tanson515

Fanfic Writer

Contentv2.1.0
By tanson515Updated 2026-05-174 versions · latest released 2026-02-15fanfic-writer@clawhub_tanson515/fanfic-writer
Article Writing#小说写作

According to AlphaMoat, as of 2026-10, Fanfic Writer has 8,729 downloads and 5 stars — ranked by downloads #3,184 among 10,914 AI skills in this ranking, and #316 of 927 in Content.

The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.

Downloads
8.7K
Stars
5
Overall download rank
#3,184
Top 30% overall · Top 35% in Content
PlatformDownloadsStarsComments
ClawHub ↗2.5K2-
SkillHub ↗8.7K5—

Platforms count differently and update at different times.

What this skill does

It splits writing into a staged pipeline running from initialisation to final QC, and each stage waits for human confirmation before continuing. Characters, plot lines, timeline, props, locations, point-of-view rules and session memory sit in separate state panels, and every state change carries chapter, snippet and confidence evidence.

Profile published 2026-10-27

What you can do with it

  • Keep the settings and chapter state of a long novel in one place
  • Check for timeline or character conflicts before continuing a draft

When to use it

  • A long draft has grown inconsistent halfway through
  • Each step needs sign-off rather than a fully automatic run

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Set up the characters and timeline for this novel, then stop at the first stage for my confirmation
Check which plot threads from the last chapter are still unresolved

Monthly Trend

Downloads8.7K
1.4K5.3K9.3K2026-03 · Downloads 2.6K2026-05 · Downloads 3.5K2026-06 · Downloads 1.9K2026-07 · Downloads 4.1K2026-08 · Downloads 4.3K2026-09 · Downloads 5.0K2026-10 · Downloads 8.7K26-0326-0926-10
Stars5
2462026-03 · Stars 22026-05 · Stars 62026-06 · Stars 22026-07 · Stars 62026-08 · Stars 62026-09 · Stars 52026-10 · Stars 526-0326-0926-10

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-108.7K—5
2026-095.0K—5
2026-084.3K+4.8%6
2026-074.1K+113.3%6
2026-061.9K-44.8%2
2026-053.5K—6
2026-032.6K—2

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

6.8 KB · ClawHub v2.1.0
---
name: fanfic-writer
version: 2.1.0
description: 自动化小说写作助手 v2.1 - 基于证据的状态管理、多视角QC、原子I/O、每个阶段人工确认
homepage: https://github.com/openclaw/clawd
metadata:
  openclaw:
    emoji: "📖"
    category: "creative"
---
Show all (241 lines)
# Fanfic Writer v2.1 - 自动化小说写作系统 / Automated Novel Writing System

**版本 Version**: 2.1.0  
**架构 Architecture**: 基于证据的状态管理 with atomic I/O  
**安全机制 Safety**: Auto-Rescue, Auto-Abort Guardrail, FORCED 连击熔断  
**核心特性**: 每个阶段人工确认

---

## 系统概览 / System Overview

Fanfic Writer v2.1 是一套生产级的小说写作流水线,每个阶段都需要人工确认:

/ Fanfic Writer v2.1 is a production-grade novel writing pipeline with human confirmation at each phase:

- **9 阶段流水线 / 9 Phase Pipeline**: 从初始化到最终QC
- **7 状态面板 / 7 State Panels**: 角色、剧情线、时间线、道具、地点、POV规则、会话记忆
- **证据链 / Evidence Chain**: 所有状态变更带有 (章节, 片段, 置信度) 追踪
- **原子I/O / Atomic I/O**: temp → fsync → rename 模式 + 快照回滚
- **多视角QC / Multi-Perspective QC**: 3-评审协议 + 100分制评分
- **安全机制 / Safety Mechanisms**: Auto-Rescue, Auto-Abort
- **人工确认 / Human Confirmation**: 每个阶段必须确认才能继续

---

## 人工确认流程 / Human Confirmation Flow

根据设计文档,每个阶段都需要人工确认:

| 阶段 Phase | 需要确认的内容 | 状态 Status |
|-----------|---------------|-------------|
| Phase 1 | 书名、类型、字数、存放目录 | 必需 |
| Phase 2 | 风格指南 | 必需 |
| Phase 3 | 主线大纲 | 必需 |
| Phase 4 | 章节规划 | 必需 |
| Phase 5 | 世界观设定 | 必需 |
| Phase 6 | 每章正文后确认进入下一章 | 必需 |
| Phase 7 | Backpatch 确认 | 必需 |
| Phase 8-9 | 最终合并确认 | 必需 |

---

## 快速开始 / Quick Start

### 通过 OpenClaw 调用

```
帮我写一本都市灵异小说
```

AI 会引导你完成每个阶段的确认。

### 通过 CLI

```bash
# 初始化新书 (每个阶段会确认)
python -m scripts.v2.cli init

# 写作 (每章会确认)
python -m scripts.v2.cli write --run-dir <path>
```

---

## 架构 / Architecture

### 目录结构 / Directory Structure

```
novels/
└── {book_title_slug}__{book_uid}/
    └── runs/
        └── {run_id}/
            ├── 0-config/              # 配置层
            ├── 1-outline/             # 大纲层
            ├── 2-planning/           # 规划层
            ├── 3-world/              # 世界观层
            ├── 4-state/              # 运行时状态 (7面板)
            ├── drafts/                # 草稿层
            ├── chapters/              # 最终章节
            ├── anchors/               # 锚点
            ├── logs/                  # 日志
            ├── archive/              # 归档
            └── final/                 # 最终输出
```

---

## 阶段参考 / Phase Reference

| 阶段 Phase | 名称 Name | 描述 Description | 需要确认 |
|-----------|-----------|-----------------|---------|
| 1 | Initialization | 创建工作空间、配置 | ✅ 书名/类型/字数/目录 |
| 2 | Style Guide | 定义叙事风格 | ✅ 风格指南 |
| 3 | Main Outline | 生成书籍级情节结构 | ✅ 主线大纲 |
| 4 | Chapter Planning | 详细章节列表与钩子 | ✅ 章节规划 |
| 5 | World Building | 角色、阵营、规则、道具 | ✅ 世界观 |
| 5.5 | Alignment Check | 验证世界观匹配意图清单 | 自动 |
| 6 | Writing Loop | 清洗→草稿→QC→提交 | ✅ 每章确认 |
| 7 | Backpatch Pass | FORCED章节回补修复 | ✅ 确认 |
| 8 | Merge Book | 合并章节为最终版本 | ✅ 确认 |
| 9 | Whole-Book QC | 最终7点质量检查 | ✅ 确认 |

---

## 阶段6: 写作循环 (核心) / Phase 6: Writing Loop (Core)

### 确认流程 / Confirmation Flow

```
[生成大纲] → 用户确认 → [生成正文] → QC评分 → 用户确认 → [下一章]
```

### QC 评分标准

| 分数 Score | 状态 Status | 动作 Action |
|-----------|------------|------------|
| ≥85 | PASS | 保存,继续 |
| 75-84 | WARNING | 保存(带警告),继续 |
| <75 | REVISE | 重试 |
| 第三次<75 | FORCED | 保存,进Backpatch |

---

## 配置 / Configuration

### 0-book-config.json

```json
{
  "version": "2.1.0",
  "book": {
    "title": "书名",
    "title_slug": "book_slug",
    "book_uid": "8char_hash",
    "genre": "都市灵异",
    "target_word_count": 100000,
    "chapter_target_words": 2500
  },
  "generation": {
    "model": "moonshot/kimi-k2.5",
    "mode": "manual",
    "max_attempts": 3,
    "auto_threshold": 85,
    "auto_rescue_enabled": true
  }
}
```

---

## OpenClaw 集成 / OpenClaw Integration

### 模型说明

**重要**: 这个 skill 不硬编码任何模型。当 OpenClaw 调用此 skill 时,自动使用 OpenClaw 当前配置的模型。

### 函数入口

```python
from scripts.v2.openclaw_entry import run_skill, get_required_confirmations

# 获取某阶段需要确认的内容
confirmations = get_required_confirmations("6_write")
# Returns: ["每章正文生成后确认", "每章评分确认"]

# 运行 skill - 模型由 OpenClaw 自动提供
result = run_skill(
    book_title="我的小说",
    genre="都市",
    target_words=100000,
    mode="manual"
    # oc_context 由 OpenClaw 自动传入,包含当前模型
)
```

### oc_context 参数

OpenClaw 会自动传入 `oc_context` 参数,包含:
- `model_call` - 调用当前模型的方法
- `model_name` - 当前模型名称(可选)
- `generate` - 备选方法(可选)

---

## 开发 / Development

### 模块结构 / Module Structure

```
scripts/v2/
├── __init__.py
├── utils.py              # ID生成、slug、路径
├── atomic_io.py          # 原子写入、快照
├── workspace.py          # 目录管理
├── config_manager.py     # 配置I/O
├── state_manager.py      # 7面板
├── prompt_registry.py    # 模板注册表
├── prompt_assembly.py   # 提示词构建
├── price_table.py       # 费率表管理
├── resume_manager.py    # 断点续传、锁管理
├── phase_runner.py      # 阶段1-5
├── writing_loop.py       # 阶段6
├── safety_mechanisms.py  # 阶段7-9
├── cli.py               # CLI入口
└── openclaw_entry.py    # OpenClaw入口 (v2.1新增)
```

---

## 版本历史 / Version History

### v2.1.0 (2026-02-16)
- ✅ 每个阶段人工确认机制
- ✅ OpenClaw 函数入口
- ✅ 接入真实模型 API
- ✅ 修复 Windows 兼容性
- ✅ 完善中文文档

### v2.0.0 (2026-02-11)
- 初始版本
- 9阶段流水线
- 7状态面板
- 多视角QC

---

## 许可证 / License

MIT License

Popular in Content

李白.SkillContent

李白.Skill:润色专家 检测并消除中文文本中的AI生成痕迹,将生硬的机器输出转化为自然流畅的人类文笔。融合规则检测、分层改写和质控流水线,确保最终文本通过人工审查。

↓ 1.3M★ 121user_741dc82b
libai-skillContent

李白.Skill:润色专家 检测并消除中文文本中的AI生成痕迹,将生硬的机器输出转化为自然流畅的人类文笔。融合规则检测、分层改写和质控流水线,确保最终文本通过人工审查。

↓ 1.0M★ 11user_814dbe54
文章去AI味工具Content

Detects and removes AI writing traces so text reads more like a person wrote it.

↓ 951.0K★ 767user_ab5ae6ee
视频号爆款短视频拆解(付费版:全能)【零一数科·出品】Content

【零一数科·出品】视频号爆款短视频拆解(全能版)(付费版)。视频号爆款短视频拆解(付费版:全能)。一键拆解爆款,把一条视频号视频拆成结构分段、爆款归因、六维评分和可借鉴策略,照着学照着抄。支持视频号分享链接和本地视频,付费全能版远端分析,1–5 分钟出可视化 HTML 报告。

↓ 918.5K★ 116u_c19e970c
视频号挂车爆单短视频脚本生成【零一数科·出品】Content

【零一数科·出品】视频号挂车爆单短视频脚本生成(付费版)。一条链接二创脚本,丢进爆款视频号链接即以此骨架改写成你的挂车脚本,或按方向/目的/商品原创多条口播脚本(含分段表、口播全文、六维质检评分)。

↓ 554.4K★ 39u_c19e970c
HumanizerContent

A writing-editor skill that finds the usual marks of AI-generated text and rewrites them into more natural prose without losing the meaning.

↓ 508.8K★ 1.1KB*T
中文公文写作Content

用于中文公文、事务性材料和新闻稿件的起草、改写、压缩、润色、审校、文种核对、去口语化、降 AI 味及 Word 格式处理,适用于机关、企事业单位、学校和新闻机构。涵盖申请、请示、报告、通知、通告、意见、决定、决议、议案、公报、命令、函、复函、批复、说明、方案、纪要、公告、公示、通报、制度、规定、办法、细则、操作规程、工作要点、总结、调研、讲话、致辞、主持词、述职、可研、审查材料、技术需求、新闻消息、编者按、新闻评论,以及采购、整改、反馈和 AI 算力等场景。

↓ 413.4K★ 84gongyu0918
视频号爆款文案生成(体验版)【零一数科·出品】Content

【零一数科·出品】视频号爆款文案生成(体验版)。免费免登录出脚本,给创作目的、行业、受众、选题就按爆款结构(Hook-中段-CTA、节奏标签)产出口播脚本,信息不全也能按爆款潜质兜底。本地运行、无需 Key,零成本上手。

↓ 339.1K★ 94u_c19e970c

Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.