gooseworks-ai/goose-skills / skills/video/render-stopmotion-hand-swatch-cycle
render-stopmotion-hand-swatch-cycle
VerifiedAssemble a stop-motion hand-swatch-cycle product-demo ad from a config — a sequence of still PLATES (one hand swiping a single-barrel product across a test surface, the barrel + swatch changing per plate while the hand, background, crop, and lighting stay locked) is PNG→mp4 loop-encoded at each plate's own stop-motion hold (fast motion frames 150–250ms, per-shade ~380ms, hero beats 1100–1800ms), concat-demuxed with HARD cuts into a silent master, closed on a Playwright HTML-rendered branded end card (serif tagline + sans subtitle + real logo SVG over a hero BG, never AI-rendered text), and muxed with a pre-sourced music track playing under the end card with a fade tail (no VO). This is the FREE deterministic assembly stage (loop-encode + concat-demux + end-card render + music mux); the master-anchor plate, shade plates, and end-card BG come from create-image-gpt-image-fal and the track from create-music-elevenlabs. Use for the stopmotion-hand-swatch-cycle format.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.9 KB |
| scripts/PIPELINE.md | markdown | 5.7 KB |
| scripts/README.md | markdown | 3.0 KB |
| scripts/config.example.json | config | 11.2 KB |
| skill.meta.json | config | 190 B |
| tests/smoke-test.md | markdown | 1.4 KB |
tests/smoke-test.md
View on GitHub# Smoke Test
Given N still plates (a master-anchor hand + barrel + empty test surface, then per-shade / motion /
finale plates with ONE locked hand + crop + background), an end-card hero BG + brand logo SVG, and a
pre-sourced music track, `render-stopmotion-hand-swatch-cycle` assembles the master: loop-encode each
plate at its own stop-motion hold, concat-demux with HARD cuts into a silent body master, append a
Playwright HTML-rendered branded end card, mux the music under it → 1080×1920 h264+aac (~16.6s).
Pass when the assembly runs to a valid MP4 and:
- each plate is a still held for its `pose_hold_ms` (fast motion 150–250ms, per-shade ~380ms, hero
1100–1800ms); hard cuts between plates (no crossfades); the ONE locked hand + crop + background
holds across every cycle plate (no drift);
- each swatch stripe is the real variant color (grounded on the shade's swatch + hero refs);
- the end card is a Playwright HTML render (serif tagline + sans subtitle + the real logo SVG over
the hero BG, no AI-rendered text), the music carrying under it with a fade tail (no silent tail);
- the music is the entire bed — no separate VO;
- **no paid call is made** — the master-anchor plate, the shade / motion / finale plates, and the
end-card BG come from `create-image-gpt-image-fal`, and the track from `create-music-elevenlabs`;
this assembly is **free** and a re-cut (re-timed holds, a re-ordered cycle, a swapped end card) reuses
the existing plates.
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 |