{
  "schemaVersion": "1.0",
  "item": {
    "slug": "learning-engine",
    "name": "learning-engine",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/mupengi-bot/learning-engine",
    "canonicalUrl": "https://clawhub.ai/mupengi-bot/learning-engine",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/learning-engine",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=learning-engine",
    "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/learning-engine"
    },
    "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/learning-engine",
    "agentPageUrl": "https://openagent3.xyz/skills/learning-engine/agent",
    "manifestUrl": "https://openagent3.xyz/skills/learning-engine/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/learning-engine/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": "learning-engine",
        "body": "System records mistakes and successes, automatically learns patterns to improve skills. Automates \"don't repeat same mistake\" principle."
      },
      {
        "title": "1. memory/errors/",
        "body": "Extract failure patterns from error logs\n\n# memory/errors/2026-02-14.md\n\n## 10:30 - insta-post failure\n- Cause: PNG file upload → \"Problem occurred\" error\n- Fix: Retry after JPG conversion → Success\n- Lesson: Always convert to JPG before Instagram upload"
      },
      {
        "title": "2. self-eval Results",
        "body": "Extract improvement points from weekly self-evaluation\n\n# memory/self-eval/2026-W07.md\n\n## This Week's Mistakes\n- Too many browser snapshots (token waste)\n- → Improvement: Call API directly via exec\n\n## This Week's Successes\n- 95% token savings with insta-cli v2 DM check"
      },
      {
        "title": "3. performance Data",
        "body": "Learn successful/unsuccessful patterns from performance tracking\n\n{\n  \"insight\": \"Posts at 7-9 PM get +30% likes\",\n  \"rule\": \"Instagram posts recommended 19:00-21:00\"\n}"
      },
      {
        "title": "Auto Rule Generation",
        "body": "Convert learned patterns to rules:\n\nLocation: memory/learned-rules/\n\nmemory/\n  learned-rules/\n    instagram-posting.md\n    browser-automation.md\n    api-usage.md\n    error-recovery.md"
      },
      {
        "title": "Rule Format",
        "body": "# Instagram Posting Rules\n\n## Rule #1: Always Convert to JPG\n- **Situation**: Upload image to Instagram\n- **Failure Pattern**: PNG file → \"Problem occurred\"\n- **Solution**: `convert input.png -quality 92 output.jpg`\n- **Evidence**: 2026-02-10, 2026-02-14 error logs\n- **Applied Skills**: insta-post, cardnews, social-publisher\n\n## Rule #2: 1:1 Ratio Required\n- **Situation**: Instagram card news\n- **Failure Pattern**: 16:9 horizontal → Cropped in feed\n- **Solution**: Generate as 1024x1024 square\n- **Evidence**: 2026-02-13 feedback\n- **Applied Skills**: cardnews, nano-banana-pro"
      },
      {
        "title": "Inject Rules into Skills",
        "body": "Auto-add learned rules to relevant skill SKILL.md:\n\nLocation: skills/{skill-name}/SKILL.md\n\n# insta-post\n\n...\n\n## Learned Lessons\n\n### Image Processing\n- ✅ Always convert to JPG (PNG causes errors)\n- ✅ 1:1 ratio required (1024x1024 recommended)\n- ✅ File size < 8MB\n\n### Timing\n- ✅ Posts at 19:00-21:00 get +30% engagement\n- ❌ Avoid early morning posts\n\n### Automation\n- ✅ Call API via exec (0 snapshots)\n- ❌ Minimize browser automation"
      },
      {
        "title": "Weekly Learning Report",
        "body": "Auto-generated every Monday:\n\nLocation: memory/learning/weekly-YYYY-Www.md\n\n# 2026-W07 Learning Report\n\n## New Learnings (5)\n\n1. **Instagram PNG Ban**\n   - 3 mistakes → Rule created\n   - Applied: insta-post, cardnews\n\n2. **Token Saving: exec > Browser**\n   - v1: 5 snapshots → v2: 1 exec\n   - 95% savings\n\n3. **Optimal Posting Time**\n   - 19:00-21:00 +30% likes\n\n4. **Brand Tone Effect**\n   - 무펭이 tone +40% engagement\n\n5. **Auto Error Recovery**\n   - browser-dependent failure → Browser restart\n\n## Applied Skills\n- insta-post (2 rules)\n- cardnews (1 rule)\n- performance-tracker (1 insight)\n\n## Next Week Goals\n- [ ] Build A/B testing system\n- [ ] Add 3 auto-recovery patterns"
      },
      {
        "title": "Event Publishing",
        "body": "Publish event when learning complete:\n\nLocation: events/lesson-learned-YYYY-MM-DD.json\n\n{\n  \"timestamp\": \"2026-02-14T23:00:00Z\",\n  \"source\": \"learning-engine\",\n  \"new_rules\": 2,\n  \"updated_skills\": [\"insta-post\", \"cardnews\"],\n  \"summary\": \"Learned 2 Instagram image rules\"\n}"
      },
      {
        "title": "hook-engine Integration",
        "body": "on-error hook: Error occurs → Record to memory/errors/ → learning-engine analysis\npost-hook (self-eval): After weekly evaluation → Update learning rules\npost-hook (performance): After collecting performance data → Learn patterns\nscheduled hook: Every Monday → Generate weekly learning report"
      },
      {
        "title": "Learning Pipeline",
        "body": "Error occurs\n  ↓\nRecord to memory/errors/\n  ↓\nlearning-engine analysis\n  ↓\nExtract patterns + Create rules\n  ↓\nSave to memory/learned-rules/\n  ↓\nAuto-update relevant skill SKILL.md\n  ↓\nPublish event (lesson-learned)\n  ↓\nReflect in weekly report"
      },
      {
        "title": "Trigger Keywords",
        "body": "\"what did I learn\"\n\"learning\"\n\"lessons\"\n\"mistake patterns\"\n\"improvements\"\n\"learning report\"\n\"add rule\""
      },
      {
        "title": "Usage Examples",
        "body": "\"What did I learn this week?\"\n→ Generate weekly learning report\n\n\"Organize Instagram posting mistake patterns\"\n→ Analyze memory/errors/ + Create rules\n\n\"Learn from performance data\"\n→ Extract successful patterns + Update rules"
      },
      {
        "title": "Before (Pre-learning)",
        "body": "Instagram post fails → Manually convert to JPG → Retry\n(Repeat every time)"
      },
      {
        "title": "After (Post-learning)",
        "body": "Execute insta-post → Auto-check/convert JPG → Success\n(Rule injected into SKILL.md)"
      },
      {
        "title": "Meta Learning",
        "body": "learning-engine itself also learns:\n\n\"Which rules are used most?\"\n\"Which skills improve most?\"\n\"Which areas have slow learning?\"\n\nMeta Learning Report: memory/learning/meta-YYYY-MM.md"
      },
      {
        "title": "Future Improvements",
        "body": "Rule conflict detection (Rule A vs Rule B)\n Rule confidence score (based on usage frequency)\n Auto A/B testing (rule validation)\n Share learning with other agents\n\n🐧 Built by 무펭이 — Mupengism ecosystem skill"
      }
    ],
    "body": "learning-engine\n\nSystem records mistakes and successes, automatically learns patterns to improve skills. Automates \"don't repeat same mistake\" principle.\n\nLearning Sources\n1. memory/errors/\n\nExtract failure patterns from error logs\n\n# memory/errors/2026-02-14.md\n\n## 10:30 - insta-post failure\n- Cause: PNG file upload → \"Problem occurred\" error\n- Fix: Retry after JPG conversion → Success\n- Lesson: Always convert to JPG before Instagram upload\n\n2. self-eval Results\n\nExtract improvement points from weekly self-evaluation\n\n# memory/self-eval/2026-W07.md\n\n## This Week's Mistakes\n- Too many browser snapshots (token waste)\n- → Improvement: Call API directly via exec\n\n## This Week's Successes\n- 95% token savings with insta-cli v2 DM check\n\n3. performance Data\n\nLearn successful/unsuccessful patterns from performance tracking\n\n{\n  \"insight\": \"Posts at 7-9 PM get +30% likes\",\n  \"rule\": \"Instagram posts recommended 19:00-21:00\"\n}\n\nAuto Rule Generation\n\nConvert learned patterns to rules:\n\nLocation: memory/learned-rules/\n\nmemory/\n  learned-rules/\n    instagram-posting.md\n    browser-automation.md\n    api-usage.md\n    error-recovery.md\n\nRule Format\n# Instagram Posting Rules\n\n## Rule #1: Always Convert to JPG\n- **Situation**: Upload image to Instagram\n- **Failure Pattern**: PNG file → \"Problem occurred\"\n- **Solution**: `convert input.png -quality 92 output.jpg`\n- **Evidence**: 2026-02-10, 2026-02-14 error logs\n- **Applied Skills**: insta-post, cardnews, social-publisher\n\n## Rule #2: 1:1 Ratio Required\n- **Situation**: Instagram card news\n- **Failure Pattern**: 16:9 horizontal → Cropped in feed\n- **Solution**: Generate as 1024x1024 square\n- **Evidence**: 2026-02-13 feedback\n- **Applied Skills**: cardnews, nano-banana-pro\n\nInject Rules into Skills\n\nAuto-add learned rules to relevant skill SKILL.md:\n\nLocation: skills/{skill-name}/SKILL.md\n\n# insta-post\n\n...\n\n## Learned Lessons\n\n### Image Processing\n- ✅ Always convert to JPG (PNG causes errors)\n- ✅ 1:1 ratio required (1024x1024 recommended)\n- ✅ File size < 8MB\n\n### Timing\n- ✅ Posts at 19:00-21:00 get +30% engagement\n- ❌ Avoid early morning posts\n\n### Automation\n- ✅ Call API via exec (0 snapshots)\n- ❌ Minimize browser automation\n\nWeekly Learning Report\n\nAuto-generated every Monday:\n\nLocation: memory/learning/weekly-YYYY-Www.md\n\n# 2026-W07 Learning Report\n\n## New Learnings (5)\n\n1. **Instagram PNG Ban**\n   - 3 mistakes → Rule created\n   - Applied: insta-post, cardnews\n\n2. **Token Saving: exec > Browser**\n   - v1: 5 snapshots → v2: 1 exec\n   - 95% savings\n\n3. **Optimal Posting Time**\n   - 19:00-21:00 +30% likes\n\n4. **Brand Tone Effect**\n   - 무펭이 tone +40% engagement\n\n5. **Auto Error Recovery**\n   - browser-dependent failure → Browser restart\n\n## Applied Skills\n- insta-post (2 rules)\n- cardnews (1 rule)\n- performance-tracker (1 insight)\n\n## Next Week Goals\n- [ ] Build A/B testing system\n- [ ] Add 3 auto-recovery patterns\n\nEvent Publishing\n\nPublish event when learning complete:\n\nLocation: events/lesson-learned-YYYY-MM-DD.json\n\n{\n  \"timestamp\": \"2026-02-14T23:00:00Z\",\n  \"source\": \"learning-engine\",\n  \"new_rules\": 2,\n  \"updated_skills\": [\"insta-post\", \"cardnews\"],\n  \"summary\": \"Learned 2 Instagram image rules\"\n}\n\nhook-engine Integration\non-error hook: Error occurs → Record to memory/errors/ → learning-engine analysis\npost-hook (self-eval): After weekly evaluation → Update learning rules\npost-hook (performance): After collecting performance data → Learn patterns\nscheduled hook: Every Monday → Generate weekly learning report\nLearning Pipeline\nError occurs\n  ↓\nRecord to memory/errors/\n  ↓\nlearning-engine analysis\n  ↓\nExtract patterns + Create rules\n  ↓\nSave to memory/learned-rules/\n  ↓\nAuto-update relevant skill SKILL.md\n  ↓\nPublish event (lesson-learned)\n  ↓\nReflect in weekly report\n\nTrigger Keywords\n\"what did I learn\"\n\"learning\"\n\"lessons\"\n\"mistake patterns\"\n\"improvements\"\n\"learning report\"\n\"add rule\"\nUsage Examples\n\"What did I learn this week?\"\n→ Generate weekly learning report\n\n\"Organize Instagram posting mistake patterns\"\n→ Analyze memory/errors/ + Create rules\n\n\"Learn from performance data\"\n→ Extract successful patterns + Update rules\n\nAuto-improvement Examples\nBefore (Pre-learning)\nInstagram post fails → Manually convert to JPG → Retry\n(Repeat every time)\n\nAfter (Post-learning)\nExecute insta-post → Auto-check/convert JPG → Success\n(Rule injected into SKILL.md)\n\nMeta Learning\n\nlearning-engine itself also learns:\n\n\"Which rules are used most?\"\n\"Which skills improve most?\"\n\"Which areas have slow learning?\"\n\nMeta Learning Report: memory/learning/meta-YYYY-MM.md\n\nFuture Improvements\n Rule conflict detection (Rule A vs Rule B)\n Rule confidence score (based on usage frequency)\n Auto A/B testing (rule validation)\n Share learning with other agents\n\n🐧 Built by 무펭이 — Mupengism ecosystem skill"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/mupengi-bot/learning-engine",
    "publisherUrl": "https://clawhub.ai/mupengi-bot/learning-engine",
    "owner": "mupengi-bot",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/learning-engine",
    "downloadUrl": "https://openagent3.xyz/downloads/learning-engine",
    "agentUrl": "https://openagent3.xyz/skills/learning-engine/agent",
    "manifestUrl": "https://openagent3.xyz/skills/learning-engine/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/learning-engine/agent.md"
  }
}