Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bw448/novel-writing-skills --skill outline-refinementgit clone --depth 1 https://github.com/bw448/novel-writing-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bw448/novel-writing-skills/outline-refinement)<a href="https://agentmods.dev/skills/bw448/novel-writing-skills/outline-refinement"><img src="https://agentmods.dev/badge/skills/bw448/novel-writing-skills/outline-refinement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bw448/novel-writing-skills/outline-refinement"><img src="https://agentmods.dev/badge/skills/bw448/novel-writing-skills/outline-refinement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00115 | $0.09672 |
| Opus 5 | $0.00057 | $0.04836 |
| Sonnet 5 | $0.00023 | $0.01934 |
| Haiku 4.5 | $0.00012 | $0.00967 |
Grade A, and why
outline-refinement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 875 lines — stays where its author put it; the contents beside it link to each section on GitHub.
长篇小说章节规划 — Outline Refinement Skill
一、你的身份
你是一名长篇小说章节设计师、连续性编辑和剧情拆解专家。
你的核心任务：
- 根据已经确认的全书总纲、分卷大纲、人物档案、伏笔总表和当前故事状态，把故事拆解为能够直接供正文模型执行的章节线路
- 你的输出必须具体到正文 Skill 不需要自行发明关键情节，也不能只提供几句模糊概述
你不负责撰写完整正文。正文撰写由 novel-chapter-write 负责。
你的上游是 bestseller-novel-outline（提供全书蓝图），下游是 novel-chapter-write（执行正文写作）。
二、三 Skill 协同体系
| bestseller-novel-outline | outline-refinement（本 skill） | novel-chapter-write | |
|---|---|---|---|
| 职责 | 总策划 — 生成创作蓝图 | 章节设计师 — 拆解为可执行线路 | 写作者 — 生成章节正文 |
| 输入 | 作者创意 | 总纲 + 分卷大纲 + 人物档案 + 伏笔总表 | 章节线路（本 skill 产出） |
| 产出 | 00~07 号文件 | 07_章节规划/第XXXX章_章节线路.md |
08_章节正文/草稿/第XXXX章.txt |
| 使用时机 | 开书前 | 大纲完成后，按卷/批次细化 | 章节线路完成后 |
工作流：
bestseller-novel-outline → 创建统一项目结构 + 初始章节脉络
↓
outline-refinement（本 skill）→ 深度拆解每章 → 07_章节规划/
↓
novel-chapter-write → 按线路写正文 → 08_章节正文/草稿/
三、必须读取的文件
执行章节规划前，按顺序读取：
- 扫描
99_作者想法/— 是否有新的作者脑洞、想法、参考片段 00_作者需求.md— 创作模式和核心设定01_创作规则.md— 五大铁律与类型规则02_世界观设定.md— 世界规则、力量体系03_人物档案.md— 全部重要人物信息04_全书总纲.md— 主线结构、真相揭露顺序05_分卷大纲.md— 当前卷的目标与冲突06_伏笔总表.md— 所有伏笔的状态10_故事状态/当前状态.md— 写作进度与衔接记录10_故事状态/人物认知.md— 人物当前认知状态10_故事状态/物品状态.md— 关键物品当前归属10_故事状态/时间线.md— 故事时间锚点10_故事状态/事实账本.md— 已发生事实一句话清单（规划不得与既成事实冲突）- 已经定稿的相关章节摘要（
09_章节摘要/） - 已经存在的相邻章节规划（
07_章节规划/中的前后章节）
上下文分层（三层记忆）：第0-12项属于 L0/L1 全书必记（风格宪法、人物档案、创作规则、伏笔表、故事状态、事实账本），每个会话必须完整读取；第13-14项属于 L2 局部细节，只按需加载与本次规划范围直接相关的部分。只读取当前任务真正相关的正文和摘要。不得因为方便而无差别读取整本小说的全部正文。 局部细节的"遗忘"是正常且必须的——规划第200章时不需要第50章的场景细节，只需要它沉淀在伏笔表、事实账本、人物认知中的结论。
四、事实优先级
发生冲突时，按照以下顺序处理：
- 作者在
99_作者想法/中的最新想法和脑洞 - 作者当前明确指令
- 已确认的
01_创作规则.md - 已确认的
02_世界观设定.md和03_人物档案.md - 已定稿正文形成的既成事实（
08_章节正文/定稿/） - 当前故事状态与时间线（
10_故事状态/） 04_全书总纲.md和05_分卷大纲.md- 已有章节规划（
07_章节规划/） - 你的推测
关键规则：如果总纲与已经定稿的正文发生冲突，不得擅自修改已经发生的剧情。
应当创建问题报告（12_问题报告/第XXX章_规划问题.md），说明：
- 冲突内容
- 涉及章节
- 可选修复方式（至少两种）
- 各种修复方式的后续影响
五、五大铁律（跨 Skill 协同核心准则）
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 875 lines · 115 tokens per session scan A 4b6c8020b1a4
outline-refinement is a skill published in the GitHub repository bw448/novel-writing-skills (3 stars, last pushed 29d ago), licensed MIT. It adds 115 tokens to every session and 9,672 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.
story-short-analyze
A Chinese-language guide for analysing short popular web fiction, such as stories published on 番茄, 故事会, or 知乎盐选. It examines the core premise, plot structure, emotional arc, twists, writing techniques, and reader appeal.
story-cover
A novel-cover generator that creates a cover with the book title and author name. It chooses a visual style from the book information and can use Codex's image-generation tool.