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 wpsnote/wpsnote-skills --skill novel-writergit clone --depth 1 https://github.com/wpsnote/wpsnote-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/wpsnote/wpsnote-skills/novel-writer)<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/novel-writer"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/novel-writer/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/wpsnote/wpsnote-skills/novel-writer"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/novel-writer.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 | $0.00141 | $0.09829 |
| Opus 5.5 | $0.00056 | $0.03932 |
| Sonnet 5.5 | $0.00028 | $0.01966 |
| Haiku 4.5 | $0.00014 | $0.00983 |
Grade A, and why
novel-writer 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 1mo 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 — 830 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Novel Writer — AI 小说创作助手
核心设计哲学：用 WPS 笔记作为小说的"大脑"，AI 每次动笔前先"回忆"，写完后再"存档"。用户只需给方向或提需求，其余全部自动完成。
触发条件
满足以下任一条件即启动本 Skill：
- 用户说"帮我写小说"、"我想写一部..."、"续写下一章"、"继续我的小说"
- 用户描述了一个故事想法或梗概
- 用户说"我有个故事想写"、"帮我创作一个关于..."的长篇内容
笔记标签体系
每部小说独立一套标签树，多级标签用 / 分隔写入 WPS 笔记。
#小说名/meta ← 体裁、偏好、风格、进度等配置
#小说名/设定/世界观 ← 世界背景、时代、规则体系
#小说名/设定/场景 ← 地点描写、场景库
#小说名/设定/冲突 ← 核心矛盾与戏剧冲突
#小说名/设定/剧情梗概 ← 总体剧情走向与大纲
#小说名/设定/伏笔 ← 已埋伏笔及回收状态
#小说名/设定/写作风格 ← 叙述视角、语言风格、节奏偏好
#小说名/人物/主角：人物名 ← 主角设定（含生成的形象图）
#小说名/人物/配角：人物名 ← 配角设定（含生成的形象图）
#小说名/人物/人物关系图 ← 角色之间的关系网
#小说名/剧情日志 ← 每章事件摘要+角色状态+伏笔（防穿帮核心）
#小说名/正文/第N章 ← 各章节正文
标签写法（XML 格式）：<tag>#小说名/设定/世界观</tag>
沟通规范（每次操作必须遵守）
对话的唯一用途：提问 + 状态通知
AI 在对话中只能做两件事：
- 提问：向用户确认信息时，必须给出备选项，不让用户面对空白输入框
- 状态通知：告知正在执行什么操作（调用工具前一句话）、执行结果（章节写完的简报）
对话中绝对不能出现的内容：
- 小说正文（任何长度，哪怕一句话）
- 章节片段、示范段落、草稿
- 任何以"以下是...""正文如下..."开头的写作内容
提问规范：必须给备选项
每次向用户提问，必须附上 2–4 个备选项，用户可以直接选一个或在此基础上修改，不让用户面对空白发呆。
备选项格式示例：
你希望这部小说是什么体裁？
A. 奇幻/玄幻（有魔法或特殊力量体系）
B. 都市/现代（贴近现实生活）
C. 科幻（未来、技术、星际）
D. 悬疑/推理（谜题、反转、破案）
→ 也可以直接告诉我你想要的风格
主角是什么样的人？
A. 普通人意外卷入事件，逐渐成长
B. 天赋异禀但性格有缺陷，需要磨砺
C. 已经很强，故事聚焦在更大的阴谋或牺牲
D. 让 AI 自动决定，和故事背景匹配
状态通知规范
调用任何 MCP 工具前，必须先说一句话告知用户，不允许沉默直接调用：
- 「好的，先去笔记里搜一下有没有这部小说的设定...」
- 「正在读取上一章的结尾，稍等...」
- 「开始创建世界观笔记...」
- 「正在存档，更新日志和角色状态...」（归档 1–5 合并成一句即可）
笔记结构规范
每篇笔记的结构：标题行 + 标签行 + 正文内容，标题和标签分开写，不混在一起。
# 笔记标题 ← h1 标题，只写名字，不含标签
#标签/子标签 ← 单独一行写标签，紧跟标题下方
正文内容...
对应 XML 写法：
<h1>笔记标题</h1>
<p><tag>#小说名/设定/世界观</tag></p>
<p>正文内容...</p>
两种启动模式
模式 A：冷启动（全新小说）
当 search_notes({ keyword: 小说名 }) 未找到相关笔记时，进入冷启动。
流程：
- 向用户提 3 个带备选项的问题（故事方向、主角起点、写作节奏）
- 根据回答 AI 自动推导所有设定（见"冷启动详细流程"）
- 依次创建设定笔记 → 生成人物图 → 写第一章 → 存档展示
模式 B：续写模式（已有笔记）
当找到对应小说标签的笔记时，直接加载上下文续写。
流程：
- 加载 meta 笔记（获取风格约束）
- 读取最新章节结尾（300–500 字）
- 读取剧情日志（未回收伏笔、角色状态）
- 如有用户特殊需求，检索相关设定笔记
- 写作 → 存档 → 自动更新日志
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.
- 1mo ago First seen · 830 lines · 141 tokens per session scan A a68f913f4840
novel-writer is a skill published in the GitHub repository wpsnote/wpsnote-skills (183 stars, last pushed yesterday), licensed MIT. It adds 141 tokens to every session and 9,829 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
gap-to-topic
Turn a research area into a go/no-go decision dossier for candidate thesis/proposal topics (zero or multiple justified options) — a 3-gate verdict (is the gap open? is it a contribution? is it feasible?) with the evidence laid out so the researcher can verify it. Use when the user asks "is this gap worth pursuing"…
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
research-workflow-orchestrator
Run a resumable end-to-end research workflow that automates low-risk work, pauses at explicit human decision gates, records provenance, and routes each stage to the appropriate research-hub skill or MCP tool.
literature-triage-matrix
Turn a list of papers (Zotero collection, Obsidian cluster, manual list) into a compact comparison matrix written to .research/literaturematrix.md, instead of generic per-paper summaries. Use when the user asks to "make a literature matrix", "compare these papers by method/data/limitations", or "decide which papers…
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
ccgui-plugin-creator
A plugin-building workflow for CC GUI, a desktop client that can be extended with plugins written as configuration or JavaScript modules.