pr-to-video

Converts a GitHub pull request into a code-change explainer video built from its diff and commits.

Updated Aug 28, 2026
One-click install
npx skills add https://github.com/AnderHonorato/Mem-rias-IA---Infinity --skill pr-to-video-anderhonorato
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pr-to-video
Source: https://github.com/AnderHonorato/Mem-rias-IA---Infinity/tree/main/Manus/Skills/html-video-production/references/pr-to-video
Command: npx skills add https://github.com/AnderHonorato/Mem-rias-IA---Infinity --skill pr-to-video-anderhonorato

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Turning a merged or proposed pull request into a clear video explanation normally requires manual scripting, screen recording, and editing. This Skill automates that pipeline: it ingests a PR via the GitHub CLI, plans a narrative from the diff, and renders a finished MP4 explainer. ## Core Features & Use Cases - Deterministic PR ingestion: Fetches PR metadata, the full paginated file list, and the diff via gh, then builds a synthetic capture package with contributor avatars for a credits close. - Storyboard and script generation: Plans changelog, feature-reveal, fix-explainer, or refactor-walkthrough narratives with real diff hunks, then produces narration audio, captions, and background music. - Frame-by-frame HTML video assembly: Dispatches bounded frame workers to build HTML compositions, assembles them into an index, and renders the final MP4 with lint, check, and snapshot verification gates. - Use Case: After merging a large feature PR, point the Skill at owner/repo#123 to produce a narrated walkthrough video highlighting the key diff hunks and crediting contributors. ## Quick Start Turn the pull request at owner/repo#123 into a narrated code-change explainer video and render it as an MP4.

Frequently Asked Questions about pr-to-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn a GitHub pull request into a video?

Provide a PR URL, an owner/repo#N reference, or run it in a checked-out repo. The skill fetches the PR with the gh CLI, plans a storyboard from the diff, builds HTML frames, and renders a final MP4 after approval.

What inputs does a PR explainer video workflow accept?

It accepts a full GitHub PR URL, an owner/repo#N shorthand, or the phrase 'this PR' inside a checked-out repository. It does not capture websites; the only real assets are contributor avatars used in the credits close.

Does this work for product promos or general topic explainers?

No. It is scoped to code changes from a pull request. Product launch videos and non-PR topic explainers are routed to separate skills, and unclear requests fall back to the hyperframes intent layer.

Why does PR fetching fail with an auth or not-found error?

The fetch step exits when the gh CLI is unauthenticated or the PR is private or missing. Authenticate gh and verify the PR reference, then rerun; the skill never fabricates PR contents.

How are large pull requests with many files handled?

The fetch script completes the files list through paginated gh api calls, so a large PR does not truncate at roughly 100 files. The storyboard then features only 2-4 representative diff hunks for legibility.

Can the video render without narration or audio?

Yes. A project marked with music set to none and no script file is treated as fully silent. Duration sync and SFX fetching are skipped, and assembly proceeds with frames only.