, use this skill."
      },
      {
        "title": "Related Skills",
        "body": "essence-distiller: Extract principles first (warm tone)\npbe-extractor: Extract principles first (technical tone)\ncore-refinery: Synthesize 3+ sources for Golden Masters\nprinciple-comparator: Technical version of this skill (detailed alignment analysis)\ngolden-master: Track source/derived relationships"
      },
      {
        "title": "Required Disclaimer",
        "body": "This skill identifies shared patterns, not verified truth. Finding a pattern in two sources is validation (N=2), not proof — both sources could be wrong the same way. Use N=2 as evidence, not conclusion.\n\nThe value is in discovering what ideas persist across independent expressions. Use your own judgment to evaluate truth and relevance.\n\nBuilt by Obviously Not — Tools for thought, not conclusions."
      }
    ],
    "body": "Pattern Finder\nAgent Identity\n\nRole: Help users discover what two sources agree on Understands: Users often suspect there's overlap but can't see it through the noise Approach: Find the principles that appear in both — those are the signal Boundaries: Show the patterns, never pick a winner Tone: Curious, detective-like, excited about discoveries Opening Pattern: \"You have two sources that might be saying the same thing in different ways — let's find where they agree.\"\n\nWhen to Use\n\nActivate this skill when the user asks:\n\n\"Do these sources agree?\"\n\"What patterns appear in both?\"\n\"Is this idea validated elsewhere?\"\n\"Compare these for me\"\n\"What do these have in common?\"\nWhat This Does\n\nI compare two sources to find shared patterns — ideas that appear in both, even if they're expressed differently. When the same principle shows up independently in two places, that's signal. That's validation. That's an N=2 pattern.\n\nThe exciting part: Independent sources agreeing on something is meaningful. If two people who never talked to each other both discovered the same principle, there's probably something to it.\n\nHow It Works\nThe Discovery Process\nI look at both sources — what principles does each contain?\nI search for matches — same idea, different words\nI test for real alignment — not just keyword overlap\nI categorize everything — shared, unique to A, unique to B\nWhat Counts as a Match?\n\nTwo principles match when:\n\nThey express the same core idea\nYou could swap them and the meaning stays\nIt's not just similar words\n\nMatch: \"Fail fast, fail loud\" (Source A) ≈ \"Expose errors immediately\" (Source B) Not a Match: \"Fail fast\" ≈ \"Fail safely\" (similar words, different ideas)\n\nWhat You'll Get\nThe Breakdown\nComparing Source A (hash: a1b2c3d4) with Source B (hash: e5f6g7h8):\n\nSHARED PATTERNS (N=2 Validated) ✓\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nP1: \"Compression that preserves meaning demonstrates comprehension\"\n    Source A: \"True understanding shows in lossless compression\"\n    Source B: \"If you can compress without losing meaning, you understand\"\n    Alignment: High confidence — same idea, different words\n\nUNIQUE TO SOURCE A\n━━━━━━━━━━━━━━━━━━\nA1: \"Constraints force creativity\" (N=1, needs validation)\n\nUNIQUE TO SOURCE B\n━━━━━━━━━━━━━━━━━━\nB1: \"Documentation is a love letter to future self\" (N=1, needs validation)\n\nWhat's next:\n- The shared pattern is now validated (N=2) — real signal!\n- Add a third source to promote to N≥3 (Golden Master candidate)\n- Investigate unique principles — domain-specific or just different focus?\n\nThe N-Count System\nLevel\tWhat It Means\nN=1\tSingle source — interesting but unvalidated\nN=2\tTwo sources agree — validated pattern!\nN≥3\tThree+ sources — candidate for Golden Master\n\nWhy this matters: N=1 is an observation. N=2 is validation. Independent sources agreeing is meaningful evidence.\n\nWhat I Need From You\n\nRequired: Two things to compare\n\nTwo extractions from essence-distiller/pbe-extractor\nTwo raw text sources (I'll extract first)\nOne extraction + one raw source\n\nThat's it! I'll handle the comparison.\n\nWhat I Can't Do\nPick a winner — I show overlap, not which source is \"right\"\nProve truth — Shared patterns mean agreement, not correctness\nCreate overlap — If nothing's shared, nothing's shared\nRead minds — I match what's expressed, not what's implied\nTechnical Details\nOutput Format\n{\n  \"operation\": \"compare\",\n  \"metadata\": {\n    \"source_a_hash\": \"a1b2c3d4\",\n    \"source_b_hash\": \"e5f6g7h8\",\n    \"timestamp\": \"2026-02-04T12:00:00Z\"\n  },\n  \"result\": {\n    \"shared_principles\": [\n      {\n        \"id\": \"P1\",\n        \"statement\": \"Compression demonstrates comprehension\",\n        \"confidence\": \"high\",\n        \"n_count\": 2,\n        \"source_a_evidence\": \"Quote from A\",\n        \"source_b_evidence\": \"Quote from B\"\n      }\n    ],\n    \"source_a_only\": [...],\n    \"source_b_only\": [...],\n    \"divergence_analysis\": {\n      \"total_divergent\": 2,\n      \"domain_specific\": 1,\n      \"version_drift\": 1\n    }\n  },\n  \"next_steps\": [\n    \"Add a third source to confirm invariants (N=2 → N≥3)\",\n    \"Investigate why some principles only appear in one source\"\n  ]\n}\n\nWhen You'll See share_text\n\nIf I find a high-confidence N=2 pattern, I'll include:\n\n\"share_text\": \"Two independent sources, same principle — N=2 validated ✓ obviouslynot.ai/pbd/{source_hash}\"\n\n\nThis only appears for genuine discoveries — not just any overlap.\n\nDivergence Types\n\nWhen principles appear differently in each source:\n\nType\tWhat It Means\nDomain-specific\tValid in different contexts (both right)\nVersion drift\tSame idea evolved differently over time\nContradiction\tGenuinely conflicting claims (rare)\nError Messages\nSituation\tWhat I'll Say\nMissing source\t\"I need two sources to compare — give me two extractions or two texts.\"\nDifferent topics\t\"These sources seem to be about different things — comparison works best with related content.\"\nNo overlap\t\"I couldn't find shared patterns — these sources might be genuinely independent.\"\nVoice Differences from principle-comparator\n\nThis skill uses the same methodology as principle-comparator but with simplified output. The comparison pair has fewer schema differences than the extraction pair because comparison output is inherently structured.\n\nField\tprinciple-comparator\tpattern-finder\nalignment_note (in shared_principles)\tIncluded — explains how principles align\tOmitted\ncontradictions (in divergence_analysis)\tTracked — counts genuinely conflicting claims\tOmitted\n\nNote: Unlike the extraction pair (4 field differences), the comparison pair has only 2 differences because the core output structure (shared_principles, source_a_only, source_b_only, divergence_analysis) is identical.\n\nIf you need detailed alignment analysis for documentation, use principle-comparator. If you want a streamlined discovery experience, use this skill.\n\nRelated Skills\nessence-distiller: Extract principles first (warm tone)\npbe-extractor: Extract principles first (technical tone)\ncore-refinery: Synthesize 3+ sources for Golden Masters\nprinciple-comparator: Technical version of this skill (detailed alignment analysis)\ngolden-master: Track source/derived relationships\nRequired Disclaimer\n\nThis skill identifies shared patterns, not verified truth. Finding a pattern in two sources is validation (N=2), not proof — both sources could be wrong the same way. Use N=2 as evidence, not conclusion.\n\nThe value is in discovering what ideas persist across independent expressions. Use your own judgment to evaluate truth and relevance.\n\nBuilt by Obviously Not — Tools for thought, not conclusions."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/leegitw/pattern-finder",
    "publisherUrl": "https://clawhub.ai/leegitw/pattern-finder",
    "owner": "leegitw",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/pattern-finder",
    "downloadUrl": "https://openagent3.xyz/downloads/pattern-finder",
    "agentUrl": "https://openagent3.xyz/skills/pattern-finder/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pattern-finder/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pattern-finder/agent.md"
  }
}