digitalsamba__claude-code-video-toolkit

skills/digitalsamba__claude-code-video-toolkit

mirror of https://github.com/digitalsamba/claude-code-video-toolkit.git synced 2026-09-18 19:41:13 +08:00

Files

T

Conal Mullan 9a57fdf284 SKILLS: add moviepy skill, audio-anchored timelines, LTX-2 cameo pattern

Three coordinated additions promoting lessons from the q2-townhall projects
to toolkit-level guidance:

- New moviepy skill covering deterministic text overlay on AI-generated
  video (LTX-2, SadTalker) — the canonical post-process for any genre
  where text must be trustworthy (news, trailers, lower thirds, social
  captions). Includes the PIL workaround for moviepy 2.x's TextClip
  ascender-clipping bug, plus common composite recipes.

- ltx2 skill: add "Stylized Character Cameo" use case as a SadTalker
  alternative for non-photoreal faces (fantasy characters, heavy beards,
  masks) where lip-sync precision matters less than motion + atmosphere.

- docs/sadtalker.md: add "When NOT to Use" section pointing to LTX-2 for
  the same cases.

- CLAUDE.md: add "Audio-Anchored Timelines" section to the timing guide
  as a prevention-first complement to the existing reactive sync_timing.py
  flow. Especially useful for moviepy build.py-style projects.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-08 21:21:29 +01:00

contributing.md

Add /versions to README and documentation checklist

2025-12-20 17:12:29 +00:00

creating-brands.md

Add tone presets, voice-clone command, and brand integration for Qwen3-TTS

2026-02-20 13:38:53 +00:00

creating-templates.md

Complete transitions library with checkerboard, fix clockWipe and pixelate

2025-12-18 11:03:34 +00:00

getting-started.md

Add /setup wizard, verify script, and migrate dewatermark to cloud_gpu