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 jianshuo/claude-skills --skill wjs-distilling-stylegit clone --depth 1 https://github.com/jianshuo/claude-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/jianshuo/claude-skills/wjs-distilling-style)<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-distilling-style"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-distilling-style/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/jianshuo/claude-skills/wjs-distilling-style"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-distilling-style.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 | $0.00094 | $0.03444 |
| Opus 5 | $0.00047 | $0.01722 |
| Sonnet 5 | $0.00019 | $0.00689 |
| Haiku 4.5 | $0.00009 | $0.00344 |
Grade A, and why
wjs-distilling-style 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
蒸馏文风 · Style Fingerprint
核心原则
风格不是形容词，是指纹。能照着复现的，才叫蒸馏出来了。
裸模型做这件事会犯三个错（已实测）：(1) 风格观察临时拼凑、混入内容立场、不可复用；(2) 改写后没人盲测，自己既当运动员又当裁判，悄悄滑回平庸 AI 腔；(3) 改写时擅自加料删料，把原文事实改没了。这个 skill 用结构化指纹 + 独立判官盲测 + 事实骨架纪律钉死这三点。
两个模式：蒸馏（样本 → Style Card 文件）和改写（目标文章 + Style Card → 改写稿，带盲测闭环）。
默认走精简版（用户约定）：日常蒸馏 / 改写任务优先用
references/oneshot-prompts.md的一次性 prompt（Prompt A 改写 / Prompt B 蒸馏）——9 轴指纹 + 锚点 + 事实骨架纪律 + AI 露馅 6 反制都在，只把多轮判官盲测 / 图灵测 / 回炉换成一轮内联自检。够用、一把过。只有要硬验一张卡到底像不像（发布级、批量伪造）时，才回到下面的完整闭环（判官 subagent + 图灵盲测）。
何时用
- 用户给几篇某作者的文章，想提炼他怎么写
- 用户想把一段话 / 一篇稿 / 一份 AI 生成的文本改成某作者的味儿
- 不适用：用户要的是这个人怎么思考（心智模型、世界观、角色扮演）→ 那是
huashu-nuwa，不是这里；本 skill 只管怎么写。
存储（独立库，不进公开 repo）
~/code/style-cards/<author-slug>/
samples/ # 喂进来的原始样本
style-card.md # 蒸馏出的 Style Fingerprint（真源，人可读可手改）
rewrites/ # 历史改写稿（可选）
wjs-* skill 会自动同步到公开 repo，所以别人的稿子和卡片放这个独立库，不外泄。库或作者目录不存在就先建。
Style Fingerprint — 9 轴
每一轴写三件事：观察（样本里看到什么）、可执行规则（改写时怎么照做）、锚点原句（从样本摘 2–3 句真实原句）。规则会骗人，原句不会——没有锚点的轴等于没蒸馏。
| # | 轴 | 抓什么 |
|---|---|---|
| 1 | 句子节奏 | 长短句分布、长短交替的拍子、标点签名（破折号/省略号/问句/感叹） |
| 2 | 段落长度 | 平均段长、有没有单句成段、长段密度 |
| 3 | 词汇 | 高频词、口头禅、自造词、人称、成语/网络语倾向、中英混用、用词雅俗 |
| 4 | 语气腔调 | 自信度、距离感（亲密 vs 客观）、正式度、幽默 |
| 5 | 论证结构 | 断言先行 vs 层层铺垫、是否用小标题/列表/表格、推进路径 |
| 6 | 比喻运用 | 家常 vs 抽象、频率、抽象↔具体之间怎么架梯子 |
| 7 | 情绪强度 | 情绪温度、克制 vs 喷发、感叹密度 |
| 8 | 开头与收尾 | 怎么起（断言/场景/钩子）、怎么落地收束 |
| 9 | 雷区 | 他绝不会做的事（如不用小白提问钩子、不写没验证过的、不用某类书面词） |
模板见 references/style-card-template.md，直接照着填。
别把内容立场写进指纹：「他爱唱反调」「他三观是 X」是想法不是文风。指纹只抓「怎么写」——同一个观点换了他来写会长什么样。
「调料不是公式」校准注（写进每张卡）：签名动作（造词 / 家常比喻 / 单句成段 / 破折号）是工具不是清单。短内容就短写，别把每个签名动作都堆满——堆满就是拙劣模仿，不是那个人。
9 轴 → 几十个细颗粒维度（推荐成卡形态）：9 轴是起手拆解的脚手架。成卡时拆成 ~30–45 个细颗粒可执行维度，分组放表格（句子与标点 / 段落 / 词汇 / 语气 / 论证 / 比喻 / 开头 / 结尾 / 锚点纪律 / 雷区…），每维一句「怎么样的」规则。蒸馏过程靠锚点原句校准（必须，否则规则空转），但成卡里例子要精简——例子不一定典型、容易被当公式照搬，规则才有通用性。这是给「别的模型批量照着写」用的形态。
蒸馏流程
- 样本入库
samples/。建议 3–6 篇，覆盖不同主题 / 长度。少于 3 篇要明确提示用户：指纹会不稳、容易把一篇的偶然写法当成签名。 - 长样本起一个 subagent 做 9 轴拆解，避免污染主上下文，只回收结构化结果。
- 逐轴分析，每轴必须摘锚点原句。
- 写出
style-card.md（照模板），让用户过目 / 手改。
What ships with it
6 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.
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.
- 13d ago First seen · 128 lines · 94 tokens per session scan A cbd4255dd9cd
wjs-distilling-style is a skill published in the GitHub repository jianshuo/claude-skills (129 stars, last pushed 23d ago), licensed MIT. It adds 94 tokens to every session and 3,444 once invoked, about $0.0005 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
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.