Individual skill

story-review

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」。

skills/story-review/SKILL.md

Read pinned source

Source commit 7383fd6cd8acee8cf9f7805b058d1f342874a7c2

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 8,545
Repository last updated: Nov 11, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

ai-writing Repository topic
claude-code Repository topic
claude-skills Repository topic
creative-writing Repository topic
novel-writing Repository topic
openclaw Repository topic
writing-assistant Repository topic
ai-agent Repository topic
chinese-novel Repository topic
skill Repository topic
engineering Derived category

Declared tags are partial or unavailable.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 21,128 bytes
SKILL.mdcore · 21,128 bytes
references/agent-prompts.mddoc · 14,249 bytes
references/banned-words.mddoc · 11,297 bytes
references/batch-review.mddoc · 2,325 bytes
references/expression.mddoc · 9,746 bytes
references/narrative-focus.mddoc · 6,856 bytes
references/quality-rubric.mddoc · 4,847 bytes
references/review-tracking.mddoc · 2,620 bytes
references/rubrics/fanqie.mddoc · 1,140 bytes
references/rubrics/qidian.mddoc · 1,133 bytes
references/rubrics/zhihu.mddoc · 1,571 bytes
references/solo.mddoc · 3,471 bytes
references/story-logic.mddoc · 6,051 bytes
references/style-resolution.mddoc · 3,799 bytes
references/tracking-initialization.mddoc · 1,651 bytes
references/tracking-transaction.mddoc · 15,877 bytes
scripts/check-ai-patterns.jsruns · 75,274 bytes
scripts/check-degeneration.jsruns · 15,389 bytes
scripts/normalize-punctuation.jsruns · 15,411 bytes
scripts/style-whitelist.jsruns · 1,168 bytes
scripts/tracking_commit.pyruns · 85,124 bytes
scripts/wordcount_core.pyruns · 19,317 bytes

Read excerpt

# 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: 40` 不一致时（标记缺失、字段缺失/非整数、小于或大于 40）**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 40）` 原文写进技术备注行；大于 40 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](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。

## 作者偏好边界

只接收调用方已有的作者偏好，不查询或记录作者记忆；独立调用时不加载记忆文件。偏好只能帮助解释意图和组织报告，不能降低 rubric 严重度、把事实冲突判为无问题或跳过平台门禁；当前请求仍优先。

---