story-long-analyze
story-long-analyze is a Fiction & storytelling skill for AI agents, published by zenstory-ai in the oh-story-claudecode repository on GitHub. Skillspace rates story-long-analyze C (74/100) and it passed the safety scan; a judge model has also reviewed it.
长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。单一深度拆解管道：跑完黄金三章（Stage 1）后产出快速预览报告并询问是否继续全量拆解，确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告，全程产物落盘 拆文库/{书名}/。触发方式：/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」「深度拆解」「完整拆解」「系统拆解」或提供小说文本文件路径——全部进入同一管道。
- Grade
- C
- Quality
- 74 / 100
- Safety
- Passed
- GitHub stars
- 6,471
Placed #2 of 6 in the judged category final for Fiction & storytelling.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 88 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Portable: works in any project. General web-novel structural analysis method, no repo dependencies.
Judge review
Placed #2 of 6 in the judged category final for Fiction & storytelling.
- Trigger
88 88 - Instructions
92 92 - Specificity
92 92 - Safety
55 55 - Disclosure
55 55 - Maintenance
80 80
An extraordinarily engineered multi-stage pipeline with resumability and cross-runtime fallbacks, undercut by an instruction telling the model not to refuse whole chapters on sensitivity grounds.
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Also published in 1 other repo
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.