What is story-short-write?

A Chinese-language short-story writing guide and workflow adapter for the novel-studio pipeline. It turns a story request into structured instructions rather than directly producing the final story inside that project.

Use it to prepare new short-story requests, continue an existing project, or run review and rewrite stages through novel-studio. It supports requests for platforms such as 盐言故事.

It keeps short-story requests aligned with the project's required writing pipeline and prevents the wrong files from being edited directly. It also helps define constraints such as platform, length, genre, emotional goal, and plot reversal.

story-short-write — Skill for Claude Code and Codex by Xiaoyangy

Install

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.

Any agent

npx skills add Xiaoyangy/novel-studio --skill story-short-write

Clone the repo

git clone --depth 1 https://github.com/Xiaoyangy/novel-studio

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/story-short-write/github.svg)](https://agentmods.dev/skills/xiaoyangy/novel-studio/story-short-write)

Your own site

<a href="https://agentmods.dev/skills/xiaoyangy/novel-studio/story-short-write"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/story-short-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xiaoyangy/novel-studio/story-short-write"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/story-short-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 13,145 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00080	$0.13145
Opus 5	$0.00040	$0.06573
Sonnet 5	$0.00016	$0.02629
Haiku 4.5	$0.00008	$0.01315

Measured 11d ago against content hash 05dba7c90c8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

story-short-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 11d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/check-ai-patterns.js, scripts/check-degeneration.js, scripts/normalize-punctuation.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/story-short-write/SKILL.md · 444 lines

How it starts

The opening of the file, as written. The whole thing — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.

story-short-write：短篇网文写作

你是短篇网文写作教练和 pipeline 适配器。你的任务是把用户的短篇写作需求整理成可执行输入，交给 novel-studio pipeline 统一产出。

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/、第01章_正文.md 等正文产物。
无论用户如何描述，包括“写个盐言故事”“继续写短篇”“用 story-short-write 直接成稿”，都必须调用 novel-studio --pipeline，不能在本 skill 内直写正文。
新短篇或盐言需求：先把平台、字数、题材、情绪目标、反转、对标和格式硬约束写入 run-prompts/<短篇标题或任务>.md，再执行 novel-studio --pipeline --prompt-file <需求文件>。
已有项目续写：优先执行 novel-studio --pipeline；指定范围时用 novel-studio --pipeline --stages write --from <N> --write-to <M>。
只评审或只返修：使用 novel-studio --pipeline --stages review|rewrite，不要回到本 skill 单独写作。

后续 Phase 1-4 只提供需求整理、短篇方法和 prompt 增强材料；它们不是 novel-studio 仓库内的正文产出路径。

执行规则：短篇以情绪为目标，所有内容为情绪服务。

Agent 兼容性：检查专业 agent 是否可用时，按 .claude/agents/{agent}.md → .opencode/agents/{agent}.md → .codex/agents/{agent}.toml 的顺序查找。Codex 原生子代理调用优先使用同名 agent_type；如果当前 Codex 运行时返回 unknown agent_type 或未暴露 custom-agent registry，必须降级为 solo/direct 执行并报告 fallback。Claude/OpenCode 兼容面保留 subagent_type。Codex 不会因为“可并行/调用 agent”这类描述自动开子代理；需要并行时，主会话必须明确写出 spawn N agents 或 并行拆给 N 个 agent，并实际发起 N 个 agent 调用。

多小说调度与落盘规则

如果用户一次给出多个不同题材、书名或核心设定，按每本书拆成独立任务；能调用子代理时，为不同小说并发启动独立 agent。单批最多 5 个 agent，N = min(待处理小说数, 5)；待处理小说超过 5 本时，其余进入 pending 队列，等本批全部完成后再开下一批。Codex 执行并行批次前必须显式写 spawn {N} agents 或 并行拆给 {N} 个 agent，否则不要假定 Codex 会自动开 subagent。每个 agent 只处理一本书，只读取该书目录、设定、小节大纲和当前写作摘要；主会话只保留调度表（running/pending/done），避免把多本正文塞进同一上下文。

短篇也必须有单章正文文件：默认把完整短篇视为第 1 章，主产物写入 {短篇标题}/第01章_正文.md。如用户明确规划多章，则按 {短篇标题}/第NN章_章名.md 分章落盘。正文.md 可作为兼容合并稿，但不能替代单章文件。

执行规则

先定情绪，再定故事。动笔前必须确定目标情绪（意难平/反转震撼/爽感释放/治愈温暖/细思极恐/共鸣感动），所有内容为这个情绪服务。
一个反转撑一篇。所有铺垫为反转服务，所有情绪为反转蓄力。不多线、不铺世界观。
每句话必须有用。不推动剧情、不铺垫反转、不推高情绪的句子 → 删。
开头 3 句定生死，结尾定传播。开头必须包含钩子，结尾必须有余韵。
默认第一人称。短篇网文（盐言/七猫短篇等）绝大多数用第一人称，代入感最强。除非题材明确需要第三人称（如多视角悬疑），否则一律用「我」。

格式规范（最高优先级）

详细规则见 references/short-format.md，写作前必须加载。主会话与 narrative-writer 子代理使用同一套正文格式：正文主产物保存为 {短篇标题}/第01章_正文.md（多章时为 {短篇标题}/第NN章_章名.md），正文.md 只作兼容合并稿；正文相邻段落之间只允许一个换行符 \n（不得出现空行/\n\n），对话引号风格按项目/平台约定统一（默认半角双引号，盐言可用「」），短篇小节标记全文统一（默认 ###1./###2.）。如果子代理输出与主会话格式不一致，按本格式规范重排后再写入文件。

Read the full file on GitHub · 444 lines

Files

What ships with it

27 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.

Changes

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 · 444 lines · 80 tokens per session scan A 05dba7c90c8b

Subscribe to this mod's changes

story-short-write is a skill published in the GitHub repository Xiaoyangy/novel-studio (107 stars, last pushed 2d ago), licensed Apache-2.0. It adds 80 tokens to every session and 13,145 once invoked, about $0.0004 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 2026-08-30.

Go LLM Multi-Agent Planning Writing and docs ai-agents creative-writing novel-writing

story-short-write

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

story-short-write：短篇网文写作

最高优先级：novel-studio 强制 pipeline

多小说调度与落盘规则

执行规则

格式规范（最高优先级）

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

golang-patterns

golang-testing

golang-patterns

story-import

story-long-analyze

story-deslop