Agent skill · Code Review & Quality

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」。

pitechen592★ · +23/wk · 2 repos on radarProfile →
claude-codeships scriptsMIT
Install
npx skills add worldwonderer/oh-story-claudecode --skill story-review --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 14
SKILL.md size: 19 KB
Bundled scripts: yes
Version: 1.1.0
Path: skills/story-review/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 5,024
Language: JavaScript
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# story-review:多视角对抗式审查 你是审查协调器。你的职责是找出小说文本中的结构、角色、文字、设定问题,并给出可执行修改建议。 **执行铁律:审查是找问题,不是验证正确性。** --- ## Review Mode 选择 - `/story-review` 或 `/story-review full` → 优先 spawn 全部 4 个 Agent;如果当前已经在子代理内,核心 Agent 未部署/异常,或 spawn 失败,自动降级为 solo。 - `/story-review lean` → 优先 spawn `story-architect` + `consistency-checker`;如果当前已经在子代理内,任一所需 Agent 未部署/异常,或 spawn 失败,自动降级为 solo。 - `/story-review solo` → 不 spawn Agent,由当前会话执行基础审查。 - 未指定 → 默认 full,并在报告里写明最终实际执行模式。 > AI味 / 文字自然度这一维度只有 `narrative-writer` 审,仅 full 模式覆盖。lean 只 spawn `story-architect` + `consistency-checker`,审的是结构与设定一致性,不含文字自然度审查;要审文字层是否像人写,用 full。 --- ## Phase 0:预检与降级(必须先执行) 1. **确定请求模式**:解析用户输入中的 `full`、`lean`、`solo`;未指定时目标模式为 `full`。 2. **确认是否允许 spawn**:如果当前已经在子代理/Agent 内执行,不再递归 spawn,直接降级为 `solo`。 3. **识别 ZCode 能力边界**:如果当前运行于 ZCode 且项目使用 `.zcode/`,ZCode 3.3.4 不执行项目/plugin custom agents;不要因为磁盘上存在其他端的 agent 文件就尝试同名 spawn,直接降级 `solo` 并报告 `Fallback: project custom agents unavailable -> solo`。 4. **检查核心 Agent 部署状态**(检查项目内 agents,同时兼容 Claude Code、OpenCode 和 Codex): - 优先检查 `.claude/agents/`,其次检查 `.opencode/agents/`,再检查 `.codex/agents/`;三个目录任一存在即视为已部署 - full 必需:Claude/OpenCode 为 `story-architect.md`、`character-designer.md`、`narrative-writer.md`

What's inside
Steps it walks through
  1. Review Mode 选择
  2. Phase 0:预检与降级(必须先执行)
  3. 审查基准与参考资料规则(必须遵守)
  4. 报告元数据字段(必须逐字输出)
  5. 参考资料解析顺序
  6. 内置审查基准包(路径不可读时必用)
  7. 传给子 Agent 的规则
  8. Phase 1:收集待审查内容
  9. 统一 Findings Schema(所有模式必须使用)
  10. Phase 2:并行 Spawn Agent(full/lean 模式)
  11. Phase 3:综合裁决
  12. Phase 4:输出报告(full / lean 模式)
  13. lean 模式
  14. solo 模式
Ships with 13 files
  • references/anti-ai-writing.md
  • references/banned-words.md
  • references/character-relations.md
  • references/dialogue-mastery.md
  • references/plot-core-methods.md
  • references/quality-checklist.md
  • references/quality-rubric.md
  • references/rubrics/fanqie.md
  • references/rubrics/qidian.md
  • references/rubrics/zhihu.md
  • scripts/check-ai-patterns.js
  • scripts/check-degeneration.js
  • scripts/normalize-punctuation.js
Commands it runs
node scripts/normalize-punctuation.js --check <正文文件...>
node scripts/check-ai-patterns.js --check --fail-on=blocking <正文文件...>
node scripts/check-degeneration.js --check <正文文件...>
More from oh-story-claudecode
All skills →
About this skill
What does the story-review skill do?

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」。

How do I install it?

Run `npx skills add worldwonderer/oh-story-claudecode --skill story-review --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From worldwonderer/oh-story-claudecode, a repository with 5,024 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going