{
  "schemaVersion": "1.0",
  "item": {
    "slug": "metaskill",
    "name": "Metaskill",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/fahrulalwan/metaskill",
    "canonicalUrl": "https://clawhub.ai/fahrulalwan/metaskill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/metaskill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=metaskill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "config.yaml",
      "scripts/deep-correct.sh",
      "scripts/eval.sh",
      "scripts/llm_extract.py",
      "scripts/llm_provider.py"
    ],
    "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/metaskill"
    },
    "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/metaskill",
    "agentPageUrl": "https://openagent3.xyz/skills/metaskill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/metaskill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/metaskill/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": "3 Core Components",
        "body": "Deep Self-Correction (deep-correct.sh) — 3-level breakdown on errors:\n\nSurface: What specifically failed\nPrinciple: The underlying rule/constraint violated\nHabit: Concrete behavioral change to prevent recurrence\n\n\n\nTransfer Learning (transfer-check.sh) — Before a task, search past learnings for analogous patterns. Maps domains (e.g., \"auth\" → \"security\") to prevent siloed learning.\n\n\nProactive Pattern Recognition (success-capture.sh) — Log what worked and why, building a repository of successful patterns."
      },
      {
        "title": "Usage",
        "body": "# When an error occurs\nbash skills/metaskill/scripts/deep-correct.sh \"description of the error\"\n\n# Before starting a complex task\nbash skills/metaskill/scripts/transfer-check.sh \"description of the new task\"\n\n# After successful execution\nbash skills/metaskill/scripts/success-capture.sh \"what worked\" \"why it worked\"\n\n# Monthly health eval\nbash skills/metaskill/scripts/eval.sh --save"
      },
      {
        "title": "Configuration (LLM Provider)",
        "body": "Metaskill uses two provider tiers — fast (extraction) and deep (transfer/eval). Edit config.yaml to match your setup:\n\n# config.yaml\nproviders:\n  fast: anthropic   # change to: openai | ollama | gemini\n  deep: anthropic\n\nProviderEnv VarNotesanthropicANTHROPIC_API_KEYDefaultopenaiOPENAI_API_KEYollama(none needed)Local, freegeminiGOOGLE_API_KEY\n\nOllama example (fully local, no API key):\n\nproviders:\n  fast: ollama\n  deep: ollama\nmodels:\n  ollama:\n    fast: llama3.2\n    deep: llama3.1:70b\n\nIf no provider is available, metaskill falls back to manual/heuristic mode (still works, but less precise extraction)."
      },
      {
        "title": "Integration with Self-Improving-Agent",
        "body": "Writes to skills/self-improving-agent/.learnings/ if present, otherwise falls back to its own .learnings/ directory. No extra setup needed."
      },
      {
        "title": "AGENTS.md Wiring (Mandatory)",
        "body": "Add to pre-task checklist:\n\nRun transfer-check.sh before any major task\nRun deep-correct.sh immediately after any error (not just LEARNINGS.md append)\nRun success-capture.sh after complex task completes successfully"
      }
    ],
    "body": "Metaskill\n3 Core Components\n\nDeep Self-Correction (deep-correct.sh) — 3-level breakdown on errors:\n\nSurface: What specifically failed\nPrinciple: The underlying rule/constraint violated\nHabit: Concrete behavioral change to prevent recurrence\n\nTransfer Learning (transfer-check.sh) — Before a task, search past learnings for analogous patterns. Maps domains (e.g., \"auth\" → \"security\") to prevent siloed learning.\n\nProactive Pattern Recognition (success-capture.sh) — Log what worked and why, building a repository of successful patterns.\n\nUsage\n# When an error occurs\nbash skills/metaskill/scripts/deep-correct.sh \"description of the error\"\n\n# Before starting a complex task\nbash skills/metaskill/scripts/transfer-check.sh \"description of the new task\"\n\n# After successful execution\nbash skills/metaskill/scripts/success-capture.sh \"what worked\" \"why it worked\"\n\n# Monthly health eval\nbash skills/metaskill/scripts/eval.sh --save\n\nConfiguration (LLM Provider)\n\nMetaskill uses two provider tiers — fast (extraction) and deep (transfer/eval). Edit config.yaml to match your setup:\n\n# config.yaml\nproviders:\n  fast: anthropic   # change to: openai | ollama | gemini\n  deep: anthropic\n\nProvider\tEnv Var\tNotes\nanthropic\tANTHROPIC_API_KEY\tDefault\nopenai\tOPENAI_API_KEY\t\nollama\t(none needed)\tLocal, free\ngemini\tGOOGLE_API_KEY\t\n\nOllama example (fully local, no API key):\n\nproviders:\n  fast: ollama\n  deep: ollama\nmodels:\n  ollama:\n    fast: llama3.2\n    deep: llama3.1:70b\n\n\nIf no provider is available, metaskill falls back to manual/heuristic mode (still works, but less precise extraction).\n\nIntegration with Self-Improving-Agent\n\nWrites to skills/self-improving-agent/.learnings/ if present, otherwise falls back to its own .learnings/ directory. No extra setup needed.\n\nAGENTS.md Wiring (Mandatory)\n\nAdd to pre-task checklist:\n\nRun transfer-check.sh before any major task\nRun deep-correct.sh immediately after any error (not just LEARNINGS.md append)\nRun success-capture.sh after complex task completes successfully"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/fahrulalwan/metaskill",
    "publisherUrl": "https://clawhub.ai/fahrulalwan/metaskill",
    "owner": "fahrulalwan",
    "version": "1.3.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/metaskill",
    "downloadUrl": "https://openagent3.xyz/downloads/metaskill",
    "agentUrl": "https://openagent3.xyz/skills/metaskill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/metaskill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/metaskill/agent.md"
  }
}