{
  "schemaVersion": "1.0",
  "item": {
    "slug": "auto-clipper",
    "name": "Auto Clipper",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/RuneweaverStudios/auto-clipper",
    "canonicalUrl": "https://clawhub.ai/RuneweaverStudios/auto-clipper",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/auto-clipper",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=auto-clipper",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "_meta.json",
      "config.json",
      "scripts/auto_clipper.py",
      "scripts/run.sh"
    ],
    "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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/auto-clipper"
    },
    "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/auto-clipper",
    "agentPageUrl": "https://openagent3.xyz/skills/auto-clipper/agent",
    "manifestUrl": "https://openagent3.xyz/skills/auto-clipper/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/auto-clipper/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": "Description",
        "body": "Automatically create clips and videos from media files in a specified folder. Uses Agent Swarm for intelligent task delegation and supports cron-based scheduling."
      },
      {
        "title": "AutoClipper",
        "body": "Automatic Video Clip & Highlight Generator for OpenClaw.\n\nv1.0.0 — Design draft. Automatically scan a folder for media files, create clips/highlights using ffmpeg, and organize output. Cron-ready for scheduled automation."
      },
      {
        "title": "Installation",
        "body": "# Add to crontab (crontab -e)\n# Run every hour at minute 0\n0 * * * * /Users/ghost/.openclaw/workspace/skills/auto-clipper/scripts/run.sh\n\n# Or run daily at 9 AM\n0 9 * * * /Users/ghost/.openclaw/workspace/skills/auto-clipper/scripts/run.sh --output daily"
      },
      {
        "title": "Usage",
        "body": "Screen recording highlights: Auto-clip moments from Loom/obsidian recordings\nMeeting recaps: Extract key segments from meeting recordings\nContent creation: Batch-process raw footage into short clips\nSecurity camera clips: Pull motion-triggered segments from camera feeds\nGaming highlights: Auto-clip \"best of\" moments from recordings\n\n# Run once (scan and process)\npython3 scripts/auto_clipper.py run\n\n# Dry run (show what would be processed)\npython3 scripts/auto_clipper.py run --dry-run\n\n# Force reprocess all files\npython3 scripts/auto_clipper.py run --force\n\n# Start continuous watcher (not cron-based)\npython3 scripts/auto_clipper.py watch\n\n# Show status\npython3 scripts/auto_clipper.py status"
      },
      {
        "title": "Purpose",
        "body": "AutoClipper enables OpenClaw agents to automatically:\n\nMonitor a watch folder for new media files (videos, screen recordings, camera clips)\nAnalyze media to understand what's worth clipping (via Agent Swarm delegation)\nGenerate clips using ffmpeg (highlights, segments, trimmed videos)\nProduce compilations by stitching multiple clips together\nSchedule runs via cron for fully automated workflows"
      },
      {
        "title": "Architecture",
        "body": "┌─────────────────────────────────────────────────────────────┐\n│                      AutoClipper Skill                       │\n├─────────────────────────────────────────────────────────────┤\n│  1. Watch Folder (configurable input path)                  │\n│         ↓                                                   │\n│  2. Media Scanner (find new files, filter by extension)    │\n│         ↓                                                   │\n│  3. Agent Swarm delegation (analyze → clip strategy)             │\n│         ↓                                                   │\n│  4. Clip Engine (ffmpeg operations)                         │\n│         ↓                                                   │\n│  5. Output Organizer (save to output folder, optional SNS)  │\n└─────────────────────────────────────────────────────────────┘"
      },
      {
        "title": "1. Watch Folder Scanner",
        "body": "Monitors a configured input directory\nFilters by file extensions: .mp4, .mov, .mkv, .avi, .webm\nTracks processed files (to avoid re-processing)\nConfigurable: watchFolder, fileExtensions, processedLog"
      },
      {
        "title": "2. Media Analyzer (via Agent Swarm)",
        "body": "Delegates analysis to appropriate model (MiniMax for code/technical, Kimi for creative)\nDetermines:\n\nWhich segments to clip (timestamp ranges)\nClip duration targets\nOutput format preferences\n\n\nReturns structured clip plan: [{start, end, label, priority}]"
      },
      {
        "title": "3. Clip Engine (ffmpeg)",
        "body": "Trim: Extract segments without re-encoding (fast)\nTranscode: Convert to target format/codec\nHighlight: Auto-detect \"interesting\" segments (via scene detection)\nCompile: Stitch multiple clips into single video\nOverlay: Add watermarks, timestamps, captions"
      },
      {
        "title": "4. Output Manager",
        "body": "Organized output folder structure: output/YYYY-MM-DD/\nConfigurable naming: {original}-{timestamp}-{index}.mp4\nOptional: Notify via OpenClaw message (Discord, WhatsApp, etc.)"
      },
      {
        "title": "5. Cron Scheduler",
        "body": "Standalone script for cron integration\nConfigurable schedule: 0 * * * * (hourly), 0 9 * * * (daily at 9am)\nDry-run mode for testing\nLock file to prevent overlapping runs"
      },
      {
        "title": "Configuration (config.json)",
        "body": "{\n  \"watchFolder\": \"~/Downloads/Recordings\",\n  \"outputFolder\": \"~/Videos/Clips\",\n  \"fileExtensions\": [\".mp4\", \".mov\", \".mkv\"],\n  \"processedLog\": \"logs/processed.json\",\n  \"clipSettings\": {\n    \"defaultDuration\": 60,\n    \"minClipDuration\": 10,\n    \"maxClipDuration\": 300,\n    \"outputCodec\": \"h264\",\n    \"outputFormat\": \"mp4\"\n  },\n  \"intentRouter\": {\n    \"enabled\": true,\n    \"model\": \"openrouter/minimax/minimax-m2.5\"\n  },\n  \"cron\": {\n    \"schedule\": \"0 * * * *\",\n    \"enabled\": false\n  },\n  \"notifications\": {\n    \"enabled\": false,\n    \"channel\": \"discord\"\n  }\n}"
      },
      {
        "title": "Tools Needed",
        "body": "ToolPurposeRequiredffmpegVideo transcoding, trimming, clippingYesffprobeMedia metadata extraction (duration, codec)YesAgent SwarmAnalyze media and determine clip strategyYesOpenClaw messageSend notifications when clips are readyOptionalOpenClaw nodesScreen recording capture (live input)Optionalfile systemWatch folder, output managementYes"
      },
      {
        "title": "Agent Swarm integration",
        "body": "When AutoClipper finds new media, it delegates analysis:\n\nUser task: \"Analyze video and suggest clip timestamps for meeting highlights\"\n→ router.spawn() → sessions_spawn(task, model)\n← Returns: [{start: \"00:05:30\", end: \"00:07:45\", label: \"action item discussion\"}, ...]\n\nPrompt template for media analysis:\n\nAnalyze this video file: {filename}\nDuration: {duration_seconds} seconds\nExtract: Key moments worth clipping as short highlights (30-90 seconds each)\nOutput: JSON array of {start_timestamp, end_timestamp, description}"
      },
      {
        "title": "Directory Structure",
        "body": "auto-clipper/\n├── SKILL.md              # This file\n├── _meta.json            # Skill metadata\n├── config.json           # Configuration\n├── README.md             # Setup instructions\n├── scripts/\n│   ├── auto_clipper.py   # Main entry point\n│   ├── scanner.py        # Watch folder scanner\n│   ├── clipper.py        # ffmpeg wrapper\n│   ├── analyzer.py       # Agent Swarm integration\n│   └── run.sh            # Cron launcher\n└── logs/\n    └── processed.json    # Track processed files"
      },
      {
        "title": "Keywords",
        "body": "video, clip, clips, highlight, highlights\ntrim, cut, extract, segment\nffmpeg, transcode, encode, convert\nfolder, watch, monitor, automation\ncron, schedule, batch, process\nscreen recording, meeting, recording"
      },
      {
        "title": "Skill Name Ideas",
        "body": "AutoClipper ✓ (chosen)\nClipForge\nMediaMason\nVideoHarvest\nHighlightHub\nClipStream\nMediaSnip\nAutoTrim"
      },
      {
        "title": "Phase 1: Core (MVP)",
        "body": "Folder scanner with extension filtering\n Basic ffmpeg trim operation\n Simple processed file tracking\n CLI entry point"
      },
      {
        "title": "Phase 2: Intelligence",
        "body": "Agent Swarm integration for clip planning\n Scene detection for auto-highlighting\n Metadata extraction with ffprobe"
      },
      {
        "title": "Phase 3: Automation",
        "body": "Cron launcher script\n Continuous watcher mode\n Notification system\n Output organization"
      },
      {
        "title": "Phase 4: Advanced",
        "body": "Multi-clip compilation\n Overlay/watermark support\n Custom clip templates\n Node camera integration"
      },
      {
        "title": "Notes",
        "body": "Performance: Use -c copy for fast trimming (no re-encode)\nStorage: Auto-cleanup processed files or move to archive\nError handling: Skip corrupted files gracefully, log failures\nIdempotency: Same input file should not produce duplicate output"
      }
    ],
    "body": "AutoClipper\nDescription\n\nAutomatically create clips and videos from media files in a specified folder. Uses Agent Swarm for intelligent task delegation and supports cron-based scheduling.\n\nAutoClipper\n\nAutomatic Video Clip & Highlight Generator for OpenClaw.\n\nv1.0.0 — Design draft. Automatically scan a folder for media files, create clips/highlights using ffmpeg, and organize output. Cron-ready for scheduled automation.\n\nInstallation\n# Add to crontab (crontab -e)\n# Run every hour at minute 0\n0 * * * * /Users/ghost/.openclaw/workspace/skills/auto-clipper/scripts/run.sh\n\n# Or run daily at 9 AM\n0 9 * * * /Users/ghost/.openclaw/workspace/skills/auto-clipper/scripts/run.sh --output daily\n\nUsage\nScreen recording highlights: Auto-clip moments from Loom/obsidian recordings\nMeeting recaps: Extract key segments from meeting recordings\nContent creation: Batch-process raw footage into short clips\nSecurity camera clips: Pull motion-triggered segments from camera feeds\nGaming highlights: Auto-clip \"best of\" moments from recordings\n# Run once (scan and process)\npython3 scripts/auto_clipper.py run\n\n# Dry run (show what would be processed)\npython3 scripts/auto_clipper.py run --dry-run\n\n# Force reprocess all files\npython3 scripts/auto_clipper.py run --force\n\n# Start continuous watcher (not cron-based)\npython3 scripts/auto_clipper.py watch\n\n# Show status\npython3 scripts/auto_clipper.py status\n\nPurpose\n\nAutoClipper enables OpenClaw agents to automatically:\n\nMonitor a watch folder for new media files (videos, screen recordings, camera clips)\nAnalyze media to understand what's worth clipping (via Agent Swarm delegation)\nGenerate clips using ffmpeg (highlights, segments, trimmed videos)\nProduce compilations by stitching multiple clips together\nSchedule runs via cron for fully automated workflows\nArchitecture\n┌─────────────────────────────────────────────────────────────┐\n│                      AutoClipper Skill                       │\n├─────────────────────────────────────────────────────────────┤\n│  1. Watch Folder (configurable input path)                  │\n│         ↓                                                   │\n│  2. Media Scanner (find new files, filter by extension)    │\n│         ↓                                                   │\n│  3. Agent Swarm delegation (analyze → clip strategy)             │\n│         ↓                                                   │\n│  4. Clip Engine (ffmpeg operations)                         │\n│         ↓                                                   │\n│  5. Output Organizer (save to output folder, optional SNS)  │\n└─────────────────────────────────────────────────────────────┘\n\nComponents\n1. Watch Folder Scanner\nMonitors a configured input directory\nFilters by file extensions: .mp4, .mov, .mkv, .avi, .webm\nTracks processed files (to avoid re-processing)\nConfigurable: watchFolder, fileExtensions, processedLog\n2. Media Analyzer (via Agent Swarm)\nDelegates analysis to appropriate model (MiniMax for code/technical, Kimi for creative)\nDetermines:\nWhich segments to clip (timestamp ranges)\nClip duration targets\nOutput format preferences\nReturns structured clip plan: [{start, end, label, priority}]\n3. Clip Engine (ffmpeg)\nTrim: Extract segments without re-encoding (fast)\nTranscode: Convert to target format/codec\nHighlight: Auto-detect \"interesting\" segments (via scene detection)\nCompile: Stitch multiple clips into single video\nOverlay: Add watermarks, timestamps, captions\n4. Output Manager\nOrganized output folder structure: output/YYYY-MM-DD/\nConfigurable naming: {original}-{timestamp}-{index}.mp4\nOptional: Notify via OpenClaw message (Discord, WhatsApp, etc.)\n5. Cron Scheduler\nStandalone script for cron integration\nConfigurable schedule: 0 * * * * (hourly), 0 9 * * * (daily at 9am)\nDry-run mode for testing\nLock file to prevent overlapping runs\nConfiguration (config.json)\n{\n  \"watchFolder\": \"~/Downloads/Recordings\",\n  \"outputFolder\": \"~/Videos/Clips\",\n  \"fileExtensions\": [\".mp4\", \".mov\", \".mkv\"],\n  \"processedLog\": \"logs/processed.json\",\n  \"clipSettings\": {\n    \"defaultDuration\": 60,\n    \"minClipDuration\": 10,\n    \"maxClipDuration\": 300,\n    \"outputCodec\": \"h264\",\n    \"outputFormat\": \"mp4\"\n  },\n  \"intentRouter\": {\n    \"enabled\": true,\n    \"model\": \"openrouter/minimax/minimax-m2.5\"\n  },\n  \"cron\": {\n    \"schedule\": \"0 * * * *\",\n    \"enabled\": false\n  },\n  \"notifications\": {\n    \"enabled\": false,\n    \"channel\": \"discord\"\n  }\n}\n\nTools Needed\nTool\tPurpose\tRequired\nffmpeg\tVideo transcoding, trimming, clipping\tYes\nffprobe\tMedia metadata extraction (duration, codec)\tYes\nAgent Swarm\tAnalyze media and determine clip strategy\tYes\nOpenClaw message\tSend notifications when clips are ready\tOptional\nOpenClaw nodes\tScreen recording capture (live input)\tOptional\nfile system\tWatch folder, output management\tYes\nAgent Swarm integration\n\nWhen AutoClipper finds new media, it delegates analysis:\n\nUser task: \"Analyze video and suggest clip timestamps for meeting highlights\"\n→ router.spawn() → sessions_spawn(task, model)\n← Returns: [{start: \"00:05:30\", end: \"00:07:45\", label: \"action item discussion\"}, ...]\n\n\nPrompt template for media analysis:\n\nAnalyze this video file: {filename}\nDuration: {duration_seconds} seconds\nExtract: Key moments worth clipping as short highlights (30-90 seconds each)\nOutput: JSON array of {start_timestamp, end_timestamp, description}\n\nDirectory Structure\nauto-clipper/\n├── SKILL.md              # This file\n├── _meta.json            # Skill metadata\n├── config.json           # Configuration\n├── README.md             # Setup instructions\n├── scripts/\n│   ├── auto_clipper.py   # Main entry point\n│   ├── scanner.py        # Watch folder scanner\n│   ├── clipper.py        # ffmpeg wrapper\n│   ├── analyzer.py       # Agent Swarm integration\n│   └── run.sh            # Cron launcher\n└── logs/\n    └── processed.json    # Track processed files\n\nKeywords\nvideo, clip, clips, highlight, highlights\ntrim, cut, extract, segment\nffmpeg, transcode, encode, convert\nfolder, watch, monitor, automation\ncron, schedule, batch, process\nscreen recording, meeting, recording\nSkill Name Ideas\nAutoClipper ✓ (chosen)\nClipForge\nMediaMason\nVideoHarvest\nHighlightHub\nClipStream\nMediaSnip\nAutoTrim\nImplementation Phases\nPhase 1: Core (MVP)\n Folder scanner with extension filtering\n Basic ffmpeg trim operation\n Simple processed file tracking\n CLI entry point\nPhase 2: Intelligence\n Agent Swarm integration for clip planning\n Scene detection for auto-highlighting\n Metadata extraction with ffprobe\nPhase 3: Automation\n Cron launcher script\n Continuous watcher mode\n Notification system\n Output organization\nPhase 4: Advanced\n Multi-clip compilation\n Overlay/watermark support\n Custom clip templates\n Node camera integration\nNotes\nPerformance: Use -c copy for fast trimming (no re-encode)\nStorage: Auto-cleanup processed files or move to archive\nError handling: Skip corrupted files gracefully, log failures\nIdempotency: Same input file should not produce duplicate output"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/RuneweaverStudios/auto-clipper",
    "publisherUrl": "https://clawhub.ai/RuneweaverStudios/auto-clipper",
    "owner": "RuneweaverStudios",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/auto-clipper",
    "downloadUrl": "https://openagent3.xyz/downloads/auto-clipper",
    "agentUrl": "https://openagent3.xyz/skills/auto-clipper/agent",
    "manifestUrl": "https://openagent3.xyz/skills/auto-clipper/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/auto-clipper/agent.md"
  }
}