gooseworks-ai/goose-skills / skills/video/watch
watch
VerifiedObserve actual video and sound over the whole file or named ranges, with timestamped evidence and honest coverage. Use complementary playback, listening and targeted frames; return observations without edits or verdicts.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.7 KB |
| references/parameters.md | markdown | 2.3 KB |
| skill.meta.json | config | 120 B |
| tests/expected-output.md | markdown | 724 B |
| tests/human-test.md | markdown | 1.1 KB |
| tests/sample-input.md | markdown | 692 B |
| tests/smoke-test.md | markdown | 705 B |
tests/human-test.md
View on GitHub# Human Test
Goal: run `watch` against a real short ad and confirm the observation report is useful as input for a refinement pass.
Steps:
1. Create `skills/test-runs/<timestamp>/watch/`.
2. Pick any 5–30s rendered ad you have locally (a finished render from any project).
3. Run `watch` with defaults (all audio flags true, no `ranges`, no `fps`).
4. Re-run `watch` on the same file with `ranges=[["0:00","0:03"]]` and `fps=2` to confirm the focused mode produces a denser report for the hook.
5. Re-run once more with `include_music=false` and `include_sfx=false` to confirm voice-only mode and the manifest reflects the disabled flags.
Human acceptance criteria:
- Report timestamps line up with what's actually on screen.
- VO transcript matches the audio (when voice was enabled).
- Manifest accurately records which audio dimensions were considered.
Human rejection criteria:
- Report contains verdicts or recommendations (that's the refine skill's job, not this one).
- Frames are sampled outside the requested ranges.
- A disabled audio dimension is silently skipped without being recorded in the manifest.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |