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 uu201/character-arc --skill story-short-analyzegit clone --depth 1 https://github.com/uu201/character-arcWrote 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/uu201/character-arc/story-short-analyze)<a href="https://agentmods.dev/skills/uu201/character-arc/story-short-analyze"><img src="https://agentmods.dev/badge/skills/uu201/character-arc/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.
<a href="https://agentmods.dev/skills/uu201/character-arc/story-short-analyze"><img src="https://agentmods.dev/badge/skills/uu201/character-arc/story-short-analyze.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 | $0.00230 | $0.04456 |
| Opus 5 | $0.00115 | $0.02228 |
| Sonnet 5 | $0.00046 | $0.00891 |
| Haiku 4.5 | $0.00023 | $0.00446 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- story-short-analyze — 89% identical, 71 lines differ
How it starts
The opening of the file, as written. The whole thing — 284 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。
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 字数探针(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,建议改用 /story-long-analyze。
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 拆文库/{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 拆文库/{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 拆文库/{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:
拆文库/{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)
下游契约:
story-short-write同时读全套产出——拆文报告.md取分析叙事,情节节点.md看节奏锚点,写作手法.md抄手法,原文/抄语感,_meta.json看题材识别和结构计数。完整字段定义见 references/output-contract.md。
Stage → 文件映射
| Stage | 落地文件 |
|---|---|
| 2 | 拆文报告.md(故事核+结构+梗概段) + 情节节点.md |
| 3 | 拆文报告.md(情感曲线+爆点段) |
| 4 | 拆文报告.md(反转段) + 写作手法.md |
| 5 | 拆文报告.md(人物+首尾段) |
| 6 | 拆文报告.md(综合段) + _meta.json.structure_counts(数值计入元数据) |
What ships with it
20 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.
- references/anti-ai-writing.md 17 KB
- references/banned-words.md 5.8 KB
- references/character-basics.md 17 KB
- references/character-design-methods.md 16 KB
- references/character-relations.md 16 KB
- references/deconstruction-examples.md 4.1 KB
- references/genre-catalog.md 21 KB
- references/genre-core-mechanics.md 18 KB
- references/genre-readers.md 13 KB
- references/genre-writing-formulas.md 22 KB
- references/genre-writing-techniques.md 20 KB
- references/hooks-chapter.md 8.4 KB
- references/hooks-paragraph.md 6.7 KB
- references/hooks-suspense.md 15 KB
- references/material-decomposition.md 35 KB
- references/output-contract.md 8.8 KB
- references/output-templates.md 24 KB
- references/quality-checklist.md 9.9 KB
- references/real-market-data.md 4.8 KB
- references/zhihu-style.md 2.2 KB
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 · 284 lines · 230 tokens per session scan A befcc740dfdb
story-short-analyze is a skill published in the GitHub repository uu201/character-arc (559 stars, last pushed yesterday), licensed MIT. It adds 230 tokens to every session and 4,456 once invoked, about $0.0011 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.
Other skills, from other repositories
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
教程类H5-小红书小工具
A method for building offline, single-page course experiences for Xiaohongshu’s Mini Tools, which are interactive pages published inside the platform. It combines written lessons, generated illustrations, and JavaScript page switching in a constrained container.
wechat-delivery
A workflow for preparing WeChat Official Account articles, images, covers, and publishing files in Chinese. WeChat Official Accounts are channels used by organizations to publish articles to followers.
ai-image-to-pptx
A workflow that creates a set of related images with AI and places them into a real PowerPoint file. The resulting .pptx file can be opened and edited in PowerPoint, Keynote, or WPS.