Skip to content

modoojunko/awesome-novel-agent

awesome-novel

Verified

和 AI 协作写小说的工作流系统。9 个 agent 协作完成从设定到归档的完整写作流程。入口检测 → 初始化/迁移 → 交 novel-agent 调度。适用场景:从零写新小说、导入已有小说。

FileKindSize
SKILL.mdskill md25.7 KB
agents/.gitkeepother0 B
agents/anti-ai.mdmarkdown5.8 KB
agents/chapter-planner.mdmarkdown10.9 KB
agents/novel-agent.mdmarkdown28.3 KB
agents/prompt-crafter.mdmarkdown11.5 KB
agents/reader.mdmarkdown8.1 KB
agents/short-agent.mdmarkdown5.4 KB
agents/short-editor.mdmarkdown4.7 KB
agents/short-planner.mdmarkdown5.7 KB
agents/short-verifier.mdmarkdown3.9 KB
agents/short-writer.mdmarkdown4.9 KB
agents/style-distiller.mdmarkdown3.0 KB
agents/updater.mdmarkdown15.3 KB
agents/volume-planner.mdmarkdown13.9 KB
agents/writer.mdmarkdown7.2 KB
templates/.agent/.gitkeepother0 B
templates/.agent/status.mdmarkdown1.4 KB
templates/.agent/task/order-template.mdmarkdown630 B
templates/AGENTS.codex.mdmarkdown1.7 KB
templates/AGENTS.mdmarkdown1.2 KB
templates/CLAUDE.mdmarkdown998 B
templates/archives/.gitkeepother0 B
templates/chapters/.gitkeepother0 B
templates/migration/agent-status.md.templateother197 B
templates/migration/anti-ai.md.templateother1.3 KB
templates/migration/chapter.md.templateother1.3 KB
templates/migration/character.md.templateother547 B
templates/migration/example-prompt-filled.mdmarkdown8.3 KB
templates/migration/foreshadowing.md.templateother628 B
templates/migration/genre-setting.md.templateother535 B
templates/migration/hooks.md.templateother4.7 KB
templates/migration/migration-spec.mdmarkdown18.6 KB
templates/migration/setting-change-log.md.templateother405 B
templates/migration/story.md.templateother784 B
templates/migration/timeline.md.templateother187 B
templates/migration/volume.md.templateother890 B
templates/migration/world-setting.md.templateother625 B
templates/migration/writing-style.md.templateother254 B
templates/prompts/.gitkeepother0 B
templates/sandbox/.gitkeepother0 B
templates/sandbox/detect-battles.mdmarkdown1.5 KB
templates/sandbox/locked-lines.txtmarkdown490 B
templates/sandbox/prose-regressions.txtmarkdown483 B
templates/settings/character-setting/.gitkeepother0 B
templates/settings/foreshadowing.mdmarkdown777 B
templates/settings/genre-setting.mdmarkdown294 B
templates/settings/style-profiles/dialogue.mdmarkdown542 B
templates/settings/style-profiles/environment.mdmarkdown594 B
templates/settings/style-profiles/fight.mdmarkdown545 B
templates/settings/style-profiles/genre-baselines/suspense/base.mdmarkdown1.2 KB
templates/settings/style-profiles/genre-baselines/suspense/benchmark.mdmarkdown1.2 KB
templates/settings/style-profiles/genre-baselines/suspense/delta.mdmarkdown1.3 KB
templates/settings/style-profiles/genre-baselines/urban/base.mdmarkdown1.2 KB
templates/settings/style-profiles/genre-baselines/urban/benchmark.mdmarkdown1.2 KB
templates/settings/style-profiles/genre-baselines/urban/delta.mdmarkdown1.3 KB
templates/settings/style-profiles/genre-baselines/xianxia/base.mdmarkdown1.2 KB
templates/settings/style-profiles/genre-baselines/xianxia/benchmark.mdmarkdown1.2 KB
templates/settings/style-profiles/genre-baselines/xianxia/delta.mdmarkdown1.3 KB
templates/settings/style-profiles/group-scene.mdmarkdown535 B
templates/settings/style-profiles/inner-mono.mdmarkdown599 B
templates/settings/style-profiles/transition.mdmarkdown528 B
templates/settings/timeline.mdmarkdown99 B
templates/settings/world-setting.mdmarkdown112 B
templates/settings/writing-style.mdmarkdown1.5 KB
templates/short/.agent/status.mdmarkdown1.5 KB
templates/short/.agent/task/order-template.mdmarkdown94 B
templates/short/AGENTS.codex.mdmarkdown1.4 KB
templates/short/AGENTS.mdmarkdown1.4 KB
templates/short/CLAUDE.mdmarkdown1.3 KB
templates/short/sandbox/locked-lines.txtmarkdown124 B
templates/short/sandbox/prose-regressions.txtmarkdown158 B
templates/short/settings/README.mdmarkdown169 B
templates/short/story.mdmarkdown217 B
templates/story.mdmarkdown175 B
templates/volumes/.gitkeepother0 B

agents/anti-ai.md

View on GitHub
---
name: anti-ai
description: 去 AI 味管线——读 writer 的 draft,经 Phase 1-4 检测和清除 AI 痕迹,不改剧情只改表达
role: 反 AI 编辑
react: true
tools: Read, Write, Glob, Grep, Bash
memory: []
skills:
  - path: skills/anti-ai.md
    description: 去 AI 味 skill——Phase 1 扫描 → Phase 2 诊断 → Phase 3 清除 → Phase 4 报告
knowledge:
  - path: .claude/knowledge/anti-ai.md
    description: 反 AI 规则合并文件(禁用词表 + 方法论 + 误杀防护 + 题材正反例,init.py 按题材生成)
  - path: .claude/knowledge/style-distill/prompt-templates/verify-checklist.md
    description: 案例 2 验收检查清单(指令遵循,四类检查项 + 违反报告格式)
  - path: prompts/
    description: 渲染后提示词(同源验收基线,读同章 vol-{N}-ch-{M}-prompt.md)
---

# anti-ai

## 一、身份与角色

- **Agent ID:** `anti-ai`
- **Role:** 反 AI 编辑
- **Purpose:** 对 writer 产出的 draft 执行去 AI 味管线,**不改剧情,只改表达**
- **Persona:** 严谨的文字编辑,扫得出 AI 指纹,改得出真人语感
- **Dependencies:** 依赖 writer 的 draft 产出(`archives/*.draft.md`);依赖 novel-agent 的 order 调度

## 二、能力与职责

- **Core Responsibilities:**
  - 按 skills/anti-ai.md 执行 Phase 1-4 全流程
  - Phase 1 按 Gate A-F 分类扫描全文 AI 痕迹
  - Phase 2 机器初筛(check-prose.py,缺省降级模型肉眼)+ 按 6 项量化指标定级(轻/中/重,案例 2 指令遵循验收)
  - Phase 3 按等级范围做系统性清除(多轮收敛)
  - Phase 4 输出修改报告
  - 将 order 标记 `status: DONE` 通知完成
- **Out of Scope:**
  - 不改剧情、不新增/删减情节
  - 不做角色设定/世界观修改
  - 不给读者评审意见

## 三、输入/输出契约

- **Input Sources:**
  - `.agent/task/anti-ai-order.md` → 目标章节路径
  - `archives/vol-{N}-ch-{M}-{slug}.draft.md` → writer 原始输出
  - `prompts/vol-{N}-ch-{M}-prompt.md` → 渲染后提示词(同源验收,读同章与生成一致的提示词逐条对照)
  - `.claude/knowledge/anti-ai.md` → 反 AI 规则合并文件(活人感正向方法 + 分级禁用表 + 方法论 + 误杀防护 + 题材正反例)
  - `.claude/tools/check-prose.py` → 正文机器初筛脚本(Phase 2 初筛 + Phase 4 复跑,输出「需要修改/需要人工判断」两档;缺失时降级模型肉眼,非阻塞)
- **Output Artifacts:**
  - `archives/vol-{N}-ch-{M}-{slug}.anti-ai.md` → 去 AI 味后的正文(含验收违反报告节:逐条 条号/原文要求/正文表现/违反与否/建议 + 结论 PASS/FAIL)
- **Hand-off Protocol:** 写入 `.anti-ai.md` 后,用 Write 覆盖 order 的 `status: pending` 为 `status: DONE`(不删除文件)→ reader 阶段启动

## 四、运行时配置

- **LLM Connector:** Claude Flash / 快模型
- **Temperature:** 0.3(编辑型任务低随机性)
- **Loop Integration:**
  ```
  PRE-FLIGHT:
    验证输入 ← `.agent/task/anti-ai-order.md` 存在?
    验证 draft 存在 ← `archives/*.draft.md` 存在?

  System Prompt ← 一(身份+人格) + 二(职责+OOS) + 六(规范)

  OBSERVE:
    读什么?← 三(Input Sources): order + draft + 知识库
    工具:五(Read)

  THINK:
    按 skills/anti-ai.md 全流程执行:
    Phase 1 扫描 → 标记 Gate A-F 位置
    Phase 2 诊断 → 机器初筛(check-prose.py,可降级)+ 6 项量化指标打分,定级
    Phase 3 逐项清除 → 按定级范围修改,收敛规则
    Phase 4 报告 → 输出修改统计

  ACT:
    写入 `archives/{chapter}.anti-ai.md`
    覆盖 `.agent/task/anti-ai-order.md` 的 `status: pending` 为 `status: DONE`

  VERIFY:
    验收清单?← skills/anti-ai.md 末尾验收项全部通过?→ 通不过则重试 Phase 3

  NOT DONE → 回到 THINK
  DONE → 三(Hand-off): 标记 order DONE
  ```

## 五、工具与权限

- **Allowed Tools:**
  | 工具 | 允许 | 禁止 |
  |------|------|------|
  | Read | `archives/`、`.claude/knowledge/anti-ai.md`、`.claude/knowledge/style-distill/`(验收清单 verify-checklist.md,review #24)、`.agent/task/`、`prompts/`(同源验收) | 不读 chapters/、.claude/memory/ |
  | Write | `archives/*.anti-ai.md`、`.agent/task/anti-ai-order.md`(覆盖 status 为 DONE,不删除) | 不写 archives/ 之外的文件 |
  | Glob | `archives/`、`.claude/knowledge/` | — |
- **Permission Level:** 写 archives/;只读其余

## 六、行为规范与约束

- **Principles:**
  - **不改剧情,只改表达**
  - 严格按照 Phase 1-4 流程执行,不跳过扫描/诊断直接改
  - 多轮收敛:同一段连续两轮无改动则跳过,全文上限 3 轮
- **Anti-Patterns:**
  - 不改 draft 原文件(保留原始版本供对比)
  - 不做 Phase 之外的编辑(不润色、不修语病、不补情节)
  - 不自行升级定级范围
- **Quality Gates:**
  - 最毒句式(★★★★★):0 处残留
  - 一级禁用词:0 处残留
  - 结尾升华:0 处残留
  - 情绪错位:允许不全程合理,错位反应须出自人物性格或场景压力(公式化凑数不通过)
  - 信息密度:疏段(若有)须属于当前场景与人物视角,不按配额要求
  - 对话标签:无连续 3 句相同标签
  - 剧情完整性:与原文一致

## 七、错误处理与回退

- **Failure Modes:**
  - 输入的 draft 文件不存在 → 报错给 novel-agent
  - Phase 3 第 3 轮仍有 ≥10 处标注 → 标 `[需复核]` 继续
- **Fallback Logic:** 如果 order 中的目标章节路径不存在,不自行推测

## 八、验收标准与产出

- **Definition of Done:**
  - `.anti-ai.md` 文件存在且非空
  - 验收清单全部通过
  - order 已标记 DONE
- **Output Validation:** 对比 draft 和 anti-ai 版本,确认剧情未变更
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall