{
  "schemaVersion": "1.0",
  "item": {
    "slug": "instagram-reels",
    "name": "Instagram Reels",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/antoinedc/instagram-reels",
    "canonicalUrl": "https://clawhub.ai/antoinedc/instagram-reels",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/instagram-reels",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=instagram-reels",
    "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": "2026-04-23T16:43:11.935Z",
      "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/instagram-reels"
    },
    "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/instagram-reels",
    "agentPageUrl": "https://openagent3.xyz/skills/instagram-reels/agent",
    "manifestUrl": "https://openagent3.xyz/skills/instagram-reels/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/instagram-reels/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": "Instagram Reels Skill",
        "body": "Download Instagram Reels, transcribe the audio, and extract the caption/description."
      },
      {
        "title": "Setup",
        "body": "Install required tools:\n\npip install yt-dlp\napt install ffmpeg    # or: brew install ffmpeg\n\nGet a free Groq API key at https://console.groq.com\nSet your environment variable:\n\nexport GROQ_API_KEY=\"your-groq-api-key\""
      },
      {
        "title": "Usage",
        "body": "Process a reel in three steps: extract metadata, download audio, transcribe."
      },
      {
        "title": "Step 1: Extract metadata and audio URL",
        "body": "yt-dlp --write-info-json --skip-download -o \"/tmp/reel\" \"REEL_URL\"\n\nThis writes /tmp/reel.info.json with the caption, uploader, CDN URLs, and other metadata. No login required for public reels."
      },
      {
        "title": "Step 2: Download audio and convert to mp3",
        "body": "Extract the audio CDN URL from metadata and download it directly:\n\nAUDIO_URL=$(python3 -c \"\nimport json\nd = json.load(open('/tmp/reel.info.json'))\nfor f in d.get('formats', []):\n    if f.get('ext') == 'm4a':\n        print(f['url'])\n        break\n\")\ncurl -sL \"$AUDIO_URL\" -o /tmp/reel-audio.m4a\nffmpeg -y -i /tmp/reel-audio.m4a -acodec libmp3lame -q:a 4 /tmp/reel-audio.mp3"
      },
      {
        "title": "Step 3: Transcribe with Groq Whisper",
        "body": "curl -s https://api.groq.com/openai/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $GROQ_API_KEY\" \\\n  -F \"file=@/tmp/reel-audio.mp3\" \\\n  -F \"model=whisper-large-v3-turbo\" \\\n  -F \"response_format=verbose_json\"\n\nReturns JSON with text (full transcript) and segments (with timestamps). Language is auto-detected."
      },
      {
        "title": "Extract caption from metadata",
        "body": "python3 -c \"\nimport json\nd = json.load(open('/tmp/reel.info.json'))\nprint('Caption:', d.get('description', 'No caption'))\nprint('Author:', d.get('uploader', 'Unknown'))\nprint('Duration:', round(d.get('duration', 0)), 'seconds')\n\""
      },
      {
        "title": "Notes",
        "body": "Metadata extraction works on public reels without authentication\nFor private reels, pass cookies: yt-dlp --cookies /path/to/cookies.txt --write-info-json --skip-download -o \"/tmp/reel\" \"REEL_URL\"\nExport cookies with a browser extension like \"Get cookies.txt LOCALLY\"\nGroq Whisper is free (rate-limited) and returns results in ~1-2 seconds\nMax audio length: 25 minutes per request\nClean up temp files after: rm -f /tmp/reel.info.json /tmp/reel-audio.*\nAlso works with TikTok, YouTube Shorts, and other platforms supported by yt-dlp"
      },
      {
        "title": "Examples",
        "body": "# Full transcription pipeline\nyt-dlp --write-info-json --skip-download -o \"/tmp/reel\" \"https://www.instagram.com/reel/ABC123/\" && \\\nAUDIO_URL=$(python3 -c \"import json; [print(f['url']) for f in json.load(open('/tmp/reel.info.json')).get('formats',[]) if f.get('ext')=='m4a'][:1]\") && \\\ncurl -sL \"$AUDIO_URL\" -o /tmp/reel-audio.m4a && \\\nffmpeg -y -i /tmp/reel-audio.m4a -acodec libmp3lame -q:a 4 /tmp/reel-audio.mp3 2>/dev/null && \\\ncurl -s https://api.groq.com/openai/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $GROQ_API_KEY\" \\\n  -F \"file=@/tmp/reel-audio.mp3\" \\\n  -F \"model=whisper-large-v3-turbo\" \\\n  -F \"response_format=verbose_json\"\n\n# Just get the caption (no transcription)\nyt-dlp --write-info-json --skip-download -o \"/tmp/reel\" \"https://www.instagram.com/reel/ABC123/\" && \\\npython3 -c \"import json; d=json.load(open('/tmp/reel.info.json')); print(d.get('description',''))\"\n\n# Transcribe a TikTok video (same pipeline)\nyt-dlp --write-info-json --skip-download -o \"/tmp/reel\" \"https://www.tiktok.com/@user/video/123\" && \\\nAUDIO_URL=$(python3 -c \"import json; [print(f['url']) for f in json.load(open('/tmp/reel.info.json')).get('formats',[]) if f.get('ext')=='m4a'][:1]\") && \\\ncurl -sL \"$AUDIO_URL\" -o /tmp/reel-audio.m4a && \\\nffmpeg -y -i /tmp/reel-audio.m4a -acodec libmp3lame -q:a 4 /tmp/reel-audio.mp3 2>/dev/null && \\\ncurl -s https://api.groq.com/openai/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $GROQ_API_KEY\" \\\n  -F \"file=@/tmp/reel-audio.mp3\" \\\n  -F \"model=whisper-large-v3-turbo\" \\\n  -F \"response_format=verbose_json\""
      }
    ],
    "body": "Instagram Reels Skill\n\nDownload Instagram Reels, transcribe the audio, and extract the caption/description.\n\nSetup\nInstall required tools:\npip install yt-dlp\napt install ffmpeg    # or: brew install ffmpeg\n\nGet a free Groq API key at https://console.groq.com\nSet your environment variable:\nexport GROQ_API_KEY=\"your-groq-api-key\"\n\nUsage\n\nProcess a reel in three steps: extract metadata, download audio, transcribe.\n\nStep 1: Extract metadata and audio URL\nyt-dlp --write-info-json --skip-download -o \"/tmp/reel\" \"REEL_URL\"\n\n\nThis writes /tmp/reel.info.json with the caption, uploader, CDN URLs, and other metadata. No login required for public reels.\n\nStep 2: Download audio and convert to mp3\n\nExtract the audio CDN URL from metadata and download it directly:\n\nAUDIO_URL=$(python3 -c \"\nimport json\nd = json.load(open('/tmp/reel.info.json'))\nfor f in d.get('formats', []):\n    if f.get('ext') == 'm4a':\n        print(f['url'])\n        break\n\")\ncurl -sL \"$AUDIO_URL\" -o /tmp/reel-audio.m4a\nffmpeg -y -i /tmp/reel-audio.m4a -acodec libmp3lame -q:a 4 /tmp/reel-audio.mp3\n\nStep 3: Transcribe with Groq Whisper\ncurl -s https://api.groq.com/openai/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $GROQ_API_KEY\" \\\n  -F \"file=@/tmp/reel-audio.mp3\" \\\n  -F \"model=whisper-large-v3-turbo\" \\\n  -F \"response_format=verbose_json\"\n\n\nReturns JSON with text (full transcript) and segments (with timestamps). Language is auto-detected.\n\nExtract caption from metadata\npython3 -c \"\nimport json\nd = json.load(open('/tmp/reel.info.json'))\nprint('Caption:', d.get('description', 'No caption'))\nprint('Author:', d.get('uploader', 'Unknown'))\nprint('Duration:', round(d.get('duration', 0)), 'seconds')\n\"\n\nNotes\nMetadata extraction works on public reels without authentication\nFor private reels, pass cookies: yt-dlp --cookies /path/to/cookies.txt --write-info-json --skip-download -o \"/tmp/reel\" \"REEL_URL\"\nExport cookies with a browser extension like \"Get cookies.txt LOCALLY\"\nGroq Whisper is free (rate-limited) and returns results in ~1-2 seconds\nMax audio length: 25 minutes per request\nClean up temp files after: rm -f /tmp/reel.info.json /tmp/reel-audio.*\nAlso works with TikTok, YouTube Shorts, and other platforms supported by yt-dlp\nExamples\n# Full transcription pipeline\nyt-dlp --write-info-json --skip-download -o \"/tmp/reel\" \"https://www.instagram.com/reel/ABC123/\" && \\\nAUDIO_URL=$(python3 -c \"import json; [print(f['url']) for f in json.load(open('/tmp/reel.info.json')).get('formats',[]) if f.get('ext')=='m4a'][:1]\") && \\\ncurl -sL \"$AUDIO_URL\" -o /tmp/reel-audio.m4a && \\\nffmpeg -y -i /tmp/reel-audio.m4a -acodec libmp3lame -q:a 4 /tmp/reel-audio.mp3 2>/dev/null && \\\ncurl -s https://api.groq.com/openai/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $GROQ_API_KEY\" \\\n  -F \"file=@/tmp/reel-audio.mp3\" \\\n  -F \"model=whisper-large-v3-turbo\" \\\n  -F \"response_format=verbose_json\"\n\n# Just get the caption (no transcription)\nyt-dlp --write-info-json --skip-download -o \"/tmp/reel\" \"https://www.instagram.com/reel/ABC123/\" && \\\npython3 -c \"import json; d=json.load(open('/tmp/reel.info.json')); print(d.get('description',''))\"\n\n# Transcribe a TikTok video (same pipeline)\nyt-dlp --write-info-json --skip-download -o \"/tmp/reel\" \"https://www.tiktok.com/@user/video/123\" && \\\nAUDIO_URL=$(python3 -c \"import json; [print(f['url']) for f in json.load(open('/tmp/reel.info.json')).get('formats',[]) if f.get('ext')=='m4a'][:1]\") && \\\ncurl -sL \"$AUDIO_URL\" -o /tmp/reel-audio.m4a && \\\nffmpeg -y -i /tmp/reel-audio.m4a -acodec libmp3lame -q:a 4 /tmp/reel-audio.mp3 2>/dev/null && \\\ncurl -s https://api.groq.com/openai/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $GROQ_API_KEY\" \\\n  -F \"file=@/tmp/reel-audio.mp3\" \\\n  -F \"model=whisper-large-v3-turbo\" \\\n  -F \"response_format=verbose_json\""
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/antoinedc/instagram-reels",
    "publisherUrl": "https://clawhub.ai/antoinedc/instagram-reels",
    "owner": "antoinedc",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/instagram-reels",
    "downloadUrl": "https://openagent3.xyz/downloads/instagram-reels",
    "agentUrl": "https://openagent3.xyz/skills/instagram-reels/agent",
    "manifestUrl": "https://openagent3.xyz/skills/instagram-reels/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/instagram-reels/agent.md"
  }
}