Skip to content
Back to search

fanqie-novel-skill

番茄小说专用长篇写作系统。融合番茄平台规则 + AI去味专项检查 + 商业审查。适用于在番茄小说平台进行长篇网文创作,支持120万字以上长线运营。

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/304769384-png--fanqie-novel-skill/badge.svg)](/listings/304769384-png--fanqie-novel-skill)

HTML

<a href="/listings/304769384-png--fanqie-novel-skill"><img src="/api/listings/304769384-png--fanqie-novel-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Prerequisites

- AI coding assistant with skill support (e.g., Claude Code, Cursor) - Fanqie (Tomato) Novel Platform account

Installation

1. Download or clone this repository 2. Place the skill folder in your assistant's skill directory 3. Initialize a new novel project using the provided templates

Project Structure

After initialization, your novel project contains:

your-novel/
├── story_bible.md          # World-building, settings, power system
├── book_rules.md           # Platform rules + protagonist lock + taboos
├── outline.md              # Volume outlines, chapter goals, payoff plans
├── current_state.md        # Current world state (most important!)
├── pending_hooks.md        # Foreshadowing & suspense tracking
├── handoff_current.md      # Session handoff file (living document)
├── progress_tracker.md     # Progress + rhythm quality dashboard
├── pattern_detection.md    # Narrative pattern tracking
├── chapter_summaries.md     # Per-chapter summaries
├── character_matrix.md     # Character relationships & knowledge boundaries
├── style_guide.md          # Style guide (with AI de-flavoring rules)
└── chapters/
    └── ch001.md

Per-Chapter Workflow

BEFORE writing (5 mandatory):
  ├─ Read current_state.md → Confirm location/time/status
  ├─ Read outline.md → Confirm chapter goal, word count, is-climax
  ├─ Read pending_hooks.md → Check unresolved foreshadowing
  ├─ Check battle-scene-guide.md → If combat chapter, load checklist
  └─ Check dialogue-monitor.md → Confirm dialogue ratio trend

AFTER writing (8 mandatory):
  ├─ 1. Word count check (2000-2500)
  ├─ 2. AI de-flavoring (smart replace)
  ├─ 3. Causal chain check
  ├─ 4. Behavior-rule consistency
  ├─ 5. Timeline continuity
  ├─ 6. Battle scene check (combat chapters)
  ├─ 7. Dialogue ratio check (≤40%)
  └─ 8. Talk-therapy detection (bosses can't be talked down)

STATE UPDATE (mandatory):
  ├─ current_state.md
  ├─ pending_hooks.md
  ├─ handoff_current.md
  ├─ progress_tracker.md
  └─ pattern_detection.md

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 348 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ---
  2. name: fanqie-novel-skill
  3. description: 番茄小说专用长篇写作系统。融合番茄平台规则 + AI去味专项检查 + 商业审查。适用于在番茄小说平台进行长篇网文创作,支持120万字以上长线运营。
  4. ---
  5. # 番茄小说写作 Skill(Fanqie Novel Skill)
  6. 版本:**2.0.1** | 作者:**Jayce**
  7. **专为番茄小说平台打造的长篇网文写作系统。**
  8. ---
  9. ## v2.0.1 更新说明
  10. 本版本基于大量长篇网文实战创作与深度质量审阅的经验总结,进行重大架构升级。
  11. ### 核心问题回顾
  12. 长篇网文创作中反复出现的典型质量问题:
  13. | 问题 | 表现 | 严重程度 |
  14. |------|------|---------|
  15. | "话疗"泛滥 | 大量章节含说服类关键词,多个BOSS被对话解决 | 致命 |
  16. | 战斗描写崩溃 | 后期战斗场景几乎消失,意象重复率极高 | 致命 |
  17. | 对话占比失控 | 对话占比随篇幅推进持续飙升 | 严重 |
  18. | 节奏控制失败 | 篇幅超出故事承载力,后期注水严重 | 严重 |
  19. | 循环模式重复 | "觉醒-升级-新敌人"等固定模式无变化重复 | 中等 |
  20. | 反派降智 | 终极BOSS逻辑崩塌,轻易被说服 | 致命 |
  21. ### v2.0.1 核心改进
  22. | 改进项 | v1.1.1 | v2.0.1 |
  23. |--------|--------|--------|
  24. | 战斗场景 | 无专项检查 | 新增维度30"战斗场景审计"+战斗描写指南 |
  25. | 对话占比 | 无监控 | 新增维度31"对话占比监控",上限40% |
  26. | "话疗"检测 | 无 | 新增维度32"话疗模式检测",BOSS禁止被说服 |
  27. | 循环模式 | 无检测 | 新增维度33"叙事循环检测" |
  28. | 节奏评估 | 仅字数追踪 | 新增节奏质量评估(高潮密度、冲突强度) |
  29. | 最小审计集 | 5项 | 扩展为8项(新增战斗、对话、话疗、循环) |
  30. ---
  31. ## 核心定位
  32. 本 Skill 解决**八个**核心问题:
  33. 1. **长篇不跑偏**:通过 Truth Files 系统维护世界观、角色、伏笔、状态
  34. 2. **番茄能签约**:内置番茄平台规则、商业审查、付费转化检查
  35. 3. **AI没味道**:智能 AI 去味检查(替换而非删除),避免被平台限流
  36. 4. **会话连续性**:通过 handoff_current.md 实现跨会话无缝衔接
  37. 5. **规划能落地**:进度追踪面板,实时监控字数/章节偏离
  38. 6. **战斗有张力**:战斗场景专项审计,杜绝"话疗"解决BOSS
  39. 7. **对话不注水**:对话占比监控,防止全章变成聊天记录
  40. 8. **节奏不崩塌**:高潮密度追踪,防止后期注水和循环重复
  41. ---
  42. ## 核心工作流
  43. ```
  44. init -> write-next -> draft -> ai-detox -> audit -> revise -> extract-state -> state-update -> handoff-update
  45. ```
  46. ### v2.0.1 工作流强化
  47. ```
  48. 写前(强制5项):
  49. |- 读取 current_state.md -> 确认地点/时间/状态
  50. |- 读取 outline.md -> 确认本章目标、字数、是否高潮章
  51. |- 读取 pending_hooks.md -> 确认待处理伏笔
  52. |- 检查 battle-scene-guide.md -> 如是战斗章,加载战斗描写清单
  53. |- 检查 dialogue-monitor.md -> 确认当前对话占比趋势
  54. 写后(强制8项 -- 最小审计集 v2.0.1):
  55. |- 1. 字数检查(2000-2500字)
  56. |- 2. AI去味(智能替换,非机械删除)
  57. |- 3. 因果链检查(维度29,无跳脱)
  58. |- 4. 行为-规则一致性检查(维度28)
  59. |- 5. 时间线检查(无黑洞)
  60. |- 6. 战斗场景检查(维度30,高潮章必查) [新增]
  61. |- 7. 对话占比检查(维度31,上限40%) [新增]
  62. |- 8. 话疗模式检查(维度32,BOSS禁止被说服) [新增]
  63. 状态更新(强制):
  64. |- current_state.md
  65. |- pending_hooks.md
  66. |- handoff_current.md
  67. |- progress_tracker.md
  68. |- pattern-detection.md [新增,循环模式追踪]
  69. ```
  70. ---
  71. ## 项目结构
  72. 初始化后的番茄小说项目包含以下文件:
  73. ### 核心文件(必维护)
  74. | 文件 | 用途 | 更新频率 |
  75. |------|------|---------|
  76. | `story_bible.md` | 世界观、设定、势力、力量体系 | 新设定出现时 |
  77. | `book_rules.md` | 番茄平台规则 + 主角锁定 + 禁忌 | 项目开始时 |
  78. | `outline.md` | 分卷大纲、章节目标、payoff计划 | 每卷结束时回顾 |
  79. | `current_state.md` | 当前世界状态(最重要) | 每章更新 |
  80. | `pending_hooks.md` | 伏笔追踪、悬念管理 | 每章更新 |
  81. | `handoff_current.md` | 会话交接文件(活的文件) | 每章更新 |
  82. | `progress_tracker.md` | 进度追踪面板 | 每章更新 |
  83. | `pattern-detection.md` | 循环模式检测面板(v2.0.1新增) | 每5章更新 |
  84. ### 支撑文件(建议维护)
  85. | 文件 | 用途 |
  86. |------|------|
  87. | `chapter_summaries.md` | 每章摘要和状态变化 |
  88. | `character_matrix.md` | 角色关系、信任/冲突、信息边界 |
  89. | `character_knowledge.md` | POV管理、角色知识边界 |
  90. | `emotional_arcs.md` | 情感弧线追踪 |
  91. | `subplot_board.md` | 支线进度管理 |
  92. | `continuity_issues.md` | 已知问题追踪 |
  93. ### 风格文件
  94. | 文件 | 用途 |
  95. |------|------|
  96. | `style_guide.md` | 风格指南(含AI去味规则) |
  97. | `style_profile.json` | 量化风格统计 |
  98. ---
  99. ## 最小审计集(v2.0.1 核心改进)
  100. 每章写完后**必须执行**以下8项检查,不可跳过:
  101. ### 检查1-5:继承自 v1.1.1
  102. 详见 v1.1.1 文档。
  103. ### 检查6:战斗场景检查(维度30,v2.0.1新增)
  104. ```
  105. 触发条件:
  106. - 章节标题含"战斗/决战/对抗/最终/击杀"等关键词
  107. - outline.md 标记为"高潮章"
  108. - 本章出现BOSS级敌人
  109. 检查项:
  110. 1. 是否有实质性攻击/防御动作?(至少3次)
  111. 2. 是否通过"说服/理解/感化"解决冲突? -> 禁止!
  112. 3. 战斗意象是否重复?
  113. 4. 是否有战术博弈?(而非纯力量对轰)
  114. 5. 是否有代价/牺牲?
  115. 评级标准:
  116. PASS 优秀:有战术、有代价、意象丰富
  117. WARN 及格:有战斗但模式化
  118. FAIL 不合格:无战斗或"话疗"解决
  119. ```
  120. 详见:`references/battle-scene-guide.md`
  121. ### 检查7:对话占比检查(维度31,v2.0.1新增)
  122. ```
  123. 计算方法:
  124. 对话行数 = 统计引号内内容行数
  125. 总行数 = 章节总行数
  126. 对话占比 = 对话行数 / 总行数
  127. 标准:
  128. PASS 优秀:<= 25%(氛围/叙事为主)
  129. PASS 良好:26-35%(平衡得当)
  130. WARN 偏高:36-40%(需关注)
  131. FAIL 超标:> 40%(必须压缩对话)
  132. 趋势监控:
  133. - 记录每章对话占比
  134. - 若连续3章占比上升 -> 预警
  135. - 若占比 > 50% -> 立即报警
  136. ```
  137. 详见:`references/dialogue-monitor.md`
  138. ### 检查8:话疗模式检查(维度32,v2.0.1新增)
  139. ```
  140. 检测关键词:
  141. - "我理解你"
  142. - "说服"/"感化"/"唤醒"
  143. - "不是消灭,是救赎"
  144. - "融入"/"共存"/"和解"
  145. - BOSS被对话解决(三句话内放弃抵抗)
  146. 检查规则:
  147. 1. 普通敌人:可通过对话解决(限1次/卷)
  148. 2. 精英敌人:对话解决需铺垫3章+
  149. 3. BOSS级敌人:禁止通过对话解决!必须战斗!
  150. ```
  151. ### 检查9:循环模式检查(维度33,每5章执行)
  152. ```
  153. 检测模式:
  154. 1. "遇到新敌人 -> 发现苦衷 -> 对话解决 -> 获得力量"是否重复?
  155. 2. 连续3个章节结构是否高度相似?
  156. 3. 高潮章是否真的有高潮?
  157. 预警规则:
  158. - 同模式出现2次 -> WARN 提醒
  159. - 同模式出现3次+ -> FAIL 报警,要求变化
  160. ```
  161. 详见:`references/pattern-detection.md`
  162. ---
  163. ## 进度追踪面板(v2.0.1升级)
  164. ### 新增:节奏质量评估
  165. ```
  166. 高潮密度:
  167. 高潮章数量 / 总章数
  168. 标准:>= 15%(每7章至少1个高潮)
  169. 冲突强度趋势:
  170. 统计每章冲突解决方式
  171. 战斗解决占比应 >= 对话解决占比
  172. 节奏曲线:
  173. 绘制章节质量曲线
  174. 检测是否"前高后低"崩塌
  175. ```
  176. 详见:`assets/project-template/progress_tracker.md`
  177. ---
  178. ## 会话连续性工作流
  179. ### 新会话启动流程
  180. ```
  181. 1. 用户请求继续写作
  182. 2. AI请求加载 handoff_current.md
  183. 3. 用户提供文件内容(或AI从项目文件夹读取)
  184. 4. AI确认加载成功,报告当前进度
  185. 5. 继续写作或审计
  186. ```
  187. ### 会话交接协议
  188. **AI启动时必须说**:
  189. > "请提供 handoff_current.md 文件内容,我将加载当前进度。"
  190. **加载成功后必须确认**:
  191. > "已加载 handoff_current.md,当前进度:ch{{N}},下一章:ch{{N+1}}。
  192. > 主角当前在[地点],持有[物品],待处理伏笔[X个]。
  193. > 总进度:{{actual}}字/{{target}}字({{percent}}%)。
  194. > 对话占比趋势:{{trend}}。上次高潮章:ch{{last_climax}}。"
  195. ---
  196. ## 番茄专用功能
  197. ### 1. 平台红线检查
  198. 详见:`references/fanqie-platform-rules.md`
  199. ### 2. 生死线检查
  200. 前三章必须通过,详见:`references/commercial-review.md`
  201. ### 3. AI去味专项检查
  202. 详见:`references/ai-detox-guide.md`
  203. ### 4. 商业审查
  204. 详见:`references/commercial-review.md`
  205. ### 5. 战斗场景指南(v2.0.1新增)
  206. 详见:`references/battle-scene-guide.md`
  207. ### 6. 对话占比监控(v2.0.1新增)
  208. 详见:`references/dialogue-monitor.md`
  209. ---
  210. ## 教训库(v2.0.1)
  211. > 以下是从大量长篇网文实战创作与深度审阅中总结的典型问题模式,必须在审计时特别关注。
  212. ### 问题1-8:继承自 v1.1.1
  213. (略,见 v1.1.1 文档)
  214. ### 问题9:战斗描写崩溃(v2.0.1新增,严重)
  215. - **表现**:中后期战斗场景逐渐消失,被大段对话取代
  216. - **根因**:无战斗场景专项检查,主题表达压过情节张力
  217. - **预防**:维度30强制检查,高潮章必须有实质性战斗描写
  218. ### 问题10:对话占比失控(v2.0.1新增,严重)
  219. - **表现**:对话占比随篇幅推进持续飙升,后期章节近乎对话体
  220. - **根因**:无对话占比监控,后期写作倾向用对话凑字数
  221. - **预防**:维度31持续监控,上限40%,超标必须压缩
  222. ### 问题11:"话疗"模式泛滥(v2.0.1新增,严重)
  223. - **表现**:多个重要敌人被对话/说服解决,缺乏正当战斗
  224. - **根因**:无"话疗"检测机制,主题表达滥用为万能解法
  225. - **预防**:维度32检测,BOSS级敌人禁止被说服
  226. ### 问题12:循环模式重复(v2.0.1新增,中等)
  227. - **表现**:固定叙事循环(如"觉醒-升级-新敌人")无变化反复出现
  228. - **根因**:无循环模式检测,写作陷入套路化
  229. - **预防**:维度33检测,同模式出现3次以上强制报警
  230. ### 问题13:反派降智(v2.0.1新增,严重)
  231. - **表现**:终极BOSS逻辑崩塌,轻易被主角说服或击败
  232. - **根因**:急于表达主题,牺牲反派行为逻辑与角色尊严
  233. - **预防**:BOSS必须有独立且自洽的逻辑体系,主角需找到逻辑漏洞而非简单"理解"
  234. ### 问题14:节奏崩塌(v2.0.1新增,严重)
  235. - **表现**:作品前半部质量稳定,后半部出现灾难性下滑
  236. - **根因**:无节奏质量评估机制,后期注水赶工
  237. - **预防**:节奏曲线持续监控,"前高后低"趋势及时报警
  238. ---
  239. ## 版本历史
  240. ### v2.0.1(2026-05-30)
  241. - **重大升级**:基于长篇实战经验与深度审阅的全面重构
  242. - **新增维度30**:战斗场景审计(高潮章必查)
  243. - **新增维度31**:对话占比监控(上限40%)
  244. - **新增维度32**:话疗模式检测(BOSS禁止被说服)
  245. - **新增维度33**:叙事循环检测(同模式3次+报警)
  246. - **新增文件**:battle-scene-guide.md、dialogue-monitor.md、pattern-detection.md
  247. - **最小审计集扩展**:5项 -> 8项
  248. - **进度追踪升级**:新增节奏质量评估、高潮密度、冲突强度趋势
  249. - **教训库扩展**:新增问题9-14
  250. ### v1.1.1(2026-05-14)
  251. - 新增:progress_tracker.md、维度29、最小审计集、智能替换表
  252. - 修复:规划执行脱节、AI去味破坏语义、情节跳脱无因果
  253. ### v1.1.0
  254. - 新增:handoff_current.md、维度28、教训库
  255. ### v1.0.0
  256. - 初始版本
README.md · README · 292 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <h1>🌱 Fanqie Novel Skill</h1>
  3. <p><strong>Production-Grade Writing System for Fanqie (Tomato) Novel Platform</strong></p>
  4. <p>
  5. <a href="#features">✨ Features</a> •
  6. <a href="#quick-start">🚀 Quick Start</a> •
  7. <a href="#architecture">🏗️ Architecture</a> •
  8. <a href="#changelog">📝 Changelog</a> •
  9. <a href="#license">📄 License</a>
  10. </p>
  11. </p>
  12. ---
  13. ## [中文介绍](#中文介绍) | [English](#english)
  14. ---
  15. <a id="中文介绍"></a>
  16. ## 🇨🇳 中文介绍
  17. ### 这是什么?
  18. Fanqie Novel Skill 是一个专为**番茄小说平台**设计的 AI 辅助长篇网文写作系统。它提供了一套完整的工作流,帮助你在番茄平台上创作出高质量、可签约、能变现的长篇小说。
  19. ### 为什么需要它?
  20. AI 辅助写作在番茄平台面临三大挑战:
  21. | 挑战 | 后果 | 本 Skill 的解决方案 |
  22. |------|------|-------------------|
  23. | AI 味被平台限流 | 作品被降权或下架 | 智能去味系统(替换而非删除) |
  24. | 长篇规划执行脱节 | 规划 120 万字实际只写 70 万 | 进度追踪面板 + 预警系统 |
  25. | 审计维度太多导致空转 | 28 个维度一个都不执行 | 最小审计集(8 项强制) |
  26. | 后期质量崩塌 | 前期精彩后期注水 | 节奏质量评估 + 循环模式检测 |
  27. | "话疗"解决冲突 | BOSS 被三句话说服 | 战斗场景审计 + 话疗模式检测 |
  28. ### 核心特性
  29. - **🛡️ AI 去味系统** — 智能替换表,语义完整性优先,避免机械删除
  30. - **📊 进度追踪面板** — 实时监控字数/章节偏离,预警规则自动触发
  31. - **🔍 最小审计集(8 项强制)** — 每章必查,不执行不通过
  32. - **⚔️ 战斗场景审计** — 杜绝"话疗"解决 BOSS,确保战斗有张力
  33. - **💬 对话占比监控** — 上限 40%,防止全章变成聊天记录
  34. - **🔄 循环模式检测** — 检测叙事模式重复,保持新鲜感
  35. - **📈 节奏质量评估** — 高潮密度、冲突强度趋势、节奏曲线
  36. - **🔗 会话连续性** — 跨会话无缝衔接,支持超长篇创作
  37. ### 工作流
  38. ```
  39. 初始化 → 读取状态 → 写作 → AI去味 → 审计 → 修订 → 状态更新 → 会话交接
  40. ```
  41. 每章写作前后都有强制检查点,确保质量不滑坡。
  42. ---
  43. <a id="english"></a>
  44. ## 🇺🇸 English
  45. ### What is this?
  46. Fanqie Novel Skill is a production-grade AI-assisted writing system designed specifically for the **Fanqie (Tomato) Novel Platform**. It provides a complete workflow for creating high-quality, publishable long-form web novels.
  47. ### Why do you need it?
  48. AI-assisted writing on the Fanqie platform faces critical challenges:
  49. | Challenge | Consequence | Solution |
  50. |-----------|-------------|----------|
  51. | AI-flavored text gets throttled | Works get deprioritized or removed | Smart de-flavoring system (replace, don't delete) |
  52. | Long-form planning drift | Plan 1.2M words, deliver 700K | Progress tracking dashboard + alerts |
  53. | Too many audit dimensions = none executed | 28 dimensions, zero compliance | Minimum audit set (8 mandatory checks) |
  54. | Quality collapse in later chapters | Strong start, weak finish | Rhythm quality assessment + pattern detection |
  55. | Conflicts resolved by "talking therapy" | Boss defeated by 3 sentences | Battle scene audit + talk-therapy detection |
  56. ### Core Features
  57. - **🛡️ AI De-flavoring** — Smart replacement table, semantic integrity first
  58. - **📊 Progress Tracking** — Real-time word/chapter monitoring with auto-alerts
  59. - **🔍 Minimum Audit Set** — 8 mandatory checks per chapter
  60. - **⚔️ Battle Scene Audit** — No "talk-therapy" boss defeats, ensure combat tension
  61. - **💬 Dialogue Ratio Monitor** — 40% cap, prevent chapters becoming chat logs
  62. - **🔄 Pattern Detection** — Detect narrative loop repetition, maintain freshness
  63. - **📈 Rhythm Quality Assessment** — Climax density, conflict intensity trends
  64. - **🔗 Session Continuity** — Seamless cross-session handoff for ultra-long novels
  65. ### Workflow
  66. ```
  67. Init → Read State → Write → De-flavor → Audit → Revise → State Update → Handoff
  68. ```
  69. Mandatory checkpoints before and after each chapter ensure consistent quality.
  70. ---
  71. ## Features
  72. ### 🛡️ AI De-flavoring System
  73. Not just a banned-word list. A smart replacement engine that:
  74. - **Replaces, not deletes** — Preserves metaphors and figurative language
  75. - **Context-aware** — Allows banned words in dialogue (characters can sound AI-like, narration can't)
  76. - **Semantic verification** — Post-replacement read-aloud test
  77. - **9-word smart replacement table** with context-specific alternatives
  78. ### 📊 Progress Tracking Dashboard
  79. - Total/volume/chapter progress tracking
  80. - **Rhythm quality metrics** (v2.0): climax density, conflict intensity trends, quality curve
  81. - **12 auto-alert rules**: word count deviation, dialogue overflow, pattern repetition, quality collapse
  82. - Quality scoring system (per-chapter + full-book)
  83. ### 🔍 Minimum Audit Set (8 Mandatory Checks)
  84. | # | Check | Frequency |
  85. |---|-------|-----------|
  86. | 1 | Word count (2000-2500) | Every chapter |
  87. | 2 | AI de-flavoring | Every chapter |
  88. | 3 | Causal chain | Every chapter |
  89. | 4 | Behavior-rule consistency | Every chapter |
  90. | 5 | Timeline continuity | Every chapter |
  91. | 6 | Battle scene quality | Combat chapters |
  92. | 7 | Dialogue ratio (≤40%) | Every chapter |
  93. | 8 | Talk-therapy detection | Every chapter |
  94. Plus: **Pattern detection** every 5 chapters, **Full audit** (33 dimensions) every 10 chapters.
  95. ### ⚔️ Battle Scene System (v2.0)
  96. - **Boss battles must be fought, not talked through**
  97. - Combat checklist: ≥3 attack actions, tactical gameplay, cost/sacrifice
  98. - Battle imagery diversity check (prevent "golden light" repetition)
  99. - Full battle scene writing guide with templates
  100. ### 🔄 Pattern Detection (v2.0)
  101. - Detects narrative loop repetition (same pattern 3+ times = alert)
  102. - Chapter structure similarity analysis
  103. - Climax chapter authenticity verification
  104. ---
  105. ## Quick Start
  106. ### Prerequisites
  107. - AI coding assistant with skill support (e.g., Claude Code, Cursor)
  108. - Fanqie (Tomato) Novel Platform account
  109. ### Installation
  110. 1. Download or clone this repository
  111. 2. Place the skill folder in your assistant's skill directory
  112. 3. Initialize a new novel project using the provided templates
  113. ### Project Structure
  114. After initialization, your novel project contains:
  115. ```
  116. your-novel/
  117. ├── story_bible.md # World-building, settings, power system
  118. ├── book_rules.md # Platform rules + protagonist lock + taboos
  119. ├── outline.md # Volume outlines, chapter goals, payoff plans
  120. ├── current_state.md # Current world state (most important!)
  121. ├── pending_hooks.md # Foreshadowing & suspense tracking
  122. ├── handoff_current.md # Session handoff file (living document)
  123. ├── progress_tracker.md # Progress + rhythm quality dashboard
  124. ├── pattern_detection.md # Narrative pattern tracking
  125. ├── chapter_summaries.md # Per-chapter summaries
  126. ├── character_matrix.md # Character relationships & knowledge boundaries
  127. ├── style_guide.md # Style guide (with AI de-flavoring rules)
  128. └── chapters/
  129. └── ch001.md
  130. ```
  131. ### Per-Chapter Workflow
  132. ```
  133. BEFORE writing (5 mandatory):
  134. ├─ Read current_state.md → Confirm location/time/status
  135. ├─ Read outline.md → Confirm chapter goal, word count, is-climax
  136. ├─ Read pending_hooks.md → Check unresolved foreshadowing
  137. ├─ Check battle-scene-guide.md → If combat chapter, load checklist
  138. └─ Check dialogue-monitor.md → Confirm dialogue ratio trend
  139. AFTER writing (8 mandatory):
  140. ├─ 1. Word count check (2000-2500)
  141. ├─ 2. AI de-flavoring (smart replace)
  142. ├─ 3. Causal chain check
  143. ├─ 4. Behavior-rule consistency
  144. ├─ 5. Timeline continuity
  145. ├─ 6. Battle scene check (combat chapters)
  146. ├─ 7. Dialogue ratio check (≤40%)
  147. └─ 8. Talk-therapy detection (bosses can't be talked down)
  148. STATE UPDATE (mandatory):
  149. ├─ current_state.md
  150. ├─ pending_hooks.md
  151. ├─ handoff_current.md
  152. ├─ progress_tracker.md
  153. └─ pattern_detection.md
  154. ```
  155. ---
  156. ## Architecture
  157. ### File Organization
  158. ```
  159. fanqie-novel-skill/
  160. ├── SKILL.md # Main skill definition
  161. ├── README.md # This file
  162. ├── CHANGELOG.md # Version history
  163. ├── VERSION # Current version
  164. ├── assets/
  165. │ └── project-template/ # Novel project templates
  166. │ ├── story_bible.md
  167. │ ├── book_rules.md
  168. │ ├── outline.md
  169. │ ├── current_state.md
  170. │ ├── pending_hooks.md
  171. │ ├── handoff_current.md
  172. │ ├── progress_tracker.md
  173. │ └── ...
  174. ├── examples/
  175. │ └── demo-novel/ # Example novel project
  176. └── references/ # Reference guides
  177. ├── ai-detox-guide.md # AI de-flavoring guide
  178. ├── audit-dimensions.md # 33 audit dimensions
  179. ├── battle-scene-guide.md # Battle writing guide
  180. ├── dialogue-monitor.md # Dialogue ratio monitoring
  181. ├── pattern-detection.md # Narrative pattern detection
  182. ├── commercial-review.md # Commercial viability checks
  183. └── fanqie-platform-rules.md # Platform rules & red lines
  184. ```
  185. ### Audit Dimensions (33 Total)
  186. | Category | Dimensions | Key Focus |
  187. |----------|:---:|-----------|
  188. | Minimum Set (Mandatory) | 8 | Word count, AI flavor, causality, timeline, battle, dialogue, talk-therapy |
  189. | Core | 10 | Character consistency, timeline, world-building, logic, pacing |
  190. | Style & Anti-formula | 6 | Repetition, show-don't-tell, AI transitions |
  191. | Structure | 4 | Outline drift, subplot stagnation, payoff |
  192. | Fanqie-specific | 5 | Platform red lines, golden 3 chapters, commercial checks |
  193. ---
  194. ## Changelog
  195. See [CHANGELOG.md](CHANGELOG.md) for detailed version history.
  196. ### Highlights
  197. - **v2.0.1** — Major upgrade: battle scene audit, dialogue monitoring, talk-therapy detection, pattern detection, rhythm quality assessment
  198. - **v1.1.1** — Progress tracking, causal chain check, minimum audit set, smart AI de-flavoring
  199. - **v1.1.0** — Session handoff, behavior-rule consistency
  200. - **v1.0.0** — Initial release
  201. ---
  202. ## Contributing
  203. Contributions are welcome! Please feel free to submit a Pull Request.
  204. 1. Fork the repository
  205. 2. Create your feature branch (`git checkout -b feature/amazing-feature`)
  206. 3. Commit your changes (`git commit -m 'Add amazing feature'`)
  207. 4. Push to the branch (`git push origin feature/amazing-feature`)
  208. 5. Open a Pull Request
  209. ---
  210. ## License
  211. This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
  212. ---
  213. ## Author
  214. **Jayce** — Web novel enthusiast & AI writing system designer
  215. <p align="center">
  216. If you find this skill helpful, please consider giving it a ⭐ on GitHub!
  217. </p>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.