逆向导入已有小说。将已写好的小说(半成品或完本)反向解析为标准项目目录结构,兼容 story-long-write / story-short-write 后续写作流程;内部复用 story-long-analyze / story-short-analyze 的拆解管道,按篇幅自动分流。触发方式:/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」。
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads the author's own manuscript (user-supplied file or pasted text) and its own analysis outputs, which is first-party content. The only outsider-authored text is the optional external benchmark `拆文库/{对标书名}/`, which the user must explicitly select and which is consumed only after that selection, so it is a low-risk selected-document path.
zenstory-ai/oh-story-claudecode
41a9b6c
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.