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 TulanCN/vibe-noveling --skill novel-tastegit clone --depth 1 https://github.com/TulanCN/vibe-novelingWrote 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/tulancn/vibe-noveling/novel-taste)<a href="https://agentmods.dev/skills/tulancn/vibe-noveling/novel-taste"><img src="https://agentmods.dev/badge/skills/tulancn/vibe-noveling/novel-taste/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/tulancn/vibe-noveling/novel-taste"><img src="https://agentmods.dev/badge/skills/tulancn/vibe-noveling/novel-taste.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 | $0.00051 | $0.01464 |
| Opus 5 | $0.00026 | $0.00732 |
| Sonnet 5 | $0.00010 | $0.00293 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade A, and why
novel-taste 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文风偏好测评
用对比样例法绕过抽象描述触达真实偏好——配眼镜换镜片式比较，不问「你喜欢什么风格」。
触发条件
- 用户要测评/确认文风、不确定自己喜欢什么
- novel-init 中自动调用，或用户手动
/novel-taste
前置读取
CLAUDE.md：已有偏好和目标读者（频道定位和阅读经验影响样例题材）- 最近 2-3 章
正文.md（如存在）：对比当前实际文风和偏好是否偏离
测评方法论
核心原则
- 不问抽象问题：不问「你喜欢快节奏还是慢节奏」，只给对比样例
- 控制变量：每个维度的对比样例用同一个场景、同一组人物，只改变目标维度
- 从两端往中间收：先给极端对比，确定用户落在哪一端，再在该端内精细对比
- 允许「都不喜欢」：如果用户两端都不选，说明该维度对他不重要，跳过
测评流程
分两个阶段。第一阶段粗筛，覆盖全部维度，每个维度给一组极端对比快速定位偏好方向。第二阶段精调，根据第一阶段结果，在用户偏好的方向上进一步精细化。
任何时候用户说「差不多」「都可以」，就跳过该维度——说明这不是他真正的敏感点。
第一阶段：粗筛
逐维度进行。每轮：
- 用当前小说的题材和背景，即兴写两段极短文（每段 100-150 字），同一场景，不同风格
- 样例题材匹配目标读者的频道定位（男频→战斗/升级场景，女频→关系/情感场景）
- 用
AskUserQuestion展示，让用户选 A / B / 差不多，记录偏好
如果小说背景未确定，用通用都市/日常场景。
测评维度（7 个）
维度设计基于 SWAS (Kuijpers et al., 2014)、NCPM (Jacobs, 2015)、平行与偏离理论 (Menninghaus et al., 2024)、Biber MD 分析 (1988)、聚焦理论 (Genette, 1980)。详见 references/style-dimensions.md。
| # | 维度 | A 端 | B 端 |
|---|---|---|---|
| 1 | 处理模式 | 沉浸式：叙事推进，不关注写法 | 审美式：放缓品读，关注语言质感 |
| 2 | 心理意象 | 高意象：感官丰富，画面感强 | 低意象：白描事实，不渲染感官 |
| 3 | 情感投入 | 高投入：直接写情绪和心理 | 低投入：情绪用动作/环境折射 |
| 4 | 语言可预测性 | 高平行：口语化，句式随意，流畅 | 高偏离：用词考究，句式有设计感 |
| 5 | 信息密度 | 高密度：每句推新信息，跳跃 | 低密度：信息逐步释放，有过渡 |
| 6 | 叙事距离 | 内聚焦：贴着 POV 角色呼吸 | 外聚焦：镜头拉远，冷静观察 |
| 7 | 对话对抗性 | 高对抗：交锋感强，互相挤压 | 低对抗：潜台词多，含蓄回避 |
每个维度的对比样例写法见 references/style-dimensions.md。
第二阶段：精调
第一阶段结束后，汇总结果。在用户有明确偏好的维度上，进一步细化。
精调方式：在用户偏好的方向上，写 2 段样例，只在该维度的程度上有差异。比如用户在「语言可预测性」维度选了「高平行」端，精调时给 A=极口语碎片感、B=中等口语有节奏。
不需要对所有 7 个维度精调。只对用户有强偏好的 3-4 个维度做精调即可，其余维度按粗筛结果直接用。
收束：写入小说宪法
测评完成后，更新 CLAUDE.md 中「小说宪法」的以下段落（直接替换原文，不创建新 section）：
叙事纹理：按 7 维度填入用户偏好位置。
处理模式：[落点] 心理意象：[落点] 情感投入：[落点]
语言可预测性：[落点] 信息密度：[落点]
叙事距离：[落点] 对话对抗性：[落点]
作者人格：从叙事纹理推导以下三个字段，其余字段保持不变：
- 叙事姿态 → 由「叙事距离」推导（内聚焦=贴着主角，外聚焦=冷眼旁观）
- 情感温度 → 由「情感投入」推导（高投入=热，低投入=冷，中性=温）
- 信息习惯 → 由「信息密度」推导（高密度=藏一半说一半，低密度=明牌全摊）
如果用户在测评中提到了喜欢的作品，追加到「风格锚点」。
向用户展示最终结果确认后再写入。
禁止
- 用抽象问题替代对比样例（「你喜欢快还是慢」）
- 对比样例脱离用户小说题材
- 跳过用户表示「差不多」的维度继续追问
- 所有维度都用同一组固定样例——必须根据用户题材即兴生成
- 测评结论不落盘
What ships with it
1 file 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.
- 11d ago First seen · 106 lines · 51 tokens per session scan A f8c1d3f9e51e
novel-taste is a skill published in the GitHub repository TulanCN/vibe-noveling (23 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 1,464 once invoked, about $0.0003 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…