writing-team-workbench: Skill for Claude Code

.claude/skills/04-liu-style/SKILL.md

04-liu-style is a skill for Claude Code from lisitan/writing-team-workbench. It costs 0 tokens per session (1,567 once invoked), scanned A, original, MIT.

A writing guide that studies a person's existing writing and turns its patterns into practical rules for new text. It also translates specialist language into words readers can understand.

In plain words
What is it for?
Use it to analyze writing samples, identify repeated or unwanted phrases, create style rules, rewrite passages, and flag signs of AI-generated writing.
Why use it?
It helps drafts sound like the intended writer and reduces generic, overly abstract, or assistant-like wording.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is lisitan/writing-team-workbench's own configuration. It tells Claude Code how to work on writing-team-workbench itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything writing-team-workbench configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lisitan/writing-team-workbench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lisitan/writing-team-workbench/main/.claude/skills/04-liu-style/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lisitan/writing-team-workbench

Made for: Claude Code.

Wrote 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.

agentmods badge for 04-liu-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/04-liu-style/github.svg)](https://agentmods.dev/skills/lisitan/writing-team-workbench/04-liu-style)
Your own site
<a href="https://agentmods.dev/skills/lisitan/writing-team-workbench/04-liu-style"><img src="https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/04-liu-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.

agentmods 80×15 button for 04-liu-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/lisitan/writing-team-workbench/04-liu-style"><img src="https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/04-liu-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,567 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01567
Opus 5 $0.00000 $0.00783
Sonnet 5 $0.00000 $0.00313
Haiku 4.5 $0.00000 $0.00157

Measured 11d ago against content hash fc724577a208, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

04-liu-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 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.

.claude/skills/04-liu-style/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

04-liu-style

提炼并套用用户个人表达风格。

适用场景

  • 文章结构已有,但还不像用户自己写的。
  • 用户提供了历史文章、风格样本或个人笔记库中有个人表达记录。

角色目标

给下一步写作者一套可执行的风格约束,避免通用 AI 腔。

资料源

  • 必读:当前项目 README.md项目状态.md资料.md过程/03-王整理.md
  • 必读:05-资产/个人风格画像.md
  • 必读:03-方法/AI写作痕迹检测规则.md
  • 必读:03-方法/去AI味写作规则.md
  • 可查:个人笔记库中的个人表达记录、历史想法、旧文章
  • 可读本地样本:用户指定的历史文章目录、粘贴样本,或风格画像缺失时的默认样本目录
  • 默认本地样本目录:<你的风格样本目录>,仅在用户要求重新校准风格或 个人风格画像.md 缺失时扫描
  • 可用样本抽取脚本:tools/style-samples/extract-style-samples.mjs
  • 默认不联网

可用能力

  • 历史表达样本召回:用 personal-notes-readonly.personal_notes_recall 找历史文章、口述记录、旧判断和高频表达。
  • 风格样本抽取:优先复用 05-资产/个人风格画像.md;只有用户要求重新校准风格、提供新样本,或风格画像缺失时,才读取 <你的风格样本目录>,提取标题、开头、转折、故事结构、金句句式和结尾方式。
  • 禁用表达识别:列出 AI 腔、套话、过度营销词。
  • AI 写作痕迹识别:按 03-方法/AI写作痕迹检测规则.md 识别本文最容易出现的 AI 指纹。
  • AI 味预防:识别 AI 助手式开头、机械结构、万能总结、过密洞察句和空泛大词。
  • 黑话翻译:把抽象概念、行业黑话和泛泛表述改成读者能感知的具体话。
  • 炫技削减:删掉显摆知识、制造距离、无助于理解的复杂表达。
  • 片段改写:把中性表达改成用户风格。
  • 写作约束生成:给 李文章 提供明确写法。
  • 项目状态回写:更新 项目状态.md 的当前阶段和下一步建议。

执行步骤

  1. 读取项目资料和结构。
  2. 读取 05-资产/个人风格画像.md;如果存在,以它作为默认风格底稿,不再扫描 1001 个样本。
  3. 只有用户明确要求“重新分析风格 / 更新风格画像 / 风格不对”、提供新样本,或 个人风格画像.md 缺失时,才读取默认本地样本目录。需要快速扫描时运行 node tools/style-samples/extract-style-samples.mjs <你的风格样本目录> 20
  4. 必要时用 personal_notes_recall 语义搜索历史表达样本;召回片段不足时,只用 personal_notes_get_note 读取必要详情。
  5. 读取 03-方法/AI写作痕迹检测规则.md03-方法/去AI味写作规则.md,提取本篇最容易出现的 AI 写作痕迹。
  6. 提取可执行风格规则。
  7. 列出禁用表达和替代表达。
  8. 给出 1-3 个示例改写片段。
  9. 写出给 李文章 的风格约束。
  10. 更新项目 项目状态.md:当前阶段写为 风格完成,下一步建议写为 /李文章

输出文件

过程/04-刘风格.md
项目状态.md

输出结构

# 04-刘风格

## 适用语气

## 常用表达习惯

## 禁用表达

## AI 味风险清单

- 高风险 AI 指纹:
- 禁用开头:
- 禁用结构词:
- 禁用万能总结:
- 需要克制的洞察句:
- 需要替换的空泛大词:
- 本篇最容易写假的地方:

## 黑话翻译规则

## 炫技冲动处理

## 句式节奏建议

## 个人笔记库风格参考

- 检索状态:
- 召回关键词:
- 命中样本:
- 可复用表达习惯:
- 不应复用的表达:

## 本地风格样本参考

- 样本目录:
- 样本命中:
- 开头方式:
- 转折方式:
- 故事结构:
- 金句句式:
- 结尾方式:
- 暂不模仿项:

## 示例改写片段

## 给下一步写作者的风格约束

质量检查

  • 风格约束具体到词、句式、节奏或改写示例。
  • 已读取并应用 03-方法/AI写作痕迹检测规则.md
  • 已读取并应用 03-方法/去AI味写作规则.md
  • 没有模仿名人。
  • 抽象概念有具体说法。
  • 禁用表达包含 AI 腔、套话和过度抽象词。
  • 已列出本篇 AI 味风险清单和替代表达方向。
  • 风格通过金线 4、7:克服炫技冲动,消除理解障碍。
  • 能直接指导正文写作。
  • 个人笔记库未配置时,已明确说明“个人笔记库未配置,未检索”。
  • 已优先读取 05-资产/个人风格画像.md;只有需要重新校准时才检查默认本地风格样本目录。
  • 已读取或创建 05-资产/个人风格画像.md
  • 没有大段复制样本文字。
  • 没有保存、更新、删除、打标签或创建远端知识库。

Read the full file on GitHub · 136 lines

Changes

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.

  1. 11d ago First seen · 136 lines · 0 tokens per session scan A fc724577a208

Subscribe to this mod's changes

04-liu-style is a skill published in the GitHub repository lisitan/writing-team-workbench (20 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,567 tokens. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens