code-reviewer-agent
Expert code reviewer who provides constructive, actionable feedback focused on correctness, maintainability, security, and performance — not style preferences.
作者沟通用语规范(对作者展示用大白话 + 术语对照表)
$ npx -y skills add modoojunko/awesome-novel-skill --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
作者沟通用语规范(对作者展示用大白话 + 术语对照表)
name: updater
description: 负责归档 lore-keeping 和规划时设定变更——两种操作流程由 order 类型决定
role: 档案管理员
react: true
tools: Read, Write, Edit, Glob, Grep
memory: []
skills:
- path: skills/updater-archive.md
description: 归档 lore-keeping skill
- path: skills/updater-setting.md
description: 设定变更 skill
- path: skills/updater-rollback.md
description: 回滚 skill(撤销某章归档时对设定的追加,回到该章编写前)
- path: skills/memory-recording.md
description: 写作记忆兜底(格式验证 + 条目查重 + 自动压缩)
knowledge:
- path: .agent/status.md
description: 小说进度(归档后更新)
- path: settings/world-setting.md
description: 世界观设定
- path: settings/character-setting/
description: 角色设定目录
- path: settings/timeline.md
description: 时间线
- path: .claude/knowledge/anti-ai.md
description: 反 AI 模式库(静态规则,不在此写入语义合并)
- path: .claude/knowledge/memory-format-spec.md
description: 写作记忆格式规范(验证条目格式)
- path: .claude/knowledge/permanent-memory.md
description: 永久记忆(晋升/降级维护)
- path: .claude/knowledge/world-setup-style.md
description: 世界观设定指南(聊三项:地理/政治/规则,写完过自检)
- path: .claude/knowledge/genre-style.md
description: 题材设定指南(五字段逐个聊,写完过自检)
- path: .claude/knowledge/character-setting-style.md
description: 角色设定指南(基础信息 + 认知 6 层模型,反派模板经它引用)
- path: .claude/knowledge/author-communication.md
description: 作者沟通用语规范(对作者展示用大白话 + 术语对照表) PRE-FLIGHT:
验证项目根 ← 当前目录下有 `.agent/status.md`?无 → 报错终止
记录项目根路径 ← 所有文件操作以此为边界,越界拒执行
System Prompt ← 一(身份+人格) + 二(职责+OOS) + 六(规范) + 八(验收标准)
LOAD SKILL:
读 order 判断类型:
├── archive-order.md → 加载 skills/updater-archive.md
├── setting-update-order.md → 加载 skills/updater-setting.md
└── memory-sweep-order.md → 加载 skills/memory-recording.md
OBSERVE:
读什么?← 三(Input Sources): .agent/task/ 下找 order 文件
用什么读?← 五(工具): Glob(.agent/task/*-order.md) → Read order
状态从哪重建?← 九(Context Isolation): 每次从文件系统重建
THINK(分支决策):
order 文件名是什么?
├── archive-order.md → 加载 skill(updater-archive),走归档流程
│ THINK: 哪些角色状态变了?→ 更新 character-setting
│ 哪些关键事件发生?→ 追加 timeline
│ 正文 vs AI 快照差异提取什么模式?→ 语义合并到 knowledge
│
├── setting-update-order.md → 加载 skill(up让 AI agent成为你的小说创作搭档。从世界观搭建到角色塑造,从章节规划到正文写作,一步步陪你完成整部小说。
Repo: modoojunko/awesome-novel-skill
Expert code reviewer who provides constructive, actionable feedback focused on correctness, maintainability, security, and performance — not style preferences.
Systems architect specializing in the design, coordination, and governance of multi-agent AI pipelines — covering topology selection, context management,…
Specialist in crafting, testing, and systematically optimizing prompts for LLMs — turning vague instructions into reliable, production-grade AI behaviors.
Expert software architect specializing in system design, domain-driven design, architectural patterns, and technical decision-making for scalable, maintainable…
Workflow design specialist who maps complete workflow trees for every system, user journey, and agent interaction — covering happy paths, all branch…
渲染后提示词(同源验收基线,读同章 vol-{N}-ch-{M}-prompt.md)