proving-it-works
v0.1.0by prime-radiant-inc · author: Prime Radiant, Inc.
Record a demo, tutorial, or proof movie of software actually running, and catch the silent defects (frozen picture, narration talking over a dead screen, dropped words, invisible clicks) before you hand it to anyone
What proving-it-works does, in the publisher's words
A Claude Code plugin for making a movie that proves software actually works, and for catching the defects that make such movies worthless before you hand one to anybody.
▶ Watch the full two minutes, with sound · subtitles · how it was made
A clean container installs this plugin from the public marketplace, an agent inside it uses the skill to make a narrated movie of a small web app, and the skill's own checker verifies that movie. The loop above is that inner movie playing: real screenshots, a cursor you can watch, a local voice (there is no API key in that container), and subtitles burned into the picture.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 1
- MCP servers
- 0
- Stars
- 38
- License
- MIT
- Repo created
- 2026-08-11
- Last pushed
- 2026-09-26
- Publisher type
- Organization
- Version
- 0.1.0
Links
Skills · 1
- proving-it-works-with-a-movie
- Use when asked for a demo, screencast, tutorial, walkthrough, or proof video of software actually running, when a reviewer needs to see a feature work rather than take your word for it, or when handing over any video artifact of app behavior
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Testing. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
screencast · demo-video · tutorial · ffmpeg · playwright · narration · tts · verification · evidence
Related by publisher and keywords
Ledger-backed persistent memory for coding agents: append-only facts with retraction vaccines, scars, and a generated MEMORY.md projection
Shepherd GitHub pull requests through CI and review.
Agent Plugins package (v2.0.3): 4 Playwright E2E skills: test planning by page role, script authoring with video / trace evidence, report generation with Drive archiving, and the playwright_kit runtime (init, a11y / CWV scans).
Evidence-first coding agent. Verifies before presenting. Attacks its own output with adversarial multi-model review, IDE diagnostics, and SQL-tracked verification to ensure code quality.
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
Auditable context selection, exact recovery, and receipts for AI coding agents.
[](https://agentpluginsdirectory.com/plugins/proving-it-works)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.