{
  "schemaVersion": "1.0",
  "item": {
    "slug": "roughcut-openclaw",
    "name": "RoughCut",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/samerGMTM22/roughcut-openclaw",
    "canonicalUrl": "https://clawhub.ai/samerGMTM22/roughcut-openclaw",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/roughcut-openclaw",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=roughcut-openclaw",
    "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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/roughcut-openclaw"
    },
    "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/roughcut-openclaw",
    "agentPageUrl": "https://openagent3.xyz/skills/roughcut-openclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/roughcut-openclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/roughcut-openclaw/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": "RoughCut (macOS)",
        "body": "This skill lets an OpenClaw agent run RoughCut locally on a user's Mac to produce RoughCut.xml_variants.zip from a raw video file, without uploading media."
      },
      {
        "title": "Preconditions",
        "body": "Confirm the video is present on local disk and get an absolute file path (example: /Users/alice/Movies/raw.mp4).\nIf the file is on Google Drive/iCloud/Dropbox, ensure it is fully downloaded and accessible as a local file path.\nTip: on macOS, you can drag the video file into Terminal to paste its absolute path.\nIf the user is on a different machine than the OpenClaw Mac, agree on a delivery method:\n\nSynced folder: a folder that syncs onto the OpenClaw Mac (iCloud Drive, Dropbox, Google Drive Desktop, etc.).\nDirect download URL: ask the user for a direct HTTPS download link (for example an S3/R2/GCS pre-signed URL), then run RoughCut with --video-url (it downloads into output_root/RoughCut.inputs/ automatically).\n\n\n\nConfirm RoughCut repo is present on the same Mac.\n\nRepo: https://github.com/samerGMTM22/OpenClaw-RoughCut\n\n\n\nIf the user enables fluff removal, ensure GEMINI_API_KEY is set in the environment that will run RoughCut.\nIf it is not set, ask the user to provide it and explain it is used only for fluff removal."
      },
      {
        "title": "Questions To Ask The User",
        "body": "Do you want to remove bad takes? (default: yes)\nDo you want to remove fluff/off-topic content? (default: no)\nIf fluff removal is enabled: what is the video topic/goal? (required)"
      },
      {
        "title": "How To Run",
        "body": "Use repo_root and output_root from OpenClaw config:\n\nbash \"$REPO_ROOT/scripts/openclaw/roughcut.sh\" \\\n  --video \"$VIDEO_ABS_PATH\" \\\n  --out \"$OUTPUT_ROOT\" \\\n  --remove-bad-takes true \\\n  --remove-fluff false\n\nIf the user provides a direct download URL, you can pass it directly (the runner downloads to $OUTPUT_ROOT/RoughCut.inputs/ first):\n\nbash \"$REPO_ROOT/scripts/openclaw/roughcut.sh\" \\\n  --video-url \"$VIDEO_URL\" \\\n  --out \"$OUTPUT_ROOT\" \\\n  --remove-bad-takes true \\\n  --remove-fluff false\n\nIf the URL has no filename (common for pre-signed URLs), include --video-name, and optionally --video-sha256:\n\nbash \"$REPO_ROOT/scripts/openclaw/roughcut.sh\" \\\n  --video-url \"$VIDEO_URL\" \\\n  --video-name \"my_video.mov\" \\\n  --video-sha256 \"0123456789abcdef...\" \\\n  --out \"$OUTPUT_ROOT\" \\\n  --remove-bad-takes true \\\n  --remove-fluff false\n\nIf fluff removal is enabled:\n\nbash \"$REPO_ROOT/scripts/openclaw/roughcut.sh\" \\\n  --video \"$VIDEO_ABS_PATH\" \\\n  --out \"$OUTPUT_ROOT\" \\\n  --remove-bad-takes true \\\n  --remove-fluff true \\\n  --topic \"$TOPIC\"\n\nThe runner prints a single-line JSON result to stdout. On success it includes:\n\nxml_variants_zip: absolute path to RoughCut.xml_variants.zip\nvideo_path: absolute path to the input video used for processing\ndownloaded_video_path: present only when --video-url was used (where the video was saved)\n\nOn failure it will include:\n\nerror\noptionally debug_zip (a bundle of intermediate outputs)"
      },
      {
        "title": "What To Return To The User",
        "body": "The output zip path(s) from the JSON.\nHow to import into Final Cut Pro:\n\nUnzip RoughCut.xml_variants.zip.\nIn Final Cut Pro: File -> Import -> XML...\nChoose the desired .fcpxml variant."
      }
    ],
    "body": "RoughCut (macOS)\n\nThis skill lets an OpenClaw agent run RoughCut locally on a user's Mac to produce RoughCut.xml_variants.zip from a raw video file, without uploading media.\n\nPreconditions\n\nConfirm the video is present on local disk and get an absolute file path (example: /Users/alice/Movies/raw.mp4). If the file is on Google Drive/iCloud/Dropbox, ensure it is fully downloaded and accessible as a local file path. Tip: on macOS, you can drag the video file into Terminal to paste its absolute path. If the user is on a different machine than the OpenClaw Mac, agree on a delivery method:\n\nSynced folder: a folder that syncs onto the OpenClaw Mac (iCloud Drive, Dropbox, Google Drive Desktop, etc.).\nDirect download URL: ask the user for a direct HTTPS download link (for example an S3/R2/GCS pre-signed URL), then run RoughCut with --video-url (it downloads into output_root/RoughCut.inputs/ automatically).\n\nConfirm RoughCut repo is present on the same Mac.\n\nRepo: https://github.com/samerGMTM22/OpenClaw-RoughCut\n\nIf the user enables fluff removal, ensure GEMINI_API_KEY is set in the environment that will run RoughCut. If it is not set, ask the user to provide it and explain it is used only for fluff removal.\n\nQuestions To Ask The User\nDo you want to remove bad takes? (default: yes)\nDo you want to remove fluff/off-topic content? (default: no)\nIf fluff removal is enabled: what is the video topic/goal? (required)\nHow To Run\n\nUse repo_root and output_root from OpenClaw config:\n\nbash \"$REPO_ROOT/scripts/openclaw/roughcut.sh\" \\\n  --video \"$VIDEO_ABS_PATH\" \\\n  --out \"$OUTPUT_ROOT\" \\\n  --remove-bad-takes true \\\n  --remove-fluff false\n\n\nIf the user provides a direct download URL, you can pass it directly (the runner downloads to $OUTPUT_ROOT/RoughCut.inputs/ first):\n\nbash \"$REPO_ROOT/scripts/openclaw/roughcut.sh\" \\\n  --video-url \"$VIDEO_URL\" \\\n  --out \"$OUTPUT_ROOT\" \\\n  --remove-bad-takes true \\\n  --remove-fluff false\n\n\nIf the URL has no filename (common for pre-signed URLs), include --video-name, and optionally --video-sha256:\n\nbash \"$REPO_ROOT/scripts/openclaw/roughcut.sh\" \\\n  --video-url \"$VIDEO_URL\" \\\n  --video-name \"my_video.mov\" \\\n  --video-sha256 \"0123456789abcdef...\" \\\n  --out \"$OUTPUT_ROOT\" \\\n  --remove-bad-takes true \\\n  --remove-fluff false\n\n\nIf fluff removal is enabled:\n\nbash \"$REPO_ROOT/scripts/openclaw/roughcut.sh\" \\\n  --video \"$VIDEO_ABS_PATH\" \\\n  --out \"$OUTPUT_ROOT\" \\\n  --remove-bad-takes true \\\n  --remove-fluff true \\\n  --topic \"$TOPIC\"\n\n\nThe runner prints a single-line JSON result to stdout. On success it includes:\n\nxml_variants_zip: absolute path to RoughCut.xml_variants.zip\nvideo_path: absolute path to the input video used for processing\ndownloaded_video_path: present only when --video-url was used (where the video was saved)\n\nOn failure it will include:\n\nerror\noptionally debug_zip (a bundle of intermediate outputs)\nWhat To Return To The User\nThe output zip path(s) from the JSON.\nHow to import into Final Cut Pro:\nUnzip RoughCut.xml_variants.zip.\nIn Final Cut Pro: File -> Import -> XML...\nChoose the desired .fcpxml variant."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/samerGMTM22/roughcut-openclaw",
    "publisherUrl": "https://clawhub.ai/samerGMTM22/roughcut-openclaw",
    "owner": "samerGMTM22",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/roughcut-openclaw",
    "downloadUrl": "https://openagent3.xyz/downloads/roughcut-openclaw",
    "agentUrl": "https://openagent3.xyz/skills/roughcut-openclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/roughcut-openclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/roughcut-openclaw/agent.md"
  }
}