delivery-video

A skill plugin that turns a feature that actually runs into a trustworthy delivery demo video — real screen recordings, synthesized narration, word-synced subtitles, and a deterministic quality gate that refuses to pass a fake or broken demo.

Most "AI demo videos" are stitched from static screenshots, mock pages or stale recordings. This plugin enforces the opposite discipline: every segment must point at a real recording with a traceable time range, the last shot must end on a verified result state, and the artifact must pass a hard gate (resolution/fps/codec, audio presence, loudness, black frames, freeze frames, bitrate density) before anything is posted. The uploaded file is always the gated file, bound by SHA256.

What it does

1. Verify first, record second — the workflow requires evidence that the current version really runs (git SHA, tickets, request IDs) before any recording.
2. episode.json recipe — each segment binds one real take + time range + one narration line + optional crop/case chip.
3. Self-contained renderer — render.py synthesizes narration via edge-tts (word-boundary clocks), times each segment to its narration (0.3x–3x speed clamp), draws the label chip and word-synced subtitles, concatenates, loudness-normalizes to −14 LUFS, and runs the built-in quality gate. Output: screen_demo.mp4 (1920×1080, 30fps, h264+AAC), timeline.json, cover/preview frames, quality_gate/report.json.
4. Fail-loud checks — preflight.py validates the recipe before rendering (structure, intervals, crops, browser-recording evidence, TTS cache contracts, narration red lines); verify_delivery.py verifies the finished artifact, gate binding and optional independent visual review afterwards.
5. Attachment gate — render.py gate runs the same hard checks on any mp4 before it goes into a ticket, chat or customer channel.

Prerequisites

• python3 3.9+
• ffmpeg and ffprobe on PATH
• pip install edge-tts Pillow

Side effects (disclosed for review)

• Network: narration synthesis calls the public edge-tts (Microsoft Cognitive Services) endpoint; no other network access.
• Files: writes only inside the build directory you pass in (tts/ cache, per-segment clips, final mp4, gate reports).
• Commands: runs ffmpeg/ffprobe locally; the skill never uploads, publishes or deletes anything by itself.

Quick start

1. Record real takes of the feature with your usual tool (macOS Cmd+Shift+5, OBS, or a scripted browser screencast — see the skill's recording reference).
2. Create build/screen_demo-<slug>/episode.json (copy examples/episode.example.json).
3. Run the three scripts:

python3 <skill>/scripts/preflight.py build/screen_demo-myfeature
python3 <skill>/scripts/render.py render build/screen_demo-myfeature
python3 <skill>/scripts/verify_delivery.py build/screen_demo-myfeature

Suggested trial prompt after install: "用 delivery-video 把这个项目刚完成的功能录成一段 90 秒交付演示视频" — the skill will walk verification, storyboard, recording guidance, recipe assembly, render and gating.

License

MIT © Lumos-789