Communitygithub.com

Demo-Video

Dieses Skill wird verwendet, wenn der Benutzer darum bittet, ein Demo aufzunehmen, ein Demovideo zu erstellen, einen Arbeitsablauf auf dem Bildschirm aufzuzeichnen, ein GIF zu erstellen, ein YouTube-Video zu machen, eine Sprachausgabe oder TTS-Erzählung hinzuzufügen, Untertitel zu erstellen oder eine Aufzeichnung eines Terminal- und Browser-Workflows in eine MP4-Datei mit Sprachausgabe und einer .srt-Datei oder einem kurzen GIF umzuwandeln.

Was ist Demo-Video?

Dieses Skill verwandelt einen realen Arbeitsablauf auf dem Bildschirm (Terminal, Browser oder eine App) in ein YouTube-taugliches MP4-Video mit einer TTS-Sprachausgabe und einer .srt-Untertiteldatei sowie optional in ein kurzes Highlight-GIF für README-Dateien. Es unterstützt die Planung mit dem Benutzer (Schrittliste, Fensterplatzierung), die native Bildschirmaufnahme unter Windows mithilfe von Desktop-Duplication (ddagrab), das Extrahieren von Schlüsselmomenten über zeitgestempelte Kontaktbögen (Contact Sheets) und das präzise Timen von Szenen mit Bildschirmaufzeichnungen. Die Erzählung wird über das edge-tts-Tool generiert, wobei die Sprechergeschwindigkeit an die Szenenlänge angepasst wird. Das Skill ist ideal für Entwickler, die Tutorials, Workflow-Demos oder Produktvorführungen im Terminal/Browser erstellen möchten, und erfordert ffmpeg, Python 3 und edge-tts. Es beachtet Plattform-Besonderheiten wie DPI-Skalierung und unsichtbare Fensterrahmen unter Windows und erzeugt sogar Untertitel mit Burn-In für Plattformen ohne Untertitel-Unterstützung.

Funktioniert mit✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/shannonbay/claude-demo-video-skill/tree/HEAD

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

Demo videos: record, cut, narrate, caption, GIF

Turns a real workflow on screen (a terminal, a browser, an app) into:

  • a YouTube cut: MP4 with a TTS voiceover, no burned captions, plus an .en.srt;
  • a highlights GIF: the key steps only, silent, no captions, small enough for a README;
  • optionally a captioned MP4 (burned-in subtitles) for places without caption support.

Scripts in scripts/ are templates: copy them into a folder for the video (outside any repo: recordings are hundreds of MB) and edit their config blocks. Needs ffmpeg (on PATH, or FFMPEG/FFPROBE env vars), Python 3, pip install edge-tts for the voice.

1. Plan with the person

  • Agree the story as steps, and which steps are theirs (clicks, typing) vs. waiting. Write them the step list with what to press, so they can drive while recording.
  • Pick the subject (an issue, a to-do) that shows something visible.
  • Clear the stage: remove duplicates of what the demo creates, close personal tabs (open a fresh browser window with only the site), hide notifications. Mention anything noisy (update banners).
  • Tell them anything they type to Claude while recording is on screen: keep it to "next" / "done".

2. Frame both windows on one capture box

Put every window the demo uses at exactly the same rectangle (1920×1080 is a good default) and record that box: whichever window is in front is the shot, so switching windows is the edit.

scripts/rec.ps1 place -X <px> -Y <px> does it on Windows. Things that bite:

  • DPI scaling: coordinates from a non-DPI-aware process are scaled (125 % → a "1920" window is 1536 physical). place sets per-monitor DPI awareness (SetThreadDpiAwarenessContext(-4)) so everything is physical pixels. List monitors with rec.ps1 monitors.
  • Invisible borders: Windows 10/11 windows have ~7 px invisible borders. Size by the DWM visible bounds (DWMWA_EXTENDED_FRAME_BOUNDS), not GetWindowRect; place measures and corrects.
  • Grab one frame and look at it before recording (Read the PNG).

3. Record

scripts/rec.ps1 start <name> / stop / mark <text>. Notes:

  • gdigrab isn't DPI-aware and captures a scaled-down desktop on a scaled monitor (and __COMPAT_LAYER=HighDpiAware doesn't fix it). Use Desktop Duplication (ddagrab), which is native pixels per monitor. Its offset_x/y are relative to that monitor.
  • A monitor on a second GPU (laptop + external display) isn't on adapter 0: -init_hw_device d3d11va=dx:<adapter> -filter_hw_device dx with ddagrab=output_idx=<n> in -filter_complex. rec.ps1 start takes -Adapter and -Output; try 0/1 if "Failed to enumerate DXGI output".
  • Write MPEG-TS (-f mpegts): the process is killed to stop, and MP4/MKV lose their header that way.
  • Split into clips at natural breaks (setup / the person's input / one long take of the waiting). One long take of a slow process is fine; the edit speeds up the waits.
  • While the person drives, relay what each background step reports and what to press next, briefly.

4. Find the moments

Don't scrub video. Make timestamped contact sheets and Read them: python scripts/sheets.py <clip.ts> --every 10 (whole clip), then --from 170 --to 236 --every 2 --crop 900:560:1020:0 around each click to find the exact seconds a proposal appears, a button is pressed, a page loads. Write down: (clip, start, end) for each step, and which spans are waits.

5. Narration

lines.txt: one line per scene (a step of the story), written as caption text. Spoken English, short sentences, says why not just what. voice.py has a SAY map for how symbols are spoken (#92 → "ninety-two", /goal-new → "goal new", CI → "C I"); captions keep the original. Default voice en-US-AndrewNeural at +4 %; list voices with python -m edge_tts --list-voices. Re-voice one line with --only N.

6. Build

scripts/build.py: SCENES is a list of scenes, each a list of segments (clip, start, end, speed):

  • the person's clicks at 1–2×; browser pages at 2–4×; machine work at 6–40× with a ▶▶ N× badge (drawn when speed ≥ 3);
  • a scene shorter than LEAD + its line + TAIL gets its last frame held (tpad), so the voice never overruns;
  • outputs youtube/<name>-youtube.mp4 (video + voice, -c copy), youtube/<name>-youtube.en.srt (each line split into ~70-char cues timed by character share), and a thumbnail.
  • --burn also writes <name>-captioned.mp4 with burned-in subtitles.

Aim for 1.5–3.5 min. If narration leaves long silences, speed up the scene rather than padding words.

7. GIF

A GIF is not the video at speed: it's the key steps only. scripts/gif.py: HIGHLIGHTS = (clip, start, end, speed, crop), each 3–7 s, cropped (1280×720 window of the frame: the pane, the web page, a menu) and scaled to 960×540 at 8 fps, one palette (palettegen stats_mode=diff, paletteuse dither=none diff_mode=rectangle). No captions, no badges. Keep it under 10 MB (GitHub's image limit) and under ~60 s. Check it by tiling each highlight's last frame and reading the image.

8. Hand-off

A README.md in the video folder: what the video shows, outputs table, what each source/script is, the recorder's frame and any capture quirks, and how to rebuild (re-voice → build → gif). Offer to remember the folder's location in memory.

Verwandte Skills