ワンクリックで
demo-iterate
Iteratively refine a demo spec through run-review-fix cycles until the output is satisfactory.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Iteratively refine a demo spec through run-review-fix cycles until the output is satisfactory.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Generate a polished product demo video from a YAML spec using demo-machine. Use when the user wants to create, run, or update a demo video for their app.
Generate a complete demo-machine YAML spec by crawling a live web app. Give it a URL and description, get a ready-to-run spec.
Automatically fix a broken demo-machine spec by analyzing failure artifacts (screenshots, DOM, error logs). Use when a demo fails after a UI change.
Generate compelling AI narration for every step in a demo-machine spec. Use when a spec has no narration or needs better narration text.
AI quality review of a completed demo run. Analyzes event log, timing, and narration to flag issues and suggest improvements.
Convert an existing Playwright or Cypress E2E test file into a demo-machine YAML spec. Reuses test coverage as demo scripts.
| name | demo-iterate |
| description | Iteratively refine a demo spec through run-review-fix cycles until the output is satisfactory. |
| argument-hint | ["spec-file"] |
| allowed-tools | Read, Write, Edit, Glob, Grep, Bash(node *), Bash(pnpm *), Bash(ffprobe *) |
Guide an iterative run-review-fix-rerun cycle to polish a demo spec.
$ARGUMENTS should be a path to an existing .demo.yaml file.node dist/cli.js run <spec> --output ./output --no-headless --verbose
output/output.mp4 for visual qualityoutput/events.json for timing and event flowoutput/subtitles.vtt for narration alignmentffprobe output/output.mp4 to verify resolution and durationdelay on steps, add wait stepsnarrationBufferauto-sync narration modewait after animations, increase settleDelayMsApply targeted changes to the spec file based on the diagnosis.
Run again and compare with the previous output.
--no-narration to debug visual issues without TTS overhead--no-edit (capture only) to speed up iteration on selectorsfailure.json and failure.png if the run crashesArguments: $ARGUMENTS