hiro-inagawa/write-like-me

十秒后试试。 克隆仓库，对任意Markdown或文本文件运行检查器。无配置文件，无安装，仅限Python 3.8+：

Python 脚本/voice_check.py your-draft.md

它会打印每一个长破折号、填充短语、假词和AI语句，并附上行号和修正，然后是结论。如果你愿意，之后才会建立自己的语音档案。

一项Claude代码技能，分析你的写作方式，生成个性化的语音档案，用于写作和修改散文。它采用语言和心理测量方法，而非主观描述，从你自己的写作语料库中捕捉你的真实风格。

v2（2026年9月）新增内容。 该技能现在附带确定性检查器。草稿写完成后，python scripts/voice_check.py draft.md --profile voices/ /profile.json会报告每一次违规并附上行号和修正，并在硬性规则下以非零退出，因此语音通过代码强制执行，而非要求模型小心。每个语音还会获得一个机器可读的profile.json和一个金色测试集，并且每次规则变更都会有评估线束门。详细信息见下方“检查草稿”和“评估检查器”部分，以及 CHANGELOG.md。

Try it in ten seconds. Clone the repo and run the checker on any Markdown or text file. No profile, no installs, Python 3.8+ only:

python scripts/voice_check.py your-draft.md

It prints every em dash, filler phrase, hedge, and AI tell with a line number and a fix, then a verdict. Building your own voice profile comes after, if you want it.

A Claude Code skill that analyzes how you write and generates a personalized voice profile for writing and revising prose. It uses linguistic and psychological measurement methods rather than subjective descriptions to capture your actual style from a corpus of your own writing.

New in v2 (September 2026). The skill now ships a deterministic checker. After a draft is written, python scripts/voice_check.py draft.md --profile voices//profile.json reports every violation with a line number and a fix, and exits non-zero on a hard rule, so the voice is enforced by code instead of by asking the model to be careful. Each voice also gets a machine-readable profile.json and a golden test set, and an eval harness gates every rule change. Details are in the sections “Checking a draft” and “Evaluating the checker” below, and in CHANGELOG.md.

The same skill supports multiple voices. You can build one from your primary writing register, another from a different register, and another from an author whose style you want to study, and switch between them within the same skill.

---

HOW IT WORKS

The skill has two modes.

When no voice is built yet, it runs a 7-stage analysis that discovers your corpus, extracts and filters the text, measures approximately 50 stylometric features per register, mines rules from the measurements and any existing style notes, pauses for your review, generates the voice profile, and runs a held-out verification test.

When a voice is already built, it reads your profile and writes or revises prose in that voice. The universal anti-AI baseline (references/00-universal-baseline.md) is always active, on top of whatever your profile specifies.

---

GETTING STARTED

Step 1. Gather your writing corpus.

Create a folder and put your writing in it. Good sources:

• Export your Claude conversation history: Settings → Data Controls → Export Data, then unzip the file into the folder
• Emails you have written
• Essays, articles, blog posts, papers
• Notes, journals, or any other text in your own voice

Aim for at least 20,000 words. 50,000 or more gives more reliable results.

Step 2. Run the skill.