remove-ai-flavor

remove-ai-flavor is a skill for Claude Code, Codex from ItamarZand88/awesome-agent-conventions. It costs 0 tokens per session (1,853 once invoked), scanned A, original, MIT.

A writing guide for making text sound more natural and less like an AI-generated draft. It identifies template-like wording, empty claims, translation-like phrasing, and overused formatting while preserving the author’s meaning and tone.

In plain words
What is it for?
Use it to review or rewrite articles, scripts, speeches, lessons, product copy, and other supplied text when the goal is a more human reading style.
Why use it?
It helps turn a mechanically written draft into clearer prose without changing its facts or viewpoint.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review or rewrite articles, scripts, speeches, lessons, product copy, and other supplied text when the goal is a more human reading style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/itamarzand88/awesome-agent-conventions/remove-ai-flavor
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ItamarZand88/awesome-agent-conventions --skill remove-ai-flavor
Clone the repo
git clone --depth 1 https://github.com/ItamarZand88/awesome-agent-conventions

Made for: Claude Code, Codex.

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 remove-ai-flavor

README.md
[![agentmods](https://agentmods.dev/badge/skills/itamarzand88/awesome-agent-conventions/remove-ai-flavor/github.svg)](https://agentmods.dev/skills/itamarzand88/awesome-agent-conventions/remove-ai-flavor)
Your own site
<a href="https://agentmods.dev/skills/itamarzand88/awesome-agent-conventions/remove-ai-flavor"><img src="https://agentmods.dev/badge/skills/itamarzand88/awesome-agent-conventions/remove-ai-flavor/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 remove-ai-flavor

Your own site · 80×15
<a href="https://agentmods.dev/skills/itamarzand88/awesome-agent-conventions/remove-ai-flavor"><img src="https://agentmods.dev/badge/skills/itamarzand88/awesome-agent-conventions/remove-ai-flavor.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 1,853 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.
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 $0.01853
Opus 5 $0.00000 $0.00927
Sonnet 5 $0.00000 $0.00371
Haiku 4.5 $0.00000 $0.00185

Measured 12d ago against content hash 60ae233babb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

remove-ai-flavor 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 12d 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.

conventions/skill-md/examples/content-comms/remove-ai-flavor/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: remove-ai-flavor description: 去除 AI 味道的文章风格优化技能。用于识别并改写文章、公众号稿、自媒体稿、口播稿、演讲稿、课程稿、产品文案中的 AI 痕迹、模板腔、资料味、翻译腔、空洞大词、过度金句、破折号滥用、bullet 堆叠、动不动加粗等问题;当用户说“去 AI 味”“去除 AI 痕迹”“不像 AI 写的”“更像人写的”“更自然”“别太机器味”“去掉模板感”“改得像公众号终稿”时使用。不用于事实核查、从零选题策划、论文转公众号、纯标题生成或追求 AI 检测器通过率。

去除 AI 味道

目标

把内容从“正确但像 AI 总结”改成“自然、具体、像人在认真讲一件事”。

优先保留作者的观点、判断、材料和语气,不把文章改成另一种人格。这个 skill 不是为了追求“检测器通过”,而是为了提升真实读者的阅读感。

使用边界

如果用户没有提供原文、文件路径或明确的待改片段,先索要文本,不要凭空示范。

这个 skill 只处理表达质感和读者阅读感,不负责事实核查、资料补充、选题策划、标题生成或平台格式排版。遇到事实可疑、数据缺来源、观点缺证据时,保留原意并提醒用户需要另行核查。

判断模式

先判断用户要哪种处理深度:

  • 诊断模式:用户说“看看哪里有 AI 味”“先审一下”“帮我标出来”。只输出问题清单和改写建议,不直接重写全文。
  • 轻改模式:文章基本可用,只是有少量套话、硬句、破折号、冗余连接。做最小改动。
  • 深改模式:文章像资料整理稿、翻译稿、AI 草稿或提纲稿。需要重写开头、过渡、小标题、结尾和部分段落。
  • 终稿模式:用户明确要“可发布版本”“公众号终稿”“直接改好”。输出完整优化稿,并说明关键修改。

如果用户没有说明,默认使用 轻改模式;如果原稿明显不像成稿,升级到 深改模式 并说明原因。

Gotchas

  • 不要为了“像人写”而加入夸张情绪、口水话或油腻表达。
  • 不要为了顺滑改掉作者立场、删掉关键限定条件,或发明原文没有的案例和结论。
  • 不要把专业文章改成鸡汤、营销腔或段子文。
  • 不要承诺可以绕过 AI 检测器;目标是让真实读者读起来更自然。
  • 不要把所有列表都强行改成自然段;真正方便扫描的列表要保留。

工作流程

复制此清单并跟踪进度:

去 AI 味进度:
- [ ] 步骤 1:判断处理深度
- [ ] 步骤 2:保留核心观点、事实和作者语气
- [ ] 步骤 3:识别 AI 味、资料味、翻译腔和模板句
- [ ] 步骤 4:按模式输出诊断、局部改写或完整终稿
- [ ] 步骤 5:自查自然度、具体性、节奏和可发布性

1. 先保留骨架

改写前先抓住这些内容:

  • 文章最核心的一句话
  • 必须保留的事实、数据、案例、术语
  • 作者原本的立场和语气
  • 读者为什么要读完

不要为了顺滑删掉关键细节。不要擅自加入原文没有支持的新结论。

2. 再清理味道

优先处理这些高频问题:

  • 套路开场:在这个时代、随着技术发展、众所周知
  • 生硬连接:综上所述、基于此、由此可见、值得一提的是
  • 空洞大词:卓越、革命性、颠覆性、重要意义、巨大价值
  • 假金句:听起来很猛,但没有信息增量
  • 破折号滥用:用 —— 强行制造解释和转折
  • bullet 堆叠:能写成自然段的内容,被硬拆成列表
  • 加粗过多:每段都在强调,反而没有重点
  • 翻译腔:语序像英文,抽象名词多,动作词少
  • 判词腔:用“不是免费的 X 来源”“必须看起来 Y”这类负向定义、制度化判断表达观点,读起来像模型在下结论
  • 资料味:元信息堆在开头,像笔记、讲义、PPT 备注

详细识别表和替换策略见 references/anti-ai-flavor-rules.md。当文章问题较多、需要系统处理时读取该文件。

3. 改写原则

  • 删除套话,直接切入主题。
  • 用具体场景、动作、数据替代抽象形容词。
  • 把负向定义改成正面判断或更像人会说的动作句,例如把“不是免费的可靠性来源”改成“可靠性没有那么简单”。
  • 把长句拆短,让一句话只说一个主要意思。
  • 用自然承接替代机械连接词。
  • 少用排比,避免每段都像总结。
  • 尽量不用 不是……而是……不仅……而且……更…… 这类模板句式。
  • 尽量不用破折号;改用冒号、逗号、句号、括号,或重排句子。
  • 需要列表时保留列表;不需要时改回自然段。
  • 对技术、产品、行业文章,保持准确克制,不改成鸡汤。

Read the full file on GitHub · 151 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. 12d ago First seen · 151 lines · 0 tokens per session scan A 60ae233babb6

Subscribe to this mod's changes

remove-ai-flavor is a skill published in the GitHub repository ItamarZand88/awesome-agent-conventions (31 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,853 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

ai-ml-development

AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.

travisjneuman/.claude · 43 tokens

case-interview-practice

Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.

travisjneuman/.claude · 39 tokens

i18n-localization

Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.

travisjneuman/.claude · 32 tokens

electron-desktop

Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.

travisjneuman/.claude · 38 tokens

finance

Financial analysis expertise for financial modeling (DCF, LBO, M&A), valuation, financial statement analysis, capital allocation, treasury management, and corporate finance decisions. Use when building financial models, analyzing statements, or making investment decisions.

travisjneuman/.claude · 48 tokens

investment-memo-generator

Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.

travisjneuman/.claude · 37 tokens