# Send Whisnap to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- 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.
## Suggested prompts
### New install

```text
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.
```
### Upgrade existing

```text
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.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "whisnap",
    "name": "Whisnap",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Neolio42/whisnap",
    "canonicalUrl": "https://clawhub.ai/Neolio42/whisnap",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/whisnap",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=whisnap",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "whisnap",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-11T01:24:09.481Z",
      "expiresAt": "2026-05-18T01:24:09.481Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=whisnap",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=whisnap",
        "contentDisposition": "attachment; filename=\"whisnap-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "whisnap"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/whisnap"
    },
    "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."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/whisnap",
    "downloadUrl": "https://openagent3.xyz/downloads/whisnap",
    "agentUrl": "https://openagent3.xyz/skills/whisnap/agent",
    "manifestUrl": "https://openagent3.xyz/skills/whisnap/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/whisnap/agent.md"
  }
}
```
## Documentation

### whisnap

Use whisnap for transcribing audio/video files from the terminal. Requires the Whisnap macOS app with at least one model downloaded.

Setup (once)

Open Whisnap app → Settings → Advanced → Enable CLI (creates /usr/local/bin/whisnap symlink)
Download at least one Whisper model in the app

Common commands

Transcribe audio: whisnap recording.wav
Transcribe video: whisnap meeting.mp4
Cloud transcription: whisnap recording.wav --cloud
JSON output with timestamps: whisnap lecture.m4a --json
Specific model: whisnap interview.wav -m small-q5_1
Cloud + JSON: whisnap recording.wav --cloud --json
List downloaded models: whisnap --list-models
Verbose diagnostics: whisnap recording.wav -v

Supported formats

Audio: WAV, MP3, FLAC, M4A, OGG
Video: MP4, MOV, MKV, WebM

Flags

-c, --cloud — Use Whisnap Cloud instead of local model (requires sign-in)
-m, --model <ID> — Override model (e.g., small-q5_1). Defaults to app's selected model.
-j, --json — Structured JSON output with text, segments, timestamps, model info
-v, --verbose — Print progress and diagnostics to stderr
--list-models — List available models and exit

JSON output format

{
  "text": "transcribed text",
  "segments": [{ "start_ms": 0, "end_ms": 1000, "text": "segment" }],
  "model": "small-q5_1",
  "backend": "whisper",
  "processing_time_ms": 5000
}

Notes

The CLI reuses models and settings from the Whisnap app (~/Library/Application Support/com.whisnap.desktop/).
Cloud mode requires authentication — sign in via the app first.
For scripting, use --json and pipe stdout. Diagnostics go to stderr.
Exit code 0 = success, 1 = error.
Only Whisper models are supported in CLI mode (not Parakeet).
Confirm the file path exists before transcribing — the CLI validates but does not search.
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: Neolio42
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-11T01:24:09.481Z
- Expires at: 2026-05-18T01:24:09.481Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/whisnap)
- [Send to Agent page](https://openagent3.xyz/skills/whisnap/agent)
- [JSON manifest](https://openagent3.xyz/skills/whisnap/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/whisnap/agent.md)
- [Download page](https://openagent3.xyz/downloads/whisnap)