{
  "schemaVersion": "1.0",
  "item": {
    "slug": "user-cognitive-profiles",
    "name": "🤖🤝🧠 better collab with your agent",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/sebastianffx/user-cognitive-profiles",
    "canonicalUrl": "https://clawhub.ai/sebastianffx/user-cognitive-profiles",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/user-cognitive-profiles",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=user-cognitive-profiles",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "requirements.txt",
      "references/methodology.md",
      "requirements-test.txt",
      "README.md",
      "examples/sample-profile.json",
      "examples/custom-archetypes.yaml"
    ],
    "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/user-cognitive-profiles"
    },
    "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/user-cognitive-profiles",
    "agentPageUrl": "https://openagent3.xyz/skills/user-cognitive-profiles/agent",
    "manifestUrl": "https://openagent3.xyz/skills/user-cognitive-profiles/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/user-cognitive-profiles/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": "User Cognitive Profiles",
        "body": "🤖🤝🧠 Discover how you communicate with AI and optimize your agent interactions.\n\nThis skill analyzes your ChatGPT conversation history to identify cognitive archetypes — recurring patterns in how you think, communicate, and collaborate. Use these insights to calibrate your OpenClaw agent for more effective, personalized interactions."
      },
      {
        "title": "Why This Matters",
        "body": "Human-AI communication is not one-size-fits-all. Just as you adapt your communication style between contexts (work meeting vs. casual chat), effective AI assistance requires matching your cognitive architecture.\n\nThe Problem:\n\nDefault AI behavior assumes a generic user\nYour communication style varies dramatically by context (professional vs. personal)\nMisaligned AI responses feel inefficient or frustrating\n\nThe Solution:\n\nAnalyze your actual conversation patterns\nIdentify your dominant cognitive archetypes\nConfigure your agent to match your communication style"
      },
      {
        "title": "1. Export Your ChatGPT Data",
        "body": "Go to ChatGPT → Settings → Data Controls → Export Data\nClick \"Export\" and confirm\nWait for the email (usually arrives within 24 hours)\nDownload the ZIP file from the email link\nExtract it — you'll find conversations.json"
      },
      {
        "title": "2. Run the Analysis",
        "body": "cd /path/to/user-cognitive-profiles\npython3 scripts/analyze_profile.py \\\n  --input ~/Downloads/chatgpt-export/conversations.json \\\n  --output ~/.openclaw/my-cognitive-profile.json \\\n  --archetypes 3"
      },
      {
        "title": "3. Apply to Your Agent",
        "body": "Add to your SOUL.md or AGENTS.md:\n\n## User Cognitive Profile\n<!-- Source: generated by user-cognitive-profiles skill -->\n- **Primary Archetype:** Efficiency Optimizer\n- **Avg Message Length:** 47 words\n- **Context Switching:** High (professional vs. personal modes)\n- **Key Patterns:** Prefers direct answers, values examples over theory\n\n### Communication Calibration\n- Default to concise responses\n- Provide examples + theory + hands-on steps\n- Watch for professional/personal mode shifts"
      },
      {
        "title": "Cognitive Archetypes",
        "body": "The analysis identifies archetypes based on four dimensions:\n\nDimensionLowHighMessage LengthBrief commandsExtended analysisStructureOrganic flowSystematic breakdownDepthPractical focusTheoretical explorationToneTransactionalCollaborative"
      },
      {
        "title": "Common Archetypes",
        "body": "🔧 Efficiency Optimizer\n\nMessages: Short, direct, action-oriented\nWants: Quick answers, minimal explanation\nAI Role: Tool to get things done\nExample: \"Set up email. Use pass. Go.\"\n\n🏗️ Systems Architect\n\nMessages: Long, structured, comprehensive\nWants: Deep analysis, trade-offs, strategic thinking\nAI Role: Collaborative partner for complex problems\nExample: 300-word technical breakdown with multiple considerations\n\n🧭 Philosophical Explorer\n\nMessages: Varies widely, questions assumptions\nWants: Meaning, patterns, cross-domain connections\nAI Role: Socratic partner for insight generation\nExample: \"How does this relate to [completely different domain]?\"\n\n🎨 Creative Synthesizer\n\nMessages: Connects disparate ideas, uses analogies\nWants: Novel combinations, pattern recognition\nAI Role: Ideation partner and pattern mirror\nExample: \"This is like jazz improvisation...\""
      },
      {
        "title": "Define Your Own Archetypes",
        "body": "Create ~/.openclaw/my-archetypes.yaml:\n\narchetypes:\n  - name: \"Research Mode\"\n    keywords:\n      - \"research\"\n      - \"analyze\"\n      - \"compare\"\n      - \"trade-off\"\n    patterns:\n      - long_messages\n      - multiple_questions\n      - citation_requests\n    \n  - name: \"Quick Mode\"\n    keywords:\n      - \"quick\"\n      - \"brief\"\n      - \"simple\"\n      - \"just\"\n    patterns:\n      - short_messages\n      - imperative_tone\n      - minimal_context\n\nRun with custom archetypes:\n\npython3 scripts/analyze_profile.py \\\n  --input conversations.json \\\n  --archetypes-config ~/.openclaw/my-archetypes.yaml"
      },
      {
        "title": "Adjust Cluster Count",
        "body": "More archetypes = finer granularity, but harder to act on:\n\n# Simple: 2-3 archetypes\npython3 scripts/analyze_profile.py --archetypes 2\n\n# Detailed: 5-7 archetypes\npython3 scripts/analyze_profile.py --archetypes 5\n\n# Complex: 10+ (for power users)\npython3 scripts/analyze_profile.py --archetypes 10"
      },
      {
        "title": "Profile JSON Structure",
        "body": "{\n  \"metadata\": {\n    \"total_conversations\": 3784,\n    \"date_range\": \"2024-01-01 to 2025-01-31\",\n    \"analysis_date\": \"2026-02-02\"\n  },\n  \"archetypes\": [\n    {\n      \"id\": 0,\n      \"name\": \"Systems Architect\",\n      \"confidence\": 0.87,\n      \"metrics\": {\n        \"avg_message_length\": 382,\n        \"avg_response_length\": 450,\n        \"question_ratio\": 0.23,\n        \"code_block_ratio\": 0.45\n      },\n      \"keywords\": [\"architecture\", \"design\", \"trade-off\", \"system\"],\n      \"sample_conversations\": [\"uuid-1\", \"uuid-2\"],\n      \"recommendations\": {\n        \"ai_role\": \"Senior Architect\",\n        \"communication_style\": \"Detailed, systematic, collaborative\",\n        \"response_length\": \"long\",\n        \"structure\": \"hierarchical\"\n      }\n    }\n  ],\n  \"context_shifts\": [\n    {\n      \"trigger\": \"technical_keywords\",\n      \"from_archetype\": \"Efficiency Optimizer\",\n      \"to_archetype\": \"Systems Architect\"\n    }\n  ],\n  \"insights\": {\n    \"primary_mode\": \"Systems Architect\",\n    \"context_switching\": \"high\",\n    \"communication_preferences\": [\n      \"Examples before theory\",\n      \"Hands-on application\",\n      \"Cross-domain analogies\"\n    ]\n  }\n}"
      },
      {
        "title": "Key Metrics Explained",
        "body": "MetricDescriptionWhy It Mattersavg_message_lengthAverage words per user messageShort = efficiency mode, Long = exploration modequestion_ratio% of turns that are questionsHigh = collaborative, Low = directivecode_block_ratio% of messages with codeTechnical vs. conceptual focuscontext_shiftsDetected mode transitionsIndicates multiple archetypes at playconfidenceCluster cohesion scoreHigher = more distinct pattern"
      },
      {
        "title": "Privacy & Security",
        "body": "All processing is local. The script:\n\n✅ Runs entirely on your machine\n✅ Never uploads data to external services\n✅ Stores results in your local OpenClaw workspace\n✅ You control what gets shared (if anything)\n\nRecommended workflow:\n\nExport ChatGPT data\nRun analysis locally\nReview my-cognitive-profile.json\nManually add relevant insights to SOUL.md\n(Optional) Delete the export and raw profile"
      },
      {
        "title": "Compare Profiles Over Time",
        "body": "Track how your communication evolves:\n\n# January analysis\npython3 scripts/analyze_profile.py \\\n  --input conversations_jan.json \\\n  --output profile_jan.json\n\n# June analysis\npython3 scripts/analyze_profile.py \\\n  --input conversations_jun.json \\\n  --output profile_jun.json\n\n# Compare\npython3 scripts/compare_profiles.py profile_jan.json profile_jun.json"
      },
      {
        "title": "Export for Other Agents",
        "body": "Generate a prompt snippet for Claude, GPT, or other agents:\n\npython3 scripts/analyze_profile.py \\\n  --input conversations.json \\\n  --format prompt-snippet \\\n  --output agent-prompt.txt\n\nOutput:\n\n## User Communication Profile\n- Primary style: Systems Architect (detailed, analytical)\n- Secondary style: Efficiency Optimizer (brief, pragmatic)\n- Context switching: High (watch for mode shifts)\n- Preferences: Examples + theory + hands-on steps\n- Treat as: Senior technical partner, not assistant"
      },
      {
        "title": "\"conversations.json not found\"",
        "body": "The export ZIP contains multiple files. Make sure you're pointing to:\n\nchatgpt-export/\n├── conversations.json  <-- This one\n├── user.json\n└── ..."
      },
      {
        "title": "\"No conversations detected\"",
        "body": "Your export might be empty or corrupted. Check:\n\nhead -20 conversations.json\n\nShould show: [{\"title\": \"...\", \"messages\": [...]}, ...]"
      },
      {
        "title": "\"All archetypes have similar confidence\"",
        "body": "Try adjusting the cluster count:\n\n# Too granular\npython3 scripts/analyze_profile.py --archetypes 10\n\n# Try simpler\npython3 scripts/analyze_profile.py --archetypes 3"
      },
      {
        "title": "\"Analysis takes too long\"",
        "body": "For large conversation histories (10k+ messages):\n\n# Sample for faster analysis\npython3 scripts/analyze_profile.py \\\n  --input conversations.json \\\n  --sample 1000  # Analyze random 1000 conversations"
      },
      {
        "title": "Automatic Profile Loading",
        "body": "Add to your OpenClaw workspace AGENTS.md:\n\n## On Session Start\n1. Read `~/.openclaw/my-cognitive-profile.json` if exists\n2. Adapt communication style to primary archetype\n3. Watch for context shift indicators"
      },
      {
        "title": "Dynamic Mode Detection",
        "body": "For agents that can switch modes mid-conversation:\n\n# Pseudocode for agent integration\ndef detect_mode_shift(current_message, profile):\n    for shift in profile[\"context_shifts\"]:\n        if shift[\"trigger\"] in current_message:\n            return shift[\"to_archetype\"]\n    return profile[\"insights\"][\"primary_mode\"]"
      },
      {
        "title": "Contributing",
        "body": "Have a new archetype that works well? Submit a PR with:\n\nArchetype definition in examples/\nSample data (anonymized)\nValidation that it clusters distinctly"
      },
      {
        "title": "References",
        "body": "references/methodology.md — Technical details on clustering algorithm\nreferences/archetype-taxonomy.md — Full archetype definitions\nexamples/ — Sample profiles and configurations\n\nBuilt for humans who want their AI to truly understand them. 🤖🤝🧠"
      }
    ],
    "body": "User Cognitive Profiles\n\n🤖🤝🧠 Discover how you communicate with AI and optimize your agent interactions.\n\nThis skill analyzes your ChatGPT conversation history to identify cognitive archetypes — recurring patterns in how you think, communicate, and collaborate. Use these insights to calibrate your OpenClaw agent for more effective, personalized interactions.\n\nWhy This Matters\n\nHuman-AI communication is not one-size-fits-all. Just as you adapt your communication style between contexts (work meeting vs. casual chat), effective AI assistance requires matching your cognitive architecture.\n\nThe Problem:\n\nDefault AI behavior assumes a generic user\nYour communication style varies dramatically by context (professional vs. personal)\nMisaligned AI responses feel inefficient or frustrating\n\nThe Solution:\n\nAnalyze your actual conversation patterns\nIdentify your dominant cognitive archetypes\nConfigure your agent to match your communication style\nQuick Start\n1. Export Your ChatGPT Data\nGo to ChatGPT → Settings → Data Controls → Export Data\nClick \"Export\" and confirm\nWait for the email (usually arrives within 24 hours)\nDownload the ZIP file from the email link\nExtract it — you'll find conversations.json\n2. Run the Analysis\ncd /path/to/user-cognitive-profiles\npython3 scripts/analyze_profile.py \\\n  --input ~/Downloads/chatgpt-export/conversations.json \\\n  --output ~/.openclaw/my-cognitive-profile.json \\\n  --archetypes 3\n\n3. Apply to Your Agent\n\nAdd to your SOUL.md or AGENTS.md:\n\n## User Cognitive Profile\n<!-- Source: generated by user-cognitive-profiles skill -->\n- **Primary Archetype:** Efficiency Optimizer\n- **Avg Message Length:** 47 words\n- **Context Switching:** High (professional vs. personal modes)\n- **Key Patterns:** Prefers direct answers, values examples over theory\n\n### Communication Calibration\n- Default to concise responses\n- Provide examples + theory + hands-on steps\n- Watch for professional/personal mode shifts\n\nCognitive Archetypes\n\nThe analysis identifies archetypes based on four dimensions:\n\nDimension\tLow\tHigh\nMessage Length\tBrief commands\tExtended analysis\nStructure\tOrganic flow\tSystematic breakdown\nDepth\tPractical focus\tTheoretical exploration\nTone\tTransactional\tCollaborative\nCommon Archetypes\n🔧 Efficiency Optimizer\nMessages: Short, direct, action-oriented\nWants: Quick answers, minimal explanation\nAI Role: Tool to get things done\nExample: \"Set up email. Use pass. Go.\"\n🏗️ Systems Architect\nMessages: Long, structured, comprehensive\nWants: Deep analysis, trade-offs, strategic thinking\nAI Role: Collaborative partner for complex problems\nExample: 300-word technical breakdown with multiple considerations\n🧭 Philosophical Explorer\nMessages: Varies widely, questions assumptions\nWants: Meaning, patterns, cross-domain connections\nAI Role: Socratic partner for insight generation\nExample: \"How does this relate to [completely different domain]?\"\n🎨 Creative Synthesizer\nMessages: Connects disparate ideas, uses analogies\nWants: Novel combinations, pattern recognition\nAI Role: Ideation partner and pattern mirror\nExample: \"This is like jazz improvisation...\"\nCustomization\nDefine Your Own Archetypes\n\nCreate ~/.openclaw/my-archetypes.yaml:\n\narchetypes:\n  - name: \"Research Mode\"\n    keywords:\n      - \"research\"\n      - \"analyze\"\n      - \"compare\"\n      - \"trade-off\"\n    patterns:\n      - long_messages\n      - multiple_questions\n      - citation_requests\n    \n  - name: \"Quick Mode\"\n    keywords:\n      - \"quick\"\n      - \"brief\"\n      - \"simple\"\n      - \"just\"\n    patterns:\n      - short_messages\n      - imperative_tone\n      - minimal_context\n\n\nRun with custom archetypes:\n\npython3 scripts/analyze_profile.py \\\n  --input conversations.json \\\n  --archetypes-config ~/.openclaw/my-archetypes.yaml\n\nAdjust Cluster Count\n\nMore archetypes = finer granularity, but harder to act on:\n\n# Simple: 2-3 archetypes\npython3 scripts/analyze_profile.py --archetypes 2\n\n# Detailed: 5-7 archetypes\npython3 scripts/analyze_profile.py --archetypes 5\n\n# Complex: 10+ (for power users)\npython3 scripts/analyze_profile.py --archetypes 10\n\nUnderstanding the Output\nProfile JSON Structure\n{\n  \"metadata\": {\n    \"total_conversations\": 3784,\n    \"date_range\": \"2024-01-01 to 2025-01-31\",\n    \"analysis_date\": \"2026-02-02\"\n  },\n  \"archetypes\": [\n    {\n      \"id\": 0,\n      \"name\": \"Systems Architect\",\n      \"confidence\": 0.87,\n      \"metrics\": {\n        \"avg_message_length\": 382,\n        \"avg_response_length\": 450,\n        \"question_ratio\": 0.23,\n        \"code_block_ratio\": 0.45\n      },\n      \"keywords\": [\"architecture\", \"design\", \"trade-off\", \"system\"],\n      \"sample_conversations\": [\"uuid-1\", \"uuid-2\"],\n      \"recommendations\": {\n        \"ai_role\": \"Senior Architect\",\n        \"communication_style\": \"Detailed, systematic, collaborative\",\n        \"response_length\": \"long\",\n        \"structure\": \"hierarchical\"\n      }\n    }\n  ],\n  \"context_shifts\": [\n    {\n      \"trigger\": \"technical_keywords\",\n      \"from_archetype\": \"Efficiency Optimizer\",\n      \"to_archetype\": \"Systems Architect\"\n    }\n  ],\n  \"insights\": {\n    \"primary_mode\": \"Systems Architect\",\n    \"context_switching\": \"high\",\n    \"communication_preferences\": [\n      \"Examples before theory\",\n      \"Hands-on application\",\n      \"Cross-domain analogies\"\n    ]\n  }\n}\n\nKey Metrics Explained\nMetric\tDescription\tWhy It Matters\navg_message_length\tAverage words per user message\tShort = efficiency mode, Long = exploration mode\nquestion_ratio\t% of turns that are questions\tHigh = collaborative, Low = directive\ncode_block_ratio\t% of messages with code\tTechnical vs. conceptual focus\ncontext_shifts\tDetected mode transitions\tIndicates multiple archetypes at play\nconfidence\tCluster cohesion score\tHigher = more distinct pattern\nPrivacy & Security\n\nAll processing is local. The script:\n\n✅ Runs entirely on your machine\n✅ Never uploads data to external services\n✅ Stores results in your local OpenClaw workspace\n✅ You control what gets shared (if anything)\n\nRecommended workflow:\n\nExport ChatGPT data\nRun analysis locally\nReview my-cognitive-profile.json\nManually add relevant insights to SOUL.md\n(Optional) Delete the export and raw profile\nAdvanced Usage\nCompare Profiles Over Time\n\nTrack how your communication evolves:\n\n# January analysis\npython3 scripts/analyze_profile.py \\\n  --input conversations_jan.json \\\n  --output profile_jan.json\n\n# June analysis\npython3 scripts/analyze_profile.py \\\n  --input conversations_jun.json \\\n  --output profile_jun.json\n\n# Compare\npython3 scripts/compare_profiles.py profile_jan.json profile_jun.json\n\nExport for Other Agents\n\nGenerate a prompt snippet for Claude, GPT, or other agents:\n\npython3 scripts/analyze_profile.py \\\n  --input conversations.json \\\n  --format prompt-snippet \\\n  --output agent-prompt.txt\n\n\nOutput:\n\n## User Communication Profile\n- Primary style: Systems Architect (detailed, analytical)\n- Secondary style: Efficiency Optimizer (brief, pragmatic)\n- Context switching: High (watch for mode shifts)\n- Preferences: Examples + theory + hands-on steps\n- Treat as: Senior technical partner, not assistant\n\nTroubleshooting\n\"conversations.json not found\"\n\nThe export ZIP contains multiple files. Make sure you're pointing to:\n\nchatgpt-export/\n├── conversations.json  <-- This one\n├── user.json\n└── ...\n\n\"No conversations detected\"\n\nYour export might be empty or corrupted. Check:\n\nhead -20 conversations.json\n\n\nShould show: [{\"title\": \"...\", \"messages\": [...]}, ...]\n\n\"All archetypes have similar confidence\"\n\nTry adjusting the cluster count:\n\n# Too granular\npython3 scripts/analyze_profile.py --archetypes 10\n\n# Try simpler\npython3 scripts/analyze_profile.py --archetypes 3\n\n\"Analysis takes too long\"\n\nFor large conversation histories (10k+ messages):\n\n# Sample for faster analysis\npython3 scripts/analyze_profile.py \\\n  --input conversations.json \\\n  --sample 1000  # Analyze random 1000 conversations\n\nIntegration with OpenClaw\nAutomatic Profile Loading\n\nAdd to your OpenClaw workspace AGENTS.md:\n\n## On Session Start\n1. Read `~/.openclaw/my-cognitive-profile.json` if exists\n2. Adapt communication style to primary archetype\n3. Watch for context shift indicators\n\nDynamic Mode Detection\n\nFor agents that can switch modes mid-conversation:\n\n# Pseudocode for agent integration\ndef detect_mode_shift(current_message, profile):\n    for shift in profile[\"context_shifts\"]:\n        if shift[\"trigger\"] in current_message:\n            return shift[\"to_archetype\"]\n    return profile[\"insights\"][\"primary_mode\"]\n\nContributing\n\nHave a new archetype that works well? Submit a PR with:\n\nArchetype definition in examples/\nSample data (anonymized)\nValidation that it clusters distinctly\nReferences\nreferences/methodology.md — Technical details on clustering algorithm\nreferences/archetype-taxonomy.md — Full archetype definitions\nexamples/ — Sample profiles and configurations\n\nBuilt for humans who want their AI to truly understand them. 🤖🤝🧠"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/sebastianffx/user-cognitive-profiles",
    "publisherUrl": "https://clawhub.ai/sebastianffx/user-cognitive-profiles",
    "owner": "sebastianffx",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/user-cognitive-profiles",
    "downloadUrl": "https://openagent3.xyz/downloads/user-cognitive-profiles",
    "agentUrl": "https://openagent3.xyz/skills/user-cognitive-profiles/agent",
    "manifestUrl": "https://openagent3.xyz/skills/user-cognitive-profiles/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/user-cognitive-profiles/agent.md"
  }
}