{
  "schemaVersion": "1.0",
  "item": {
    "slug": "loom-workflow",
    "name": "Loom Workflow",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/G9Pedro/loom-workflow",
    "canonicalUrl": "https://clawhub.ai/G9Pedro/loom-workflow",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/loom-workflow",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=loom-workflow",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "DESIGN.md",
      "SKILL.md",
      "scripts/analyze-workflow.py",
      "scripts/generate-lobster.py",
      "scripts/smart-extract.py",
      "test-output/video.info.json"
    ],
    "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/loom-workflow"
    },
    "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/loom-workflow",
    "agentPageUrl": "https://openagent3.xyz/skills/loom-workflow/agent",
    "manifestUrl": "https://openagent3.xyz/skills/loom-workflow/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/loom-workflow/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": "Loom Workflow Analyzer",
        "body": "Transforms Loom recordings into structured, automatable workflows."
      },
      {
        "title": "Quick Start",
        "body": "# Full pipeline - download, extract, transcribe, analyze\n{baseDir}/scripts/loom-workflow analyze https://loom.com/share/abc123\n\n# Individual steps\n{baseDir}/scripts/loom-workflow download https://loom.com/share/abc123\n{baseDir}/scripts/loom-workflow extract ./video.mp4\n{baseDir}/scripts/loom-workflow generate ./analysis.json"
      },
      {
        "title": "Pipeline",
        "body": "Download - Fetches Loom video via yt-dlp\nSmart Extract - Captures frames at scene changes + transcript timing\nTranscribe - Whisper transcription with word-level timestamps\nAnalyze - Multimodal AI analysis (requires vision model)\nGenerate - Creates Lobster workflow with approval gates"
      },
      {
        "title": "Smart Frame Extraction",
        "body": "Frames are captured when:\n\nScene changes - Significant visual change (ffmpeg scene detection)\nSpeech starts - New narration segment begins\nCombined - Speech + visual change = high-value moment\nGap fill - Max 10s without a frame"
      },
      {
        "title": "Analysis Output",
        "body": "The analyzer produces:\n\nworkflow-analysis.json - Structured workflow definition\nworkflow-summary.md - Human-readable summary\n*.lobster - Executable Lobster workflow file"
      },
      {
        "title": "Ambiguity Detection",
        "body": "The analyzer flags:\n\nUnclear mouse movements\nImplicit knowledge (\"the usual process\")\nDecision points (\"depending on...\")\nMissing credentials/context\nTool dependencies"
      },
      {
        "title": "Vision Analysis Step",
        "body": "After extraction, use the generated prompt with a vision model:\n\n# The prompt is at: output/workflow-analysis-prompt.md\n# Attach frames from: output/frames/\n\n# Example with Claude:\ncat output/workflow-analysis-prompt.md | claude --images output/frames/*.jpg\n\nSave the JSON response to workflow-analysis.json, then:\n\n{baseDir}/scripts/loom-workflow generate ./output/workflow-analysis.json"
      },
      {
        "title": "Lobster Integration",
        "body": "Generated workflows use:\n\napprove gates for destructive/external actions\nllm-task for classification/decision steps\nResume tokens for interrupted workflows\nJSON piping between steps"
      },
      {
        "title": "Requirements",
        "body": "yt-dlp - Video download\nffmpeg - Frame extraction + scene detection\nwhisper - Audio transcription\nVision-capable LLM for analysis step"
      },
      {
        "title": "Multilingual Support",
        "body": "Works with any language - Whisper auto-detects and transcribes.\nAnalysis should be prompted in the video's language for best results."
      }
    ],
    "body": "Loom Workflow Analyzer\n\nTransforms Loom recordings into structured, automatable workflows.\n\nQuick Start\n# Full pipeline - download, extract, transcribe, analyze\n{baseDir}/scripts/loom-workflow analyze https://loom.com/share/abc123\n\n# Individual steps\n{baseDir}/scripts/loom-workflow download https://loom.com/share/abc123\n{baseDir}/scripts/loom-workflow extract ./video.mp4\n{baseDir}/scripts/loom-workflow generate ./analysis.json\n\nPipeline\nDownload - Fetches Loom video via yt-dlp\nSmart Extract - Captures frames at scene changes + transcript timing\nTranscribe - Whisper transcription with word-level timestamps\nAnalyze - Multimodal AI analysis (requires vision model)\nGenerate - Creates Lobster workflow with approval gates\nSmart Frame Extraction\n\nFrames are captured when:\n\nScene changes - Significant visual change (ffmpeg scene detection)\nSpeech starts - New narration segment begins\nCombined - Speech + visual change = high-value moment\nGap fill - Max 10s without a frame\nAnalysis Output\n\nThe analyzer produces:\n\nworkflow-analysis.json - Structured workflow definition\nworkflow-summary.md - Human-readable summary\n*.lobster - Executable Lobster workflow file\nAmbiguity Detection\n\nThe analyzer flags:\n\nUnclear mouse movements\nImplicit knowledge (\"the usual process\")\nDecision points (\"depending on...\")\nMissing credentials/context\nTool dependencies\nVision Analysis Step\n\nAfter extraction, use the generated prompt with a vision model:\n\n# The prompt is at: output/workflow-analysis-prompt.md\n# Attach frames from: output/frames/\n\n# Example with Claude:\ncat output/workflow-analysis-prompt.md | claude --images output/frames/*.jpg\n\n\nSave the JSON response to workflow-analysis.json, then:\n\n{baseDir}/scripts/loom-workflow generate ./output/workflow-analysis.json\n\nLobster Integration\n\nGenerated workflows use:\n\napprove gates for destructive/external actions\nllm-task for classification/decision steps\nResume tokens for interrupted workflows\nJSON piping between steps\nRequirements\nyt-dlp - Video download\nffmpeg - Frame extraction + scene detection\nwhisper - Audio transcription\nVision-capable LLM for analysis step\nMultilingual Support\n\nWorks with any language - Whisper auto-detects and transcribes. Analysis should be prompted in the video's language for best results."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/G9Pedro/loom-workflow",
    "publisherUrl": "https://clawhub.ai/G9Pedro/loom-workflow",
    "owner": "G9Pedro",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/loom-workflow",
    "downloadUrl": "https://openagent3.xyz/downloads/loom-workflow",
    "agentUrl": "https://openagent3.xyz/skills/loom-workflow/agent",
    "manifestUrl": "https://openagent3.xyz/skills/loom-workflow/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/loom-workflow/agent.md"
  }
}