{
  "schemaVersion": "1.0",
  "item": {
    "slug": "loop",
    "name": "Loop",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ivangdavila/loop",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/loop",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/loop",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=loop",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "examples.md",
      "memory.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",
      "slug": "loop",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T07:18:31.170Z",
      "expiresAt": "2026-05-09T07:18:31.170Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=loop",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=loop",
        "contentDisposition": "attachment; filename=\"loop-1.0.2.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "loop"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/loop"
    },
    "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/loop",
    "agentPageUrl": "https://openagent3.xyz/skills/loop/agent",
    "manifestUrl": "https://openagent3.xyz/skills/loop/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/loop/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": "Data Storage",
        "body": "~/loop/\n├── active.json         # Currently running loops\n├── history/            # Completed loop logs\n│   └── {loop-id}.json\n└── learnings.md        # Cross-loop patterns\n\nCreate on first use: mkdir -p ~/loop/history"
      },
      {
        "title": "Scope",
        "body": "This skill:\n\n✅ Runs iterative attempts toward defined success criteria\n✅ Logs each iteration with learnings\n✅ Exits on success, max iterations, or unrecoverable error\n❌ NEVER makes Git commits automatically\n❌ NEVER deploys to production\n❌ NEVER modifies system configuration\n❌ NEVER runs indefinitely (max 10 iterations hard limit)"
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileLoop examplesexamples.mdMemory between iterationsmemory.md"
      },
      {
        "title": "1. Pattern",
        "body": "Task + Criteria → Execute → Verify → [Pass? Exit : Retry]"
      },
      {
        "title": "2. Required Setup",
        "body": "ElementRequiredExampleTaskYes\"Fix failing tests\"Success criteriaYes\"All tests pass\"Max iterationsDefault: 5Max: 10Verify commandRecommendednpm test"
      },
      {
        "title": "3. When to Propose",
        "body": "Task has clear success criteria but uncertain path\nPrevious attempt failed but error is fixable\nUser says \"keep trying until...\"\n\nNOT for: One-shot tasks, undefined goals, exploratory work"
      },
      {
        "title": "4. Each Iteration",
        "body": "Fresh context — Only carry: task, criteria, count, learnings\nExecute — Attempt the task\nVerify — Check success criteria\nRecord — Append to history: what worked, what failed\nDecide — Pass? Exit. Fail? Retry if under limit."
      },
      {
        "title": "5. Stopping Conditions",
        "body": "✅ Success criteria met\n❌ Max iterations reached\n⚠️ Unrecoverable error (missing dependency, permission denied)"
      },
      {
        "title": "6. On Failure",
        "body": "If max reached without success:\n\nSummarize all attempts\nIdentify common failure pattern\nRecommend manual intervention or different approach"
      },
      {
        "title": "7. Safety",
        "body": "Hard limit: 10 iterations maximum\nNo destructive actions without explicit per-action approval\nLog everything to ~/loop/history/"
      }
    ],
    "body": "Data Storage\n~/loop/\n├── active.json         # Currently running loops\n├── history/            # Completed loop logs\n│   └── {loop-id}.json\n└── learnings.md        # Cross-loop patterns\n\n\nCreate on first use: mkdir -p ~/loop/history\n\nScope\n\nThis skill:\n\n✅ Runs iterative attempts toward defined success criteria\n✅ Logs each iteration with learnings\n✅ Exits on success, max iterations, or unrecoverable error\n❌ NEVER makes Git commits automatically\n❌ NEVER deploys to production\n❌ NEVER modifies system configuration\n❌ NEVER runs indefinitely (max 10 iterations hard limit)\nQuick Reference\nTopic\tFile\nLoop examples\texamples.md\nMemory between iterations\tmemory.md\nCore Rules\n1. Pattern\nTask + Criteria → Execute → Verify → [Pass? Exit : Retry]\n\n2. Required Setup\nElement\tRequired\tExample\nTask\tYes\t\"Fix failing tests\"\nSuccess criteria\tYes\t\"All tests pass\"\nMax iterations\tDefault: 5\tMax: 10\nVerify command\tRecommended\tnpm test\n3. When to Propose\nTask has clear success criteria but uncertain path\nPrevious attempt failed but error is fixable\nUser says \"keep trying until...\"\n\nNOT for: One-shot tasks, undefined goals, exploratory work\n\n4. Each Iteration\nFresh context — Only carry: task, criteria, count, learnings\nExecute — Attempt the task\nVerify — Check success criteria\nRecord — Append to history: what worked, what failed\nDecide — Pass? Exit. Fail? Retry if under limit.\n5. Stopping Conditions\n✅ Success criteria met\n❌ Max iterations reached\n⚠️ Unrecoverable error (missing dependency, permission denied)\n6. On Failure\n\nIf max reached without success:\n\nSummarize all attempts\nIdentify common failure pattern\nRecommend manual intervention or different approach\n7. Safety\nHard limit: 10 iterations maximum\nNo destructive actions without explicit per-action approval\nLog everything to ~/loop/history/"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/loop",
    "publisherUrl": "https://clawhub.ai/ivangdavila/loop",
    "owner": "ivangdavila",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/loop",
    "downloadUrl": "https://openagent3.xyz/downloads/loop",
    "agentUrl": "https://openagent3.xyz/skills/loop/agent",
    "manifestUrl": "https://openagent3.xyz/skills/loop/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/loop/agent.md"
  }
}