gemini-video-analyzerlisted
Install: claude install-skill cyuanxv/agent-cockpit
# Gemini Video Analyzer
Analyze local video files with Gemini API while keeping Codex as the local harness. The main contract is: fixed JSON first, Markdown report second, and timestamp evidence that a human can replay.
## Inputs
Ask for a local video path if the user did not provide one. Accept only `.mp4`, `.mov`, `.m4v`, and `.webm`.
Default analysis goal:
- Chinese output.
- One-sentence conclusion.
- Content summary.
- Timeline with reviewable timestamps.
- Key visuals, audio, subtitles, narration, UI flow, and actions.
- Key moments, editing suggestions, follow-up suggestions, and uncertainties.
## Procedure
1. Verify that the video file exists.
2. Tell the user that the video will be uploaded to Gemini API for analysis.
3. Run a cost estimate before analysis when the user has not already approved the run:
```bash
python3 skills/gemini-video-analyzer/scripts/gemini_video_analyze.py estimate "<video_path>"
```
4. Analyze with the recommended model and explicit confirmation:
```bash
python3 skills/gemini-video-analyzer/scripts/gemini_video_analyze.py analyze "<video_path>" --goal "<analysis_goal>"
```
For non-interactive approved runs, pass `--yes`.
5. If the user names a model, pass it explicitly:
```bash
python3 skills/gemini-video-analyzer/scripts/gemini_video_analyze.py analyze "<video_path>" --model gemini-3.5-flash --goal "<analysis_goal>" --yes
```
6. Transfer mode defaults to `auto`: videos up to 20 MB use inline Gemini c