# Compose Summary Video

> Compose Summary Video is an Agent Skill for documents published in the understudy-ai/understudy repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Compose the final draft summary video from the generated assets and brief.

- Skill name: `compose-summary-video`
- Category: [Documents](https://www.openparable.com/skill/documents/1)
- Source: https://github.com/understudy-ai/understudy/blob/HEAD/packages/gateway/src/__tests__/fixtures/handwritten-playbook-demo/skills/compose-summary-video/SKILL.md
- Repository: understudy-ai/understudy (448 GitHub stars when collected)

## SKILL.md

# compose-summary-video

## Overall Goal

Compose a draft summary video from the generated brief assets.

## Inputs

- cover.png
- summary-card.png
- brief.md
- screenshots/*

## Outputs

- draft.mp4

## Staged Workflow

1. Pick the screenshots that best support the brief.
2. Assemble a concise timeline.
3. Render `draft.mp4`.

## Tool Route Options

- shell plus ffmpeg for deterministic composition

## Detailed GUI Replay Hints

- None. This stage should not require GUI work.

## Failure Policy

- If video composition fails, keep the still assets and emit a fallback note.

---

Source: https://www.openparable.com/skill/documents/compose-summary-video (OpenParable). Cite the canonical URL above.