Skip to content
Back to search

anti-vibe-writing

MarketplaceWorks with Claude CodeGitHub

Make AI writing sound human, in English and 中文. A Claude Code / Codex / any-agent skill that strips templated phrasing, consultant-speak, markdown clutter, em-dashes, and copy-paste model residue while keeping the meaning.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked yesterday
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/weijt606--anti-vibe-writing/badge.svg)](/listings/weijt606--anti-vibe-writing)

HTML

<a href="/listings/weijt606--anti-vibe-writing"><img src="/api/listings/weijt606--anti-vibe-writing/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

At its core this is just a set of markdown rules (`SKILL.md` + `references/` + `assets/`), not tied to any one agent. Claude Code, Codex, Kimi, work-buddy, Hermes. If it can read files or take an instruction prompt, it can use this.

**Claude Code, one step:**

/plugin install anti-vibe-writing --marketplace weijt606/anti-vibe-writing

Then call `/anti-vibe-writing`, or just ask Claude to de-AI a draft. On Claude Code older than 2.1.275, run `/plugin marketplace add weijt606/anti-vibe-writing` first, then `/plugin install anti-vibe-writing@anti-vibe-writing`.

**Codex, Cursor, Gemini CLI and other agents, one step with the GitHub CLI** (gh 2.90 or newer):

gh skill install weijt606/anti-vibe-writing anti-vibe-writing --agent codex --scope user

Swap `codex` for `cursor`, `gemini-cli`, `claude-code`, `opencode` or any other name in `gh skill install --help`. It installs the latest release, and `gh skill update` pulls newer ones later. No GitHub CLI? Follow the three steps below.

**1. Get the rules**

Clone the repo, or just copy the `skills/anti-vibe-writing/` folder:

git clone https://github.com/weijt606/anti-vibe-writing.git

**2. Feed it to your agent (pick whichever fits)**

- **Simplest: just hand it the repo link.** No need to clone first: send `https://github.com/weijt606/anti-vibe-writing` and let the agent read `SKILL.md` and `references/` and configure itself. Works with any agent that can browse the web or run git. - **One-off (any agent)**: open `skills/anti-vibe-writing/assets/rewrite-prompt-template.md`. It has ready-made instruction blocks: Full Rewrite / Light Cleanup in English, and "中文改写(带负向约束)" for Chinese. Copy the block for your language and send it with your draft. - **Persistent**: put `SKILL.md` and the matching `references/*patterns-to-remove.md` wherever your agent loads context. Names differ by tool: - Agents with a skills directory (e.g. Claude Code): drop it in `~/.claude/skills/anti-vibe-writing/`, then call `/anti-vibe-writing` - Agents with a project-instructions file (e.g. Codex's `AGENTS.md`): write or include the rules there - Otherwise: paste into the system prompt / custom instructions / knowledge base

**3. (Optional) Name the scenario and mode**

One line of context changes the result a lot: - Scenario: "this is a tweet / a newsletter / a technical memo" - Loosen up: "make it feel personal" / "blog voice" → enables human-texture mode - Match a voice: paste a few of your own samples and say "learn my style" → enables learning mode

When in doubt, say nothing. The default clean mode is right for most drafts.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines
  1. {
  2. "name": "anti-vibe-writing",
  3. "owner": { "name": "weijt606", "url": "https://github.com/weijt606" },
  4. "metadata": {
  5. "description": "Make AI writing sound genuinely idiomatic, in English and Chinese."
  6. },
  7. "plugins": [
  8. {
  9. "name": "anti-vibe-writing",
  10. "source": "./",
  11. "description": "Bilingual (English + 中文) skill that removes the AI-generated feel from drafts while preserving meaning.",
  12. "version": "1.9.0",
  13. "category": "writing"
  14. }
  15. ]
  16. }
README.md · README · 196 lines
  1. # anti-vibe-writing
  2. ![anti-vibe-writing: a black-and-white comic banner, four panels showing AI writing going from em-dash-and-emoji clutter that gets auto-removed, through a human cleanup pass, to clean copy that reads human](./anti-vibe-writing-banner.png)
  3. [![English](https://img.shields.io/badge/README-English-1f6feb?style=flat-square)](./README.md)
  4. [![中文](https://img.shields.io/badge/README-%E4%B8%AD%E6%96%87-15803d?style=flat-square)](./README.zh.md)
  5. [![License: MIT](https://img.shields.io/badge/License-MIT-111111?style=flat-square)](./LICENSE)
  6. [![Skill version](https://img.shields.io/badge/skill-1.9.0-orange?style=flat-square)](./CHANGELOG.md)
  7. > 本 README 提供中英文两个版本:**English**(本页,默认)和 **[中文](./README.zh.md)**。点上方徽章切换。
  8. > **One goal: make AI sound genuinely idiomatic, 倍儿地道.**
  9. An agent writing skill that removes the AI-generated feel from documents. Works in English and Chinese, with optional modes for matching a specific author's voice.
  10. ![Before and after: a 73-word AI-drafted launch tweet full of emoji, an em-dash, marketing adjectives and a benefits list, rewritten into 37 words: "Most AI drafts get the facts right and still read like a machine put them together. Anti-Vibe Writing is a final editing pass that takes those assembly marks out, for drafts in English as well as Chinese."](./anti-vibe-writing-before-after.png)
  11. <sub>A real pair from [`examples/03-tweet.md`](./examples/03-tweet.md). More in [examples/](./examples/).</sub>
  12. It runs best as a final pass after drafting with Claude Code, Codex, or any LLM-backed agent. Its job is to keep the substance and remove the tells: templated phrasing, vague abstraction, consultant-speak, markdown-heavy formatting, over-structured outlines, the copy-paste residue chat and search models leave behind (`oaicite` / `turn0search0` / `[cite: 1]` / stray `【】` markers), and the cautious over-balancing that makes writing feel assembled.
  13. If the default "clean" mode is not enough, the skill also supports:
  14. - **Human-texture mode**: inject controlled irregularities (inversions, particles, half-sentences, non-standard punctuation) for personal voice
  15. - **Learning mode**: build a reusable host profile from real samples so future drafts sound like the person who would write them
  16. - **Scenario presets**: format and tone constraints tuned for tweets, Weibo, blogs, podcast show notes, and professional reports
  17. ## Quick start
  18. At its core this is just a set of markdown rules (`SKILL.md` + `references/` + `assets/`), not tied to any one agent. Claude Code, Codex, Kimi, work-buddy, Hermes. If it can read files or take an instruction prompt, it can use this.
  19. **Claude Code, one step:**
  20. ```text
  21. /plugin install anti-vibe-writing --marketplace weijt606/anti-vibe-writing
  22. ```
  23. Then call `/anti-vibe-writing`, or just ask Claude to de-AI a draft. On Claude Code older than 2.1.275, run `/plugin marketplace add weijt606/anti-vibe-writing` first, then `/plugin install anti-vibe-writing@anti-vibe-writing`.
  24. **Codex, Cursor, Gemini CLI and other agents, one step with the GitHub CLI** (gh 2.90 or newer):
  25. ```bash
  26. gh skill install weijt606/anti-vibe-writing anti-vibe-writing --agent codex --scope user
  27. ```
  28. Swap `codex` for `cursor`, `gemini-cli`, `claude-code`, `opencode` or any other name in `gh skill install --help`. It installs the latest release, and `gh skill update` pulls newer ones later. No GitHub CLI? Follow the three steps below.
  29. **1. Get the rules**
  30. Clone the repo, or just copy the `skills/anti-vibe-writing/` folder:
  31. ```bash
  32. git clone https://github.com/weijt606/anti-vibe-writing.git
  33. ```
  34. **2. Feed it to your agent (pick whichever fits)**
  35. - **Simplest: just hand it the repo link.** No need to clone first: send `https://github.com/weijt606/anti-vibe-writing` and let the agent read `SKILL.md` and `references/` and configure itself. Works with any agent that can browse the web or run git.
  36. - **One-off (any agent)**: open `skills/anti-vibe-writing/assets/rewrite-prompt-template.md`. It has ready-made instruction blocks: Full Rewrite / Light Cleanup in English, and "中文改写(带负向约束)" for Chinese. Copy the block for your language and send it with your draft.
  37. - **Persistent**: put `SKILL.md` and the matching `references/*patterns-to-remove.md` wherever your agent loads context. Names differ by tool:
  38. - Agents with a skills directory (e.g. Claude Code): drop it in `~/.claude/skills/anti-vibe-writing/`, then call `/anti-vibe-writing`
  39. - Agents with a project-instructions file (e.g. Codex's `AGENTS.md`): write or include the rules there
  40. - Otherwise: paste into the system prompt / custom instructions / knowledge base
  41. **3. (Optional) Name the scenario and mode**
  42. One line of context changes the result a lot:
  43. - Scenario: "this is a tweet / a newsletter / a technical memo"
  44. - Loosen up: "make it feel personal" / "blog voice" → enables human-texture mode
  45. - Match a voice: paste a few of your own samples and say "learn my style" → enables learning mode
  46. When in doubt, say nothing. The default clean mode is right for most drafts.
  47. ## Quick examples
  48. Curated before/after snippets live in [examples/](./examples/) for anyone scanning the repo. The full regression set stays under `references/`.
  49. ## Voice modes
  50. The skill runs in one of three modes:
  51. | Mode | When to use | Triggered by |
  52. |---|---|---|
  53. | Default (clean) | Most product, docs, and professional copy | Default, no opt-in needed |
  54. | Human texture | Personal blogs, founder notes, social posts | "Loosen it up" / "blog voice" / "make it feel personal" |
  55. | Learning mode | Series content, personal newsletters, voice-consistent comms | User provides samples, or asks "learn my style" |
  56. Modes combine with scenario presets (tweet / Weibo / blog / podcast / report). Conflict resolution rules are documented in `SKILL.md`.
  57. Human-texture mode also has a **social-only "casual typing" (随手打) layer** (off by default; turn it on by naming it, "casual typing" / "开随手打", or describing the effect, "like a quick phone post"; matched by intent, not a fixed phrase, and a plain "loosen it up" won't trigger it): a tiny amount of phone-typing texture on casual posts (dropped end punctuation, no capitalization, an omitted particle) that **never touches numbers, names, or links** and never makes meaning-changing typos. It's phone-typing texture, not error injection to dodge AI detectors.
  58. ## Use cases
  59. **The flagship case: Chinese posts on X.** Chinese AI-smell is most obvious on X: 赋能 / 打通, 首先 / 其次, three-clause parallelism, and machine-translation syntax give it away at a glance. This skill is built for exactly that: take an "obviously AI-written" Chinese post and make it read like something a person actually typed. See [`examples/07-tweet-zh.md`](./examples/07-tweet-zh.md) and [`examples/08-translationese-zh.md`](./examples/08-translationese-zh.md).
  60. Other common cases:
  61. - Social posts (X, Weibo, Jike, RedNote)
  62. - Blogs, newsletters, public WeChat articles
  63. - Podcast show notes and video scripts
  64. - README cleanup
  65. - Product docs and landing page copy
  66. - Proposals, founder notes, technical memos, internal reports
  67. ## Output goals
  68. - More human rhythm
  69. - More intentional structure
  70. - Cleaner phrasing
  71. - Stronger voice
  72. - Less AI smell
  73. - Sounds like a person chose every word
  74. ## Repository layout
  75. ```text
  76. .claude-plugin/
  77. plugin.json # Claude Code plugin manifest
  78. marketplace.json # lets `/plugin install` find it
  79. agents/
  80. README.md
  81. anti-vibe-writing-dev.agent.md # local, gitignored
  82. anti-vibe-writing-dev.agent.example.md
  83. skills/
  84. anti-vibe-writing/
  85. SKILL.md
  86. references/
  87. patterns-to-remove.md # English AI-smell
  88. chinese-patterns-to-remove.md # 中文 AI 味
  89. before-after-benchmarks.md # English benchmarks
  90. chinese-before-after.md # 中文基准
  91. common-problems-and-fixes.md
  92. human-passes.md
  93. human-texture.md # Optional irregularity
  94. learning-mode.md # Sample-driven style learning
  95. scenario-presets.md # Per-scenario constraints
  96. assets/
  97. final-pass-checklist.md
  98. rewrite-prompt-template.md
  99. host-profile-template.md # Fillable host profile
  100. style-extraction-prompt.md # One-shot extraction prompt
  101. examples/
  102. ...
  103. scripts/
  104. check-own-prose.sh # CI: project prose passes its own rules
  105. CHANGELOG.md
  106. CONTRIBUTING.md
  107. README.md # English (default)
  108. README.zh.md # Chinese
  109. LICENSE
  110. ```
  111. ## Working with the files
  112. Skill files are versioned. The developer agent file is local and gitignored by default, so contributors can adjust it without changing the public repository.
  113. To create a local agent file, copy `agents/anti-vibe-writing-dev.agent.example.md` to `agents/anti-vibe-writing-dev.agent.md`.
  114. If you want tool-specific auto-discovery, you may still need to mirror these files into the locations required by the target agent platform.
  115. ## Credits & references
  116. This skill stands on the shoulders of several open de-AI / humanizer projects and writeups. The patterns below were studied and adapted into this skill's own structure; the original analysis and wording belong to their authors. Thanks to:
  117. English:
  118. - [blader/humanizer](https://github.com/blader/humanizer): a 30-pattern humanizer skill (MIT). Informed the sentence-level tells: copula avoidance, negative parallelism, synonym cycling, false ranges, signposting, diff-anchored writing.
  119. - [hardikpandya/stop-slop](https://github.com/hardikpandya/stop-slop): AI-slop detection skill (MIT). Source of the optional five-dimension scoring pass (Directness / Rhythm / Trust / Authenticity / Density) in `assets/final-pass-checklist.md`.
  120. 中文 / Chinese:
  121. - [op7418/Humanizer-zh](https://github.com/op7418/Humanizer-zh): a 24-pattern Chinese humanizer skill, itself a Chinese adaptation of blader/humanizer (MIT). Informed the copula-"是" avoidance and synonym-cycling tells in the Chinese track.
  122. - ["AI 中文翻译腔" by yage.ai](https://yage.ai/share/ai-chinese-translationese-20260418.html): the analysis of Chinese translationese (物理动作动词写抽象 / 形容词加冒号预判读者 / 抽象名词主语). Informed the 翻译腔层 of `references/chinese-patterns-to-remove.md`.
  123. - [@dotey on X](https://x.com/dotey/status/2022774029220749538): discussion of de-AI prompt techniques (role-setting, negative constraints) that shaped the 改写心态 section and the Chinese rewrite prompt block.
  124. AI-writing research (added in 1.9.0):
  125. - [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing): the community-maintained catalog of AI-writing signs (October 2026 revision). Source of the mid-2026 vocabulary band, source-gap hedging, trailing participle analysis, placeholder and `utm_source` residue, the "Challenges and Future Outlook" ending, and the weak-evidence list.
  126. - [Graphite's 2026 model-tell analysis, reported by TechCrunch](https://techcrunch.com/2026/10/01/opus-5-5-loves-to-tell-you-this-matters-and-other-ai-writing-tells/): per-model frequencies behind "this matters" / "why X matters", "dependable", the 2026 contrast-frame variants, and the em-dash decline.
  127. - [《消除"罪证":给写作去除"AI味"的不完全手册(2026版)》](https://eu.36kr.com/zh/p/3824601267196037) by 蒋雨恬, first published on the WeChat account 有三思 U Sense and reprinted by 36kr: informed 过度拔高, the "最" (豆包体) rule, 学术套话 openers, 虚假范围, and the note about people misjudged over two dashes.
  128. These are independent projects and writeups with their own scope; this repo borrows their ideas and none of their code. If you maintain one of them and want a credit adjusted, open an issue.
  129. ## Contributing
  130. See [CONTRIBUTING.md](./CONTRIBUTING.md) for how to add new patterns, benchmarks, or scenario presets.
  131. ## License
  132. This project is open source under the MIT License. See `LICENSE`.
  133. ## Contributor notes
  134. - Preserve meaning. Sharpen the writing without changing facts.
  135. - Prefer concrete edits over generic style advice.
  136. - Keep structure only when it helps the reader.
  137. ## What's new
  138. **1.9.0**: catches up with how models write in late 2026 ("this matters", "not simply X", fewer em-dashes, Chinese 过度拔高 and "最" overuse, placeholders and tracking links), adds a list of features too weak to call a text AI-written on their own, and fixes places where the skill broke its own rules. Each version's full notes are in [Releases](https://github.com/weijt606/anti-vibe-writing/releases), and the whole history is in [CHANGELOG.md](./CHANGELOG.md).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.