HezaoHezao
Featured
poirot
Poirot is a deep research agent kernel with a middleware-first architecture, five-layer long-term memory, multi-agent orchestration, sandbox isolation, and a three-layer skill self-evolution system, backed by 2400+ tests.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It enforces a three-stage human approval process (concept → still frame → video) to prevent wasted API costs, while producing a distinctive stop-motion paper collage aesthetic.
Who it is for
- Video editors seeking unique B-roll assets
- Content creators who need to quickly visualize spoken lines
- AI video workflow adopters wanting cost-efficient generation
- Media producers requiring batch processing of short scripts
Use cases
- Generating editorial-style B-roll for podcast or voiceover videos
- Producing multiple collage animations from a list of script lines in one batch
- Creating visually striking transitions or background clips for presentations
Strengths
- Three-gate workflow minimizes expensive video re-generation by catching poor ideas early
- Uses Gemini Omni Flash for first/last frame animation, ensuring consistent motion
- Produces a unique halftone paper-collage look with flat color fields and stop-motion feel
- Supports batch processing with partial pass-through for approved entries only
Considerations
- Requires manual environment setup (Gemini API key, Python, ffmpeg) and dependencies
- First frame may show slight paper edge details, potentially needing timeline tools for strict empty-field shots
- Default locked to gemini-omni-flash-preview model; switching requires explicit specification
README quick start
安装
Description
半调纸拼贴 B-roll 生成 skill：三闸门审批，Gemini Omni Flash 首尾帧组装动画 | Editorial halftone paper-collage B-roll agent skill
Related repositories
Similar projects matched by category, topics, and programming language.
0xwilliamortiz
Featured
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
lopopolo
Featured
harness-engineering
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.