Writing DNA Distiller

What it does

When your agent uses it

• Analyzing the writing style of an author or publication from past articles
• Preparing a style guide so new posts match an existing brand voice
• Comparing how two authors approach the same topic

Example prompts

• “Distill the writing DNA of our company blog from these articles.”
• “Analyze this columnist's structure and language habits and write Writing-DNA.md.”
• “Write a post about remote work in the style captured in our Writing-DNA.md.”

Requirements

• At least 20 complete articles saved as .md or .txt files

Workflow steps

7 steps, taken from the step headings in SKILL.md.

1. 1：原始素材收集
2. 2：元数据标注（_meta/ 目录）
3. 3：脚本分析（L1 表层语言）
4. 4：结构标注（L2 文章结构）
5. 5：选题与认知框架归纳（L3-L5）
6. 6：视觉风格与排版分析（L6）
7. 7：蒸馏产物整合

What it can do on your machine

Read from SKILL.md and the folder at commit ee3d97e. It shows what the files ask for, not the result of running them.

• Tool permissions

  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.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Writing DNA Distiller loads about 1.8k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 400 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~97

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.2k

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.

Safety

• WarningContains zero-width charactersSKILL.md:246

  这份文档应满足：⟨U+200B⟩**给任何一个没读过该账号/作者的人，他读完下笔能写出 70 分的近似风格文章——不仅文字像，视觉呈现也像。**

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.

SKILL.md

The full file from larashero3-dotcom/writing-dna-skill at commit ee3d97e, republished under its MIT licence (© larashero3-dotcom). 400 words, ~1,786 tokens.

name

writing-dna-skill

description

从至少 20 篇完整文章中蒸馏可复用的写作 DNA，分析语言、文章结构、选题逻辑、素材策略、认知框架和视觉风格，并生成 Writing-DNA.md；按该 DNA 写作时会读取全部蒸馏产物和 5 篇相关原文。用于中英文作者、账号、品牌或出版物的风格分析与一致性写作。 Distill reusable Writing DNA from at least 20 complete articles for Chinese or English authors, publications, brands, and accounts; use for language, structure, topic logic, source strategy, cognitive-frame, and visual-style analysis.

YYYY-MM-DD 内容类型 文章标题-来源.md

{
  "title": "文章标题",
  "date": "YYYY-MM-DD",
  "author": "作者姓名",
  "column": "内容系列名称",
  "article_type": "访谈 | 深度分析 | 短评 | 观察 | 综述",
  "topic_tags": ["AI", "创业", "商业模式"],
  "hook_type": "问题式 | 场景式 | 数据式 | 观点式 | 悬念式",
  "structure_pattern": "总-分-总 | 时间线 | 对比式 | Q&A",
  "source_types": ["一手素材", "公开资料", "案例对比"],
  "word_count": 3200,
  "notable": "值得标注的特殊之处（可留空）"
}

[开头 hook 类型] + [字数]
→ [第一转折点/核心问题引入]
→ [正文结构：总-分 / 对比 / 时间线 / Q&A]
→ [结尾处理方式：收束 / 悬念 / 呼吁 / 自然结束]

引题段（150-300字）
  → 为什么此时此人值得聊（1句）
  → 关键背景（2-3句）
  → 本篇核心问题（1-2句）
正文 Q&A
  → 每个大话题前有小标题（4-8字）
  → 每小节 3-6 轮对话
结尾
  → 多为自然收束，无刻意升华

写作 DNA 文档（Writing-DNA.md）
├── 语言特征（来自 L1）
├── 结构模板（来自 L2，按类型分类）
├── 选题判断标准（来自 L3）
├── 素材使用规范（来自 L4）
├── 核心认知框架（来自 L5）
└── 视觉风格指南（来自 L6：配图策略 + 排版 + 色彩）

账号或作者名称/
├── raw/                    # 原始文章语料（.md 格式）
├── _meta/                  # 元数据标注（JSON 或 .md）
├── 语言DNA.md              # English: language-dna.md
├── 文章结构模板.md          # English: structure-patterns.md
├── 写作视角与认知框架.md    # English: cognitive-framework.md
├── 视觉风格指南.md          # English: visual-style-guide.md
├── Writing-DNA.md          # 最终整合文档（可直接嵌入 skill）
└── index.html              # 可选：可视化展示页面

© larashero3-dotcom, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. 1 hidden character (zero-width or bidirectional) removed. Raw file

Files

SKILL.md and 41 other files (references, assets) in the repository root of larashero3-dotcom/writing-dna-skill.

• SKILL.md
• .gitignore
• CONTRIBUTING.md
• LICENSE
• README.en.md
• README.md
• agents/openai.yaml
• assets/writing-dna-hero-en.png
• assets/writing-dna-hero-zh.png
• docs/release-checklist.md
• docs/usage-boundaries.md
• examples/format-only/README.md
• examples/format-only/_meta/.gitkeep
• examples/format-only/raw/.gitkeep
• … and 28 more

Open the folder on GitHubat commit ee3d97e