Story Review

This runs a multi-agent adversarial review of your story drafts. It spawns four parallel agents (story-architect, character-designer, narrative-writer, consistency-checker) that each tear into your content from different angles, then synthesizes their findings into a single report with severity ratings. You get three modes: full runs all four agents, lean runs just architecture and consistency checks, solo does basic format validation without spawning anything. It's explicitly designed to find problems, not validate correctness, and it handles platform-specific rubrics for Chinese web fiction sites like Qidian and Fanqie. The agents don't inherit context, so each gets a self-contained prompt with file paths. If agents disagree, it surfaces the conflict instead of auto-resolving, which is honest but means you're the tiebreaker.

skills.sh installs: 11.1K
GitHub stars: 5.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add worldwonderer/oh-story-claudecode --skill story-review --agent claude-code

Installs into .claude/skills of the current project.

Files

story-review：多视角对抗式审查

Spawn 版本提示（不阻断 spawn）：先读取项目根 .story-deployed 的 agents_version。与本版 agents_version: 44 不一致时（标记缺失、字段缺失/非整数、小于或大于 44）照常按当前宿主角色来源检查并 spawn；同时在「这次怎么审的」里用一句白话提示作者「审稿助手是旧版，运行 /story-setup（ZCode 先更新插件）后新开会话」，Notice: agents bundle 版本不匹配（项目 {N}，本版 44） 原文写进技术备注行；大于 44 时额外提示先更新 oh-story-claudecode，不要用本地旧版 setup 降级覆盖。版本提示本身不触发降级；文件缺失或异常、工具不可用、递归限制或调用失败按 Phase 0 处理，技术备注写 Fallback: ... -> solo。

你负责协调审查，找出小说的结构、角色、文字与设定问题，给出有原文依据的修改建议。

执行铁律：审查是找问题，不是验证正确性。

文风裁决：先读 references/style-resolution.md，加载本书文风，复用调用方的 style_resolution 与作者偏好；单独调用时按当前请求与本书文风裁决。同一裁决交给后续执行者。