Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →silverstein/minutes-video-review
Analyze a product walkthrough, bug report video, Loom, or ScreenPal using Minutes transcription plus visual review.
Passed 15 of 18 test cases with the skill, and 8 of 18 without it.
and 6 more in the full report
9 fixed9 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
When Minutes falls back from its primary configuration to Whisper during processing, what exact label should be reported in the transcript metadata output?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies the metadata label minutes-whisper-fallback. | Missed | Passed |
The instructions your model reads when the skill loads.
Analyze a product walkthrough, bug report video, Loom, ScreenPal, or local recording into a durable artifact bundle that agents can keep working from.
This skill is for meeting-adjacent product artifacts, not for generic "understand any video" requests. Use it when the user wants a recorded demo, bug repro, or walkthrough turned into something actionable for engineering, product, support, or follow-up agent work.
The bundled script handles the deterministic pipeline:
ffmpeg~/.minutes/video-reviews/Then you review the resulting artifacts and return the actual user-facing brief.
Local file:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/minutes-video-review/scripts/video_review.py" \
"/absolute/path/to/video.mp4"
Hosted video:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/minutes-video-review/scripts/video_review.py" \
"https://go.screenpal.com/watch/..."
Useful options:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/minutes-video-review/scripts/video_review.py" \
"https://www.loom.com/share/..." \
test cases passed, vs 8 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.