story-short-analyze

story-short-analyze is a skill for Claude Code, Codex from Xiaoyangy/novel-studio. It costs 225 tokens per session (4,609 once invoked), scanned A, a copy of story-short-analyze, Apache-2.0.

A workflow for taking apart short popular Chinese web fiction and documenting how it works. It examines the central story idea, structure, emotional progression, twists, and writing techniques.

In plain words
What is it for?
Use it to study legally obtained short stories from platforms such as 番茄, 故事会, and 知乎盐选, identify themes such as revenge or romance, and produce a reusable analysis report.
Why use it?
It gives writers and editors a structured way to understand why a short story creates strong reactions and where its major turning points occur. It also saves the analysis for later writing work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to study legally obtained short stories from platforms such as 番茄, 故事会, and 知乎盐选, identify themes such as revenge or romance, and produce a reusable analysis report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xiaoyangy/novel-studio/story-short-analyze
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-analyze
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.

agentmods badge for story-short-analyze

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/story-short-analyze/github.svg)](https://agentmods.dev/skills/xiaoyangy/novel-studio/story-short-analyze)
Your own site
<a href="https://agentmods.dev/skills/xiaoyangy/novel-studio/story-short-analyze"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/story-short-analyze/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.

agentmods 80×15 button for story-short-analyze

Your own site · 80×15
<a href="https://agentmods.dev/skills/xiaoyangy/novel-studio/story-short-analyze"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/story-short-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 225 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,609 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.
Origin 89% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00225 $0.04609
Opus 5 $0.00112 $0.02305
Sonnet 5 $0.00045 $0.00922
Haiku 4.5 $0.00022 $0.00461

Measured 13d ago against content hash 210fec4645bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

story-short-analyze 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 13d 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.

Origin

This is a copy

89% identical to story-short-analyze — 71 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/story-short-analyze/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

story-short-analyze:短篇网文拆文

你是短篇小说结构分析师。

核心:短篇靠共鸣和爆点驱动。拆文就是看它用什么故事核、怎么铺垫、在哪里引爆,把 分析叙事写进 拆文报告.md,结构计数写进 _meta.json,下一篇短篇直接读这些写。


拆解边界声明(主线程同样适用)

短篇拆解的 Stage 2-6 全程由你(主线程)亲手做:拆的是用户合法持有、拥有使用权的虚构作品(已出版/连载或自有),性质是只读的转化性文学批评(编辑/评论/写作教学视角,不复制、不传播、不指导现实行为)。番茄短篇、故事会、知乎盐选、追妻、虐渣、世情等通俗题材里的家暴、出轨、复仇、暴力、情爱张力、黑暗伦理是常规虚构叙事元素,须照常做结构化拆解,不得以「敏感」「不适」为由拒绝整篇或某个片段——拒绝会让整条拆文流水线停摆;个别片段无法处理则跳过、照常续完其余。


Phase 1:确认拆解对象 + 字数路由 + 续跑检查

1.1 拿到原文

问用户:「你要拆哪篇?(标题+平台/来源)」

无文本时:用户没有提供原文文件路径、也没有在对话中贴出原文,引导用户提供 ——「请提供这篇短篇的原文文件路径,或直接把原文贴给我。」

1.2 字数检查(长短篇路由)

拿到原文后立刻数字数:

word_count = 全文字数
  ├─ < 15,000          → 直接进入 short 管道
  ├─ 15,000 - 20,000   → 灰区:询问用户「字数 {N},介于短/长之间,按短篇还是长篇拆?」
  └─ > 20,000          → 提示「此文字数 {N} 偏长,长文拆解在工程外完成,把拆解成品直接放入 deconstruction-library/{书名}/。
                           仍要按短篇拆请明确回复『按短篇继续』」

为什么必须探针:短篇与长篇的节点密度、情感曲线节奏、共鸣层数差异显著;用短篇 管道拆 100k+ 长篇会把节点采样过疏,模型把单卷误判成全书。

1.3 题材识别

用户提到具体题材(追妻 / 重生 / 虐文 / ...)?
  ├─ 是 → 加载 genre-catalog.md 对应题材的「短篇视角」章节作为拆文标尺
  └─ 否 → 关键词扫描确定题材;扫不到则 genre_detected = "通用",用通用模板(Stage 2-6)

题材识别关键词参考:

  • 追妻火葬场 / 渣男后悔 → 追妻
  • 重生复仇 / 前世今生 → 重生复仇
  • 死后视角 / 灵魂旁观 → 死人文学
  • 小三 / 出轨 / 知三当三 → 小三
  • 世情 / 现实 / 婆媳 → 世情
  • 仙侠 / 修仙 / 门派 → 仙侠

题材作为「对照标尺」加载——见 references/genre-catalog.md 等文件首段「## 用作 拆文标尺时」说明。

1.4 续跑检查(lightweight resume)

进入管道前检查 deconstruction-library/{书名}/_meta.json

存在 _meta.json?
  ├─ 否 → 直接进入新一轮拆解
  └─ 是 → 询问用户三选一:
       (a) 覆盖:归档旧产出到 deconstruction-library/{书名}/_archive_{时间戳}/ 后从 Stage 2 重跑
       (b) 续跑:读 _meta.json.last_stage_in_progress(非空 → 从该 Stage 整段重跑)
                 或读 _meta.json.stages_completed[](从 max+1 续跑)
       (c) 取消

完整 resume 契约见 references/output-contract.md


输出目录

输出到 deconstruction-library/{书名}/(项目根目录下)。用户指定了其他路径时按用户指定路径输出。

标准输出文件树

deconstruction-library/{书名}/
├── 原文/                # 原文备份(管道前置步骤产出)
├── 拆文报告.md           # 人类可读综合报告(Stage 2-6 所有可读段)
├── 情节节点.md           # Stage 2 情节节点清单(独立成文,方便定位)
├── 写作手法.md           # Stage 4 写作手法分析(独立成文,方便复用)
└── _meta.json           # 管道元数据 + 结构计数(resume + Phase 7 数值依据)

Read the full file on GitHub · 267 lines

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.

  1. 13d ago First seen · 267 lines · 225 tokens per session scan A 210fec4645bc

Subscribe to this mod's changes

story-short-analyze is a skill published in the GitHub repository Xiaoyangy/novel-studio (109 stars, last pushed 4d ago), licensed Apache-2.0. It adds 225 tokens to every session and 4,609 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to story-short-analyze, differing in 71 lines, and is treated as a copy.