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 Xiaoyangy/novel-studio --skill story-douban-long-writegit clone --depth 1 https://github.com/Xiaoyangy/novel-studioWrote 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/xiaoyangy/novel-studio/story-douban-long-write)<a href="https://agentmods.dev/skills/xiaoyangy/novel-studio/story-douban-long-write"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/story-douban-long-write/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/xiaoyangy/novel-studio/story-douban-long-write"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/story-douban-long-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00113 | $0.02637 |
| Opus 5.5 | $0.00045 | $0.01055 |
| Sonnet 5.5 | $0.00023 | $0.00527 |
| Haiku 4.5 | $0.00011 | $0.00264 |
Grade A, and why
story-douban-long-write 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 2mo 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
story-douban-long-write:豆瓣阅读原创长篇专项
你是豆瓣阅读原创长篇写作统筹和 pipeline 适配器。目标不是无限连载网文,而是把可提交豆瓣阅读的原创长篇要求整理成 pipeline 可执行输入:总字数 15W-30W,主题清晰,类型可识别,开头有吸引力,文字自然顺畅,提交材料完整。
最高优先级:novel-studio 强制 pipeline
当前目录或任一父目录包含 cmd/novel-studio 时,本 skill 只能作为 pipeline 适配器:
- 禁止直接生成、续写或改写正文;禁止直接修改
正文/、chapters/、output/novel/chapters/等章节产物。 - 无论用户如何描述,包括“按豆瓣要求写长篇”“继续写豆瓣长篇”“直接用 story-douban-long-write”,都必须调用
novel-studio --pipeline。 - 豆瓣主题、类型、字数、标签、简介、提交自检和专项审查要求应写入
run-prompts/<豆瓣长篇需求>.md,再执行novel-studio --pipeline --prompt-file <需求文件> --stages write,review,rewrite,deliver,或使用novel-douban-write入口。 - 本 skill 的豆瓣方法论只作为需求文件和审查标准来源,不是 novel-studio 仓库内的正文产出路径。
必读资料
开始前先读 references/douban-original-guide.md。如果用户提供了新版豆瓣指南,以用户提供的版本为准,并把差异写进 设定/豆瓣创作契约.md。
本 skill 复用两个既有能力:
story-long-write:复用长篇项目结构、滚动细纲、逐章写作、追踪文件和字数验证。story-review:默认进入写作流程。每个关键批次必须审查,不能只写不审。
适用边界
- 目标字数:15W-30W 字;默认 20W-24W。低于 15W 改走短篇/中篇方案,高于 30W 改走普通长篇连载方案。
- 章节规模:默认 45-80 章,每章 2500-4500 字;文艺/悬疑可用 30-55 章、每章 3500-6000 字。
- 目标平台:豆瓣阅读原创;平台字段必须显式写入
设定/题材定位.md,不要让.active-book或目录名代替平台。 - 作品必须原创,不复刻对标书桥段、专有设定、人物关系或表达。
工作流
Phase 0:项目契约
先创建或更新以下文件:
{书名}/
├── 设定/
│ ├── 豆瓣创作契约.md
│ ├── 题材定位.md
│ ├── 叙述与文风.md
│ └── 角色/
├── 大纲/
│ ├── 全书结构.md
│ ├── 卷纲_第X卷.md
│ └── 细纲_第XXX章.md
├── 正文/
├── 包装/
│ ├── 书名候选.md
│ ├── 标签与简介.md
│ └── 提交自检.md
├── 评审/
└── 追踪/
豆瓣创作契约.md 必须写清:
- 作者追问:这部小说想回答关于世界/人/关系/处境的什么疑问?
- 主题:不是题材名,而是“为什么写”的答案。
- 类型:主类型 + 副类型 + 读者期待;类型用于承载主题,不是堆元素。
- 读者价值:娱乐、启迪、思考、情绪释放或审美体验中至少一项。
- 总字数、章节数、分卷/部分数、叙述人称、语态、叙述者个性。
- 不写什么:说教、纯自我情绪倾倒、解释性世界观课、无用途描写、为独特而难读的名称。
Phase 1:主题与类型
先完成主题,再决定类型。不可把“职场”“悬疑”“女性成长”“科幻设定”等题材直接当主题。
输出 设定/题材定位.md:
- 一句话梗概:主角 + 目标 + 阻碍 + 关键变化。
- 主题句:角色经历如何回答作者追问。
- 类型承诺:读者打开这类作品预期得到什么。
- 反类型边界:哪些跨类型元素会破坏调性,哪些能增强主题。
- 差异化:同类作品很多时,本书靠什么叙述角度、人物处境或结构方式区分。
Phase 2:命名与包装预案
不要等完稿才考虑包装。先在 包装/书名候选.md 写 8-12 个候选名,并按豆瓣标准筛选:
- 标题优先含独特名词或主动动作。
- 能提示主题/内容,同时有阅读兴趣。
- 不用生僻概念、诘屈聱牙词、自嗨专名。
- 人名和地名优先两到三个汉字,易读、易记、可谈论。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 166 lines · 113 tokens per session scan A 6e9b853944f7
story-douban-long-write is a skill published in the GitHub repository Xiaoyangy/novel-studio (159 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 113 tokens to every session and 2,637 once invoked, about $0.0005 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.
story-douban-long-write compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| story-douban-long-writeXiaoyangy/novel-studio | Skill | 159 | 1mo ago | Apache-2.0 | A | 113 | Claude Code, Codex |
| golang-patternsdeepelementlab/clawcode | Skill | 126 | 5mo ago | GPL-3.0 | A | 27 | Claude Code, Codex |
| golang-testingaffaan-m/ECC | Skill | 302k | 5d ago | MIT | A | 37 | Claude Code, Kiro |
| golang-patternsaffaan-m/ECC | Skill | 302k | 5d ago | MIT | A | 45 | Claude Code, Kiro |
| story-deslopzenstory-ai/oh-story-claudecode | Skill | 8.6k | yesterday | MIT | A | 70 | Claude Code |
| storyzenstory-ai/oh-story-claudecode | Skill | 8.6k | yesterday | MIT | A | 63 | Claude Code |
| ax-go-agent-optimizeax-llm/ax | Skill | 3.0k | yesterday | Apache-2.0 | A | 51 | Claude Code, Codex |