Open-source qiaomu-cut Skill turns one sentence into a reproducible AI video production pipeline
vista8 · x · 2026-09-28
Built on popular Opus 5.5 prompting patterns, qiaomu-cut-skill (339 stars on GitHub) is an open-source "AI video director" Skill: say what video you want and it organizes sourcing, storyboarding, subtitles, transitions, rendering and QA into a reproducible video project.
- It first generates a QiaoCut IR, then routes to engines like 33taici, ClipSeek/Pexels/Pixabay, local assets, ListenHub/MarsWave TTS/music, Coli local ASR, agent image generation, and HTML/Manim/PPT, compositing via ffmpeg-full.
- v0.9 ships one-sentence explainer Autopilot, movie-recap fast track, paid-clip sentence gating, SHA asset audits, batch HTML/SVG scene rendering, auto frame review, real narration duration locking, dynamic subtitles, and three render tiers with final/full acceptance.
- v0.13 adds a code-driven motion graphics studio distilled from 54 Opus 5.5 code-generated video cases.
Install: npx skills add joeseesun/qiaomu-cut-skill --skill qiaomu-cut.
Related event: Open-Sourced Skill Lets Claude Generate Product Promo Videos From a Repo(3 posts)→
More from coding & agent
- Continual-ARC: lifelong ARC-AGI stream finds agent harness persistence rarely beats simple caching — unifyai · 2026-11-16
- WebArena-Pro: a 300-task multimodal benchmark across 20 self-hosted apps for web agents — McGill-NLP · 2026-11-16
- Filmworkbench v0.1.2: one-prompt semi-automated short films with Claude and ComfyUI — Eastern-Ad9515 · 2026-11-16
- Stop prompting LLMs for JSON: PowerShell module Jev routes with decision models — dfinke · 2026-11-16
- llama.cpp offloads CI caches and runners to Hugging Face to survive 35 PRs/day — ggerganov · 2026-11-16
- I killed my 30-minute weekly sync with a decision log my agents read before every run — Humaux · 2026-11-16