A skill your agent uses when the user wants to capture a writer's voice from a few sample articles and rewrite text to sound like that author — "蒸馏文风", "提炼XX的风格", "把这篇改成XX的味儿", "学某某笔法改写", "mimic…
$ npx skills add jianshuo/claude-skills --skill wjs-distilling-style -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jianshuo/claude-skills wjs-distilling-style --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jianshuo/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/wjs-distilling-style .claude/skills/wjs-distilling-style && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "wjs-distilling-style" agent skill from https://github.com/jianshuo/claude-skills/tree/main/wjs-distilling-style into .claude/skills/wjs-distilling-style/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wjs-distilling-style", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jianshuo/claude-skills/tree/main/wjs-distilling-styleType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jianshuo/claude-skills --skill wjs-distilling-style -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jianshuo/claude-skills wjs-distilling-style --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jianshuo/claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/wjs-distilling-style .agents/skills/wjs-distilling-style && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "wjs-distilling-style" agent skill from https://github.com/jianshuo/claude-skills/tree/main/wjs-distilling-style into .agents/skills/wjs-distilling-style/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wjs-distilling-style", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jianshuo/claude-skills --skill wjs-distilling-style -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jianshuo/claude-skills wjs-distilling-style --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jianshuo/claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/wjs-distilling-style .cursor/skills/wjs-distilling-style && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "wjs-distilling-style" agent skill from https://github.com/jianshuo/claude-skills/tree/main/wjs-distilling-style into .cursor/skills/wjs-distilling-style/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wjs-distilling-style", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jianshuo/claude-skills.git --path wjs-distilling-style--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jianshuo/claude-skills --skill wjs-distilling-style -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jianshuo/claude-skills wjs-distilling-style --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jianshuo/claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/wjs-distilling-style .gemini/skills/wjs-distilling-style && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "wjs-distilling-style" agent skill from https://github.com/jianshuo/claude-skills/tree/main/wjs-distilling-style into .gemini/skills/wjs-distilling-style/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wjs-distilling-style", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jianshuo/claude-skills wjs-distilling-styleInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jianshuo/claude-skills --skill wjs-distilling-style -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jianshuo/claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/wjs-distilling-style .github/skills/wjs-distilling-style && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "wjs-distilling-style" agent skill from https://github.com/jianshuo/claude-skills/tree/main/wjs-distilling-style into .github/skills/wjs-distilling-style/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wjs-distilling-style", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jianshuo/claude-skills --skill wjs-distilling-style -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jianshuo/claude-skills wjs-distilling-style --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jianshuo/claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/wjs-distilling-style .opencode/skills/wjs-distilling-style && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "wjs-distilling-style" agent skill from https://github.com/jianshuo/claude-skills/tree/main/wjs-distilling-style into .opencode/skills/wjs-distilling-style/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wjs-distilling-style", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
wjs-distilling-styleA skill your agent uses when the user wants to capture a writer's voice from a few sample articles and rewrite text to sound like that author — "蒸馏文风", "提炼XX的风格", "把这篇改成XX的味儿", "学某某笔法改写", "mimic…
Wjs Distilling Style is an agent skill from jianshuo/claude-skills. Use when the user wants to capture a writer's voice from a few sample articles and rewrite text to sound like that author — "蒸馏文风", "提炼XX的风格", "把这篇改成XX的味儿", "学某某笔法改写", "mimic this writer", "match this author's style", "style transfer". Works for any author, 王建硕 included.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `DESIGN.md`, `references/ai-tells.md` and `references/judge-prompt.md`).
It sits in Media & Creative. The repository describes itself as: 13 Claude Code skills for video production (transcribe / translate / dub / multicam / subtitles / reframe) + WeChat publishing. Compatible with Claude Code, OpenAI Codex CLI… The licence is MIT.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit b2690f5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are dot).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Wjs Distilling Style loads about 1.2k tokens when it runs, and up to ~5.8k if it reads all its reference files. Until then it costs about 73 tokens; SKILL.md has 322 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from jianshuo/claude-skills at commit b2690f5, republished under its MIT licence (© jianshuo). 322 words, ~1,244 tokens.
.claude/skills/wjs-distilling-style/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.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）。
huashu-nuwa，不是这里；本 skill 只管怎么写。~/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。
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。
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。style-card.md（照模板），让用户过目 / 手改。digraph rewrite {
"抽事实骨架" [shape=box];
"按9轴改写" [shape=box];
"独立判官盲测" [shape=box];
"达标?" [shape=diamond];
"拿判官具体意见回炉" [shape=box];
"对照骨架查事实" [shape=box];
"交稿" [shape=box];
"抽事实骨架" -> "按9轴改写" -> "独立判官盲测" -> "达标?";
"达标?" -> "拿判官具体意见回炉" [label="否, 最多2-3轮"];
"拿判官具体意见回炉" -> "独立判官盲测";
"达标?" -> "对照骨架查事实" [label="是"];
"对照骨架查事实" -> "交稿";
}references/judge-prompt.md。它输出：逐轴相似度评分（1–5）、具体出戏句列表、缺失/过载的签名动作。判官子 agent 是「同一个模型既当运动员又当裁判」的唯一解药。自己读一遍觉得挺像 ≠ 像——这正是裸模型滑回平庸的入口。
上面的相似度判官问「像不像」；要量化验证整张卡，再上一关图灵判别盲测：把 AI 仿写混进真迹里，让一个崭新、不同模型的判官盲猜每篇是「真迹」还是「AI 仿的」，正确率 ≤ 50%（瞎猜）算过。完整操作（选样 / 只给标题+30字从零写 / 剥光元信息归一化 / 异模型判官读整批 / 算分回炉 / 部署到 jianshuo.dev profile）见 references/turing-blindtest.md。
跑这一关前，先读 references/ai-tells.md——9 轮实测逼出的 AI 最易露馅的 6 处（缺真实专名 / 结尾太圆 / 推进太顺 / 鸡汤教科书化 / 批次指纹 / 文章原型不匹配）+ 逐条反制。把这 6 条反制写进每张风格卡的尾部（裸模型照 9 轴写仍会稳定踩这 6 个坑）。
诚实的天花板（别给用户画大饼）：平衡盘里判官对真迹召回近 100%，正确率地板就是 50%，「稳定压到 50% 以下」基本做不到。但单篇经常蒙混（纯记叙/观察型常 4/6 骗过很毒的判官，一点题落金句就被抓）。所以卡的主场是润色/改写作者已有真实素材，不是凭空批量伪造整本文集。
| 错误 | 后果 | 修正 |
|---|---|---|
| 指纹只有抽象规则，没锚点原句 | 改写时规则空转，套不出味儿 | 每轴强制摘 2–3 句真实原句 |
| 把内容立场当文风 | 改写跑偏成换观点 | 指纹只问「怎么写」 |
| 跳过判官盲测 | 滑回平庸 AI 腔自己不知道 | 判官必做，盲、独立 |
| 改写顺手加料删料 | 原意被改 | 先抽事实骨架，改写不增不减 |
| 签名动作堆满 | 拙劣模仿 | 短内容短写，调料不是公式 |
| 图灵测给写手太多信息 | AI 复述原文，测了个寂寞 | 只给标题 + ≤30 字中心思想，从零写 |
| 盲测不归一化格式 | 判官靠格式而非文风取胜 | 剥元信息 + 抹 markdown + 统一段间空行 |
| 一批 AI 同款签名动作 | 批次指纹被一锅端 | 每篇换不同的崩裂/收尾，原型与真迹对齐 |
| AI 文末非要升华点题 | 落「可迁移金句」最招判官 | 纯记叙不点题，结尾散开不收口 |
© jianshuo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 6 other files (references) in wjs-distilling-style of jianshuo/claude-skills.
Open the folder on GitHubat commit b2690f5
Wjs Distilling Style next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Wjs Distilling Style this skilljianshuo/claude-skills | 131 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Xiaohei Chinese Article Illustrationshelloianneo/ian-xiaohei-illustrations | 12k | 3 repos | ~470 | Automated safety check: Warn | MIT | |
| Podcast Generationbytedance/deer-flow | 84k | 2 repos | ~2.2k | Automated safety check: Pass | MIT | |
| ManimGL Best Practicesadithya-s-k/manim_skill | 1.2k | 2 repos | ~1.9k | Automated safety check: Pass | CC-BY-NC-4.0 | |
| Blog AudioAgriciDaniel/claude-blog | 2.3k | 1 repos | ~2.2k | Automated safety check: Notes | MIT | |
| Xhs Visual Directorziguishian/xhs-visual-director-skill | 1.4k | — | ~2.2k | Automated safety check: Pass | MIT |
helloianneo/ian-xiaohei-illustrations
Plans and generates 16:9 hand-drawn illustrations for Chinese articles on a white background, with a recurring black character and a few red, orange and blue handwritten notes.
bytedance/deer-flow
Turns written content into a two-host conversational podcast MP3 with a transcript, by drafting a JSON script and running a text-to-speech script.
adithya-s-k/manim_skill
Collects best-practice rules and tested example scripts for ManimGL, the 3Blue1Brown OpenGL animation engine, covering scenes, mobjects, Tex rendering, 3D and interactive mode.
AgriciDaniel/claude-blog
Generate audio narration of blog posts using Google Gemini TTS.
ziguishian/xhs-visual-director-skill
A skill your agent uses when planning, redesigning, or reviewing Xiaohongshu carousel visuals, covers, 3:4 image posts, page-by-page visual direction, image-generation prompts, style selection…
axtonliu/smart-illustrator
Generates article illustrations, batch slide infographics and cover images from your text, using Gemini, Mermaid or Excalidraw engines and a prompt-only mode.
jianshuo/claude-skills
A skill your agent uses when the user has a long-form video (interview / lecture / podcast / conversation) and a transcript SRT, and wants to extract 3–6 stand-alone topical short clips from it.
jianshuo/claude-skills
Upload one or many videos to YouTube. An agent skill from jianshuo/claude-skills.
jianshuo/claude-skills
A skill your agent uses when migrating a WordPress site to a Hugo static site on GitHub Pages from a WXR export (.xml) plus the wp-content/uploads folder — preserving /archives/<id/ URLs, localizing…
jianshuo/claude-skills
A skill your agent uses when the user has a video + an SRT and wants the subtitles either burned into the pixels (libass, always-visible) or soft-muxed as a togglable track.
jianshuo/claude-skills
A skill your agent uses when the user complains about spam on his X/Twitter posts — 同城面付 / 寻固炮 / 线下上门 / 免费破处 这类引流号在他推文下刷的 emoji 垃圾回复 — and wants them removed.
jianshuo/claude-skills
A skill your agent uses when the user wants a book turned into YouTube chapter videos — 每章用 VoiceDrop 读书的有声书 mp3 做音轨，配 GPT Image 2 画面和中心思想大字，输出 1920×1080 横屏视频发 YouTube。Triggers — "把这本书做成视频"…
Categories
A skill your agent uses when the user wants to capture a writer's voice from a few sample articles and rewrite text to sound like that author — "蒸馏文风", "提炼XX的风格", "把这篇改成XX的味儿", "学某某笔法改写", "mimic…. Wjs Distilling Style is an agent skill from jianshuo/claude-skills. Use when the user wants to capture a writer's voice from a few sample articles and rewrite text to sound like that author — "蒸馏文风", "提炼XX的风格", "把这篇改成XX的味儿", "学某某笔法改写", "mimic this writer", "match this author's style", "style transfer".
Wjs Distilling Style fits situations like: the user wants to capture a writers voice from a few sample articles and rewrite text to sound like that author — 蒸馏文风; mimic this writer; match this authors style.
Run `npx skills add jianshuo/claude-skills --skill wjs-distilling-style -a claude-code`. Or copy the skill folder (wjs-distilling-style in jianshuo/claude-skills) into .claude/skills/wjs-distilling-style in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jianshuo/claude-skills --skill wjs-distilling-style -a codex`. Or copy the skill folder (wjs-distilling-style in jianshuo/claude-skills) into .agents/skills/wjs-distilling-style in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jianshuo/claude-skills --skill wjs-distilling-style -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wjs-distilling-style, .gemini/skills/wjs-distilling-style, .github/skills/wjs-distilling-style and .opencode/skills/wjs-distilling-style in your project.
SKILL.md names no scripts, command-line tools or credentials: Wjs Distilling Style is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Wjs Distilling Style is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Wjs Distilling Style: Xiaohei Chinese Article Illustrations (helloianneo/ian-xiaohei-illustrations, 12k stars), Podcast Generation (bytedance/deer-flow, 84k stars), ManimGL Best Practices (adithya-s-k/manim_skill, 1.2k stars) and Blog Audio (AgriciDaniel/claude-blog, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jianshuo (a GitHub user) maintains it in jianshuo/claude-skills, which has 131 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on August 20, 2026.
Source: jianshuo/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
