generic-videolisted

Create a genre-agnostic AI video — either recreating a source (handed over by mimic-video) or from a fresh brief. Owns the creative intake (fidelity, theme/style, pacing, duration, stitch-vs-fully-AI, model, voice) and the build flow. References ugc-craft for prompt craft, ai-video-models for per-engine rules, ai-asset-generation for mechanics.
Nagellabs/libi · ★ 2 · AI & Automation · score 75

Install: claude install-skill Nagellabs/libi

# Generic Video Creation Genre-agnostic AI video creation. Two entry modes: (a) `mimic-video` handed you a source + analysis to recreate; (b) a direct from-scratch brief. Either way: run the intake, then build. **Load by reference (never duplicate):** - `video-planning` — the senior-editor planning/director layer: decompose the source/brief into building blocks (source-vs-AI, combine-vs-split, style inheritance) BEFORE building cards. Owns Step 3's beat plan. - `ugc-craft` — the 9-layer prompt formula, the **clip-duration methodology (≤15s one multi-beat clip; do NOT fragment a short ad into many 3–6s clips)**, realism cues, negative lists. - `ai-video-models` — the per-engine prompting guide for your chosen model. - `ai-asset-generation` — the call + save mechanics (recommend_model / schema / pricing / polling / import) and the universal video invariants (**no in-video text**; **native audio on**). - `realistic-image-generation` — the keyframe / portrait image craft (gpt-image-2 default). - `physical-action-video` — manipulation-beat craft (FLF-first, decomposition, model ladder) when a beat physically manipulates an object. - `voiceover-production` — the generation-time audio/voice authority (native audio always; multi-clip voice carry). - `voice-replacement` — re-voice / dub an EXISTING video (clone or new voice + lip-sync); user-triggered, only when asked. ## The Storyboard is the build spine (default — not optional) You build the video **through the Story