Purpose
Create a product stop-motion video using reference mapping, generated plates, text overlays, music, assembly, review, and export.
Implementation status: extracted from existing repository skills. The workflow is based on working source material and still requires the standard smoke and human tests after migration.
Sources: product-stopmotion-ad.
Extraction notes: Composes atoms from source workflow: product-stopmotion-ad.
Inputs
- A clear user brief or source asset path.
- Brand, product, audience, platform, and approval constraints when relevant.
- Required credentials or provider access for any external service used by this skill.
- Output directory or test-run directory where artifacts should be saved.
Composed Atoms
create-storyboardcreate-product-images-nanobananaadd-text-overlaysfind-musicstitch-videos-ffmpegwatch-and-refineexport-video-final
Workflow
- Read the brief and confirm all required inputs are present.
- Load any referenced files in this skill folder only when they are needed.
- Run the provider, script, or planning workflow described by this skill.
- Save outputs under the requested output folder or
skills/test-runs/<timestamp>/<skill-name>/during tests. - Write or update a
manifest.jsonfor executable runs with status, provider, outputs, warnings, and errors.
Decision Rules
- Prefer extracted atoms over recreating provider-specific details in this molecule.
- If an atom is marked as a scaffold, stop before production execution and report what is missing.
- Keep human approval gates when the source workflow requires brand, visual, or final-video review.
- Do not skip review and verifier steps before delivery.
Output
- Primary artifact or written plan requested by the skill.
manifest.jsonfor executable runs.verification.mdor a short verification summary that names the checks performed.- Any generated source assets, intermediate files, or final exports in the run folder.
Quality Checks
- Required files exist and paths in the manifest are valid.
- Output matches the requested format, platform, duration, dimensions, or text structure.
- Brand claims, captions, on-screen text, and CTAs follow the provided brand rules.
- Provider failures, skipped integrations, and human-review needs are explicit.
Failure Modes
- Missing credentials, provider access, or source files.
- Output does not match requested dimensions, duration, structure, or brand constraints.
- Generated media contains artifacts, unreadable text, unsafe claims, or caption collisions.
- Scaffolded skills cannot run production workflows until implementation details are added.