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 wordflowlab/novel-writer-skills --skill setting-detectorgit clone --depth 1 https://github.com/wordflowlab/novel-writer-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/wordflowlab/novel-writer-skills/setting-detector)<a href="https://agentmods.dev/skills/wordflowlab/novel-writer-skills/setting-detector"><img src="https://agentmods.dev/badge/skills/wordflowlab/novel-writer-skills/setting-detector/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/wordflowlab/novel-writer-skills/setting-detector"><img src="https://agentmods.dev/badge/skills/wordflowlab/novel-writer-skills/setting-detector.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 | $0.00038 | $0.03859 |
| Opus 5 | $0.00019 | $0.01929 |
| Sonnet 5 | $0.00008 | $0.00772 |
| Haiku 4.5 | $0.00004 | $0.00386 |
Grade A, and why
setting-detector 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.
How it starts
The opening of the file, as written. The whole thing — 567 lines — stays where its author put it; the contents beside it link to each section on GitHub.
故事设定自动检测器
核心功能
自动激活知识库系统 - 这是Novel Writer Skills的核心竞争力。
当你提到特定关键词时,我会自动:
- 检测故事的类型、时代、主题
- 加载对应的写作知识库
- 在整个创作过程中应用专业知识
无需手动调用 - 完全自动化,后台运行。
工作原理
关键词映射表
我监听以下关键词并自动激活对应知识库:
类型知识库(Genres)
言情小说(romance):
触发词:言情、爱情、恋爱、浪漫、感情线、关系弧、CP、甜文、虐文、
HE、BE、双洁、破镜重圆、先婚后爱、契约关系
激活:templates/knowledge-base/genres/romance.md
悬疑推理(mystery):
触发词:悬疑、推理、侦探、破案、谜团、线索、真相、凶手、犯罪、
密室、诡计、不在场证明、推理小说
激活:templates/knowledge-base/genres/mystery.md
历史小说(historical):
触发词:历史、古代、朝代、考据、时代背景、历史小说、古言、
穿越、重生古代、架空历史、宫斗、宅斗
激活:templates/knowledge-base/genres/historical.md
复仇爽文(revenge):
触发词:复仇、报仇、打脸、爽文、逆袭、反击、重生复仇、
穿越复仇、系统、金手指、女主爽文、男主爽文
激活:templates/knowledge-base/genres/revenge.md
武侠小说(wuxia):
触发词:武侠、江湖、武功、侠客、门派、武学、剑客、
轻功、内功、武林、江湖恩仇、侠义
激活:templates/knowledge-base/genres/wuxia.md
参考资料库(References)
1920年代中国(china-1920s):
触发词:1920、民国、军阀、北洋、穿越民国、二十年代、
民国时期、军阀混战
激活:templates/knowledge-base/references/china-1920s/
自动激活流程
示例1:单一类型检测
用户:"我要写一部言情小说"
↓
[检测到关键词:"言情"]
↓
✓ 自动加载:romance.md
↓
AI回复:"太好了!让我帮你创作言情小说。
根据言情类型惯例,我们需要明确几个核心元素...
(自动应用romance.md中的知识)"
示例2:多类型组合检测
用户:"我要写一部1920年代的言情复仇小说"
↓
[检测到关键词:"1920"、"言情"、"复仇"]
↓
✓ 自动加载:romance.md
✓ 自动加载:revenge.md
✓ 自动加载:references/china-1920s/
↓
📚 已激活知识库:
- genres/romance.md(言情小说惯例)
- genres/revenge.md(复仇爽文技巧)
- references/china-1920s/(1920年代背景)
↓
AI回复:"很好的组合!这是浪漫悬疑+复仇+民国背景。
根据这三个类型的融合,建议...
(同时应用三个知识库的内容)"
示例3:创作过程中的持续应用
/constitution 阶段:
→ 已激活:romance.md
→ 提醒:言情小说需要HEA/HFN结局承诺
/specify 阶段:
→ 已激活:romance.md + revenge.md
→ 建议:定义关系弧线+复仇目标
/plan 阶段:
→ 已激活:所有知识库
→ 应用:情感节奏点+打脸节奏+1920年代细节
/write 阶段:
→ 已激活:所有知识库
→ 实时:对话技巧+场景描写+时代氛围
/analyze 阶段:
→ 已激活:所有知识库
→ 检查:言情惯例+复仇合理性+历史准确性
Token效率优化
为什么这个系统高效?
传统方案(superpowers-skills模式):
50个独立Skills × 每个40行SKILL.md = 2000 tokens
每次对话都加载所有Skills
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 · 567 lines · 38 tokens per session scan A b04ec619a94b
setting-detector is a skill published in the GitHub repository wordflowlab/novel-writer-skills (258 stars, last pushed 10mo ago), licensed MIT. It adds 38 tokens to every session and 3,859 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…