{
  "schemaVersion": "1.0",
  "item": {
    "slug": "imsg-media",
    "name": "Imsg Media",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/tankyhsu/imsg-media",
    "canonicalUrl": "https://clawhub.ai/tankyhsu/imsg-media",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/imsg-media",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=imsg-media",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/imsg_voice_transcribe.py"
    ],
    "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/imsg-media"
    },
    "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/imsg-media",
    "agentPageUrl": "https://openagent3.xyz/skills/imsg-media/agent",
    "manifestUrl": "https://openagent3.xyz/skills/imsg-media/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/imsg-media/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": "imsg-media",
        "body": "Full iMessage multimedia pipeline:\n\n🎙️ Voice memo → text via Silicon Flow ASR (SenseVoiceSmall, cloud, no local model)\n🖼️ Image → description/OCR via agent's built-in vision model"
      },
      {
        "title": "macOS permissions",
        "body": "Full Disk Access must be granted to the process running OpenClaw\nSettings → Privacy & Security → Full Disk Access → add your terminal/app\nWithout this, imsg cannot read ~/Library/Messages/chat.db and will return permissionDenied"
      },
      {
        "title": "API key (audio only)",
        "body": "Silicon Flow API key — sign up free at https://siliconflow.cn\nLong-term use: add to ~/.openclaw/.env: SILICON_FLOW_KEY=sk-...\nQuick test / override: pass --api-key sk-... directly to the script\nImage analysis does not require this key"
      },
      {
        "title": "CLI dependency",
        "body": "imsg CLI: npm install -g imsg"
      },
      {
        "title": "Trigger conditions",
        "body": "Activate this skill when:\n\nIncoming message text contains the attachment placeholder \nUser says \"语音转文字\", \"转写\", \"识别语音\", \"transcribe\"\nUser says \"看图\", \"识别图片\", \"读图\", \"OCR\", \"截图里写的什么\"\nUser references a photo/audio/file they just sent via iMessage"
      },
      {
        "title": "Decision flow",
        "body": "Attachment detected?\n├── Audio (.m4a / .caf / .wav / .mp3)  → transcribe via Silicon Flow ASR\n├── Image (.jpg / .png / .heic / .gif) → read with vision model\n└── Unknown / not downloaded            → increase --limit or ask user to resend"
      },
      {
        "title": "Step 1 — Get the sender identifier",
        "body": "Always read from the message envelope:\n\n[iMessage sender@example.com ...] → use sender@example.com\n[SMS +1234567890 ...] → use +1234567890\nNever hardcode an address"
      },
      {
        "title": "Step 2 — Fetch the attachment",
        "body": "# Run from the skill directory\ncd ~/.openclaw/skills/imsg-voice-transcribe\n\npython3 scripts/imsg_voice_transcribe.py fetch \\\n  --identifier \"sender@example.com\" \\\n  --limit 50\n\nReturns JSON with file, type (audio or image), and metadata.\n\nIf nothing found, try --limit 100."
      },
      {
        "title": "Step 3a — Audio: transcribe",
        "body": "# One-liner (fetch + transcribe)\npython3 scripts/imsg_voice_transcribe.py auto \\\n  --identifier \"sender@example.com\" \\\n  --limit 50 --raw\n\n# Or transcribe a specific file\npython3 scripts/imsg_voice_transcribe.py transcribe \\\n  --file /path/to/audio.m4a --raw\n\n# Quick test with explicit API key (no env setup needed)\npython3 scripts/imsg_voice_transcribe.py transcribe \\\n  --file /path/to/audio.m4a --api-key sk-... --raw"
      },
      {
        "title": "Step 3b — Image: analyze",
        "body": "After fetch returns an image path (e.g. {\"file\": \"/path/to/photo.jpg\", \"type\": \"image\"}):\n\n# Example: fetch image from a sender\npython3 scripts/imsg_voice_transcribe.py fetch \\\n  --identifier \"sender@example.com\" --type image --limit 50\n# → {\"file\": \"/Users/.../Messages/Attachments/photo.jpg\", \"type\": \"image\", ...}\n\nThen in the agent:\n\nIf HEIC/HEIF: convert first → sips -s format png \"input.heic\" --out \"output.png\"\nOpen with the read tool → agent vision model processes it\nRespond with: what it is, main subject, any text/OCR, notable details\n\nDefault image response format:\n\nWhat it is: photo / screenshot / document\nMain subject: 1–2 sentences\nText (OCR): quote key text, or \"无明显文字\"\nDetails: 3–5 bullets\nFollow-up: ask if they want OCR / table extraction / comparison / etc."
      },
      {
        "title": "Supported formats",
        "body": "FormatTypeNotes.m4aAudioStandard iMessage voice memo.cafAudioOlder iOS voice memo (AAC in CAF).wav .mp3AudioOther sources.jpg .jpeg .pngImageStandard photos.heic .heifImageiPhone default — convert to PNG first.gifImageAnimated or static"
      },
      {
        "title": "Troubleshooting",
        "body": "ErrorCauseFixpermissionDeniedNo Full Disk AccessGrant FDA in System SettingsSILICON_FLOW_KEY not setMissing API keyAdd to ~/.openclaw/.envNo attachments foundLow limit or iCloud not syncedIncrease --limit; ask user to resendRequest timed outNetwork or large fileRetry; check file < 25MBHEIC not displayingFormat not supported by readConvert with sips first"
      }
    ],
    "body": "imsg-media\n\nFull iMessage multimedia pipeline:\n\n🎙️ Voice memo → text via Silicon Flow ASR (SenseVoiceSmall, cloud, no local model)\n🖼️ Image → description/OCR via agent's built-in vision model\nRequirements\nmacOS permissions\nFull Disk Access must be granted to the process running OpenClaw\nSettings → Privacy & Security → Full Disk Access → add your terminal/app\nWithout this, imsg cannot read ~/Library/Messages/chat.db and will return permissionDenied\nAPI key (audio only)\nSilicon Flow API key — sign up free at https://siliconflow.cn\nLong-term use: add to ~/.openclaw/.env: SILICON_FLOW_KEY=sk-...\nQuick test / override: pass --api-key sk-... directly to the script\nImage analysis does not require this key\nCLI dependency\nimsg CLI: npm install -g imsg\nTrigger conditions\n\nActivate this skill when:\n\nIncoming message text contains the attachment placeholder \nUser says \"语音转文字\", \"转写\", \"识别语音\", \"transcribe\"\nUser says \"看图\", \"识别图片\", \"读图\", \"OCR\", \"截图里写的什么\"\nUser references a photo/audio/file they just sent via iMessage\nDecision flow\nAttachment detected?\n├── Audio (.m4a / .caf / .wav / .mp3)  → transcribe via Silicon Flow ASR\n├── Image (.jpg / .png / .heic / .gif) → read with vision model\n└── Unknown / not downloaded            → increase --limit or ask user to resend\n\nWorkflow\nStep 1 — Get the sender identifier\n\nAlways read from the message envelope:\n\n[iMessage sender@example.com ...] → use sender@example.com\n[SMS +1234567890 ...] → use +1234567890\nNever hardcode an address\nStep 2 — Fetch the attachment\n# Run from the skill directory\ncd ~/.openclaw/skills/imsg-voice-transcribe\n\npython3 scripts/imsg_voice_transcribe.py fetch \\\n  --identifier \"sender@example.com\" \\\n  --limit 50\n\n\nReturns JSON with file, type (audio or image), and metadata.\n\nIf nothing found, try --limit 100.\n\nStep 3a — Audio: transcribe\n# One-liner (fetch + transcribe)\npython3 scripts/imsg_voice_transcribe.py auto \\\n  --identifier \"sender@example.com\" \\\n  --limit 50 --raw\n\n# Or transcribe a specific file\npython3 scripts/imsg_voice_transcribe.py transcribe \\\n  --file /path/to/audio.m4a --raw\n\n# Quick test with explicit API key (no env setup needed)\npython3 scripts/imsg_voice_transcribe.py transcribe \\\n  --file /path/to/audio.m4a --api-key sk-... --raw\n\nStep 3b — Image: analyze\n\nAfter fetch returns an image path (e.g. {\"file\": \"/path/to/photo.jpg\", \"type\": \"image\"}):\n\n# Example: fetch image from a sender\npython3 scripts/imsg_voice_transcribe.py fetch \\\n  --identifier \"sender@example.com\" --type image --limit 50\n# → {\"file\": \"/Users/.../Messages/Attachments/photo.jpg\", \"type\": \"image\", ...}\n\n\nThen in the agent:\n\nIf HEIC/HEIF: convert first → sips -s format png \"input.heic\" --out \"output.png\"\nOpen with the read tool → agent vision model processes it\nRespond with: what it is, main subject, any text/OCR, notable details\n\nDefault image response format:\n\nWhat it is: photo / screenshot / document\nMain subject: 1–2 sentences\nText (OCR): quote key text, or \"无明显文字\"\nDetails: 3–5 bullets\nFollow-up: ask if they want OCR / table extraction / comparison / etc.\nSupported formats\nFormat\tType\tNotes\n.m4a\tAudio\tStandard iMessage voice memo\n.caf\tAudio\tOlder iOS voice memo (AAC in CAF)\n.wav .mp3\tAudio\tOther sources\n.jpg .jpeg .png\tImage\tStandard photos\n.heic .heif\tImage\tiPhone default — convert to PNG first\n.gif\tImage\tAnimated or static\nTroubleshooting\nError\tCause\tFix\npermissionDenied\tNo Full Disk Access\tGrant FDA in System Settings\nSILICON_FLOW_KEY not set\tMissing API key\tAdd to ~/.openclaw/.env\nNo attachments found\tLow limit or iCloud not synced\tIncrease --limit; ask user to resend\nRequest timed out\tNetwork or large file\tRetry; check file < 25MB\nHEIC not displaying\tFormat not supported by read\tConvert with sips first"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/tankyhsu/imsg-media",
    "publisherUrl": "https://clawhub.ai/tankyhsu/imsg-media",
    "owner": "tankyhsu",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/imsg-media",
    "downloadUrl": "https://openagent3.xyz/downloads/imsg-media",
    "agentUrl": "https://openagent3.xyz/skills/imsg-media/agent",
    "manifestUrl": "https://openagent3.xyz/skills/imsg-media/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/imsg-media/agent.md"
  }
}