lieflat-less-ai-tone SKILL.md skillA
lieflat-less-ai-tone from larashero3-dotcom/writing-dna-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add larashero3-dotcom/writing-dna-skill/lieflat-less-ai-tone@git:20260824.ee3d97ePins git:20260824.ee3d97e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- larashero3-dotcom/writing-dna-skill
- Path
skills/lieflat-less-ai-tone/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260824.ee3d97e, committed Aug 24, 2026
- First version recorded
- Aug 20, 2026
- Size
- 28,453 bytes
- Repository stars
- 3,000
- License
- a license file GitHub does not identify
按 SKILL.md 明确列出的规则识别并改写写作中的 AI 痕迹。只能处理清单内的问题；未命中规则的文字必须原样保留，也不能改变文章框架。适用于写作完成后的成稿清理。 Remove AI writing tells using an explicit whitelist of rules; leaves unmatched text untouched.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 去AI味 识别并改写文本中的 AI 写作痕迹。规则基于人类文章与多个模型输出的实测对比整理，每条都有可定位的触发标记。先判断体裁，再处理 AI 味。不能为了“像人写的”强加人称、口语或短段落。 ## 与写作蒸馏器配合 本 skill 是写作流程的最后一道工序。先蒸馏出 Writing-DNA，按 DNA 写作，最后用本 skill 去掉 AI 痕迹。 同一目录下存在蒸馏产物时，先读 `语言DNA.md`（英文 `language-dna.md`）再改写。本 skill 多条规则需要判断“原语体”。第 7 条对文学体裁按原有风格判断，第 4 条和第 5 条要看作者本来的标点习惯，第 8 条要看原文有没有给出具体数据。蒸馏产物里的句长分布、标点习惯和用词偏好就是判断依据。 蒸馏产物与本规则冲突时，以蒸馏产物为准。那是目标作者的真实写法，不是 AI 痕迹。 ## 硬性边界（最高优先级） 本 skill 采用白名单式改写。只能处理“改写规则”中明确列出的规范，不能凭一般写作经验修改其他内容。没有命中任何规则的句子必须逐字保留。 一句话即使命中规则，也只能改动解决该问题所必需的部分。不得顺便润色，不得替换没有问题的词语，不得调整语气、详略或信息密度。对某处是否命中规则没有把握时，保持原文。 文章结构不在处理范围内。标题层级、章节顺序、段落数量与顺序、列表、表格、引用和代码块的位置必须原样保留。除非用户另行明确要求，否则不能概括、扩写、删减观点或重组论证。 ### 信息守恒：不许新增，不许删减 原文的观点和事实必须完整保留。以下内容绝不能凭改写添加，哪怕只是为了让句子读起来更具体、更像人写的。 - 姓名、机构名、职务、地名 - 数字、比例、金额、时长、次数 - 日期、时间、先后顺序 - 引语、对话、别人的说法 - 引用来源、出处、链接 - 因果、动机、心理活动 - 任何原文没写的细节、场景或案例 反方向同样禁止。不能删掉原文的观点、结论、限定词和让步（“可能”“通常”“在某些情况下”“据说”）。把“可能提升”改成“提升”是篡改语气强度，不是去 AI 味。 判断办法：改写后的每个实词，都要能在原文里指出出处。指不出来就是新增，必须撤销。 “把抽象写具体”不是本 skill 的职责。原文抽象就让它抽象。第 8 条只允许把原文已有的具体数据提到概括词的位置，不允许自己造数据。 ## 用法 用户丢一段文字过来，你： 1. 先锁定原文框架。标题层级、章节顺序、段落顺序、列表、表格、引用和代码块的位置都不能改 2. 只按“改写规则”逐项检查，不增加清单外的判断标准 3. 只改明确命中规则的文字，并把改动控制在解决该问题所需的最小范围。其他文字逐字保留，信息不增不减 4. 按文末验收清单复查，再输出改写后的全文 …
Read the whole file at its exact version.
How to install
mdr add larashero3-dotcom/writing-dna-skill/lieflat-less-ai-tone@sha256:16661f5c97fc856dThe line at the top of this page pins the label git:20260824.ee3d97e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ndn3i5h7lzp7rtjg)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 20, 2026 and Aug 24, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260824.ee3d97e latest | 2026-08-24 | ee3d97e | 28,453 B | A | view · diff |
| git:20260820.d5145ef | 2026-08-20 | d5145ef | 26,948 B | A | view · diff |
| git:20260820.5b04840 | 2026-08-20 | 5b04840 | 29,250 B | A | view · diff |
| git:20260820.06de0e8 | 2026-08-20 | 06de0e8 | 29,319 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (28453 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
larashero3-dotcom/writing-dna-skill · 3,000 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ndn3i5h7lzp7rtjg GET https://markdownregistry.com/api/v1/resolve?ref=larashero3-dotcom/writing-dna-skill/lieflat-less-ai-tone GET https://markdownregistry.com/api/v1/blob/16661f5c97fc856d21d7bd0b33471e7f0ca20fbc13c4d5136ef5288680bea7d1
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from larashero3-dotcom/writing-dna-skill
Every file in larashero3-dotcom/writing-dna-skill