多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn;缺失/异常 agents 或 spawn 失败时自动降级 solo,参考文件不可读时使用内置 rubric fallback。触发方式:/story-review、/审查、「审查一下」「帮我审一下」。
80%
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
Fix and improve this skill with Tessl
tessl review fix ./skills/story-review/SKILL.mdThe 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 review workflow reads the author's own manuscript, settings, and tracking files, which are not outsider-authored; the only outsider-text path is the optional story-researcher fact check, which actively searches external sources and so falls under low, not medium.
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.