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.
npx skills add renky1025/agent-skills --skill de-ai-writinggit clone --depth 1 https://github.com/renky1025/agent-skillsWrote 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.
[](https://agentmods.dev/skills/renky1025/agent-skills/de-ai-writing)<a href="https://agentmods.dev/skills/renky1025/agent-skills/de-ai-writing"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/de-ai-writing/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.
<a href="https://agentmods.dev/skills/renky1025/agent-skills/de-ai-writing"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/de-ai-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00150 | $0.05026 |
| Opus 5 | $0.00075 | $0.02513 |
| Sonnet 5 | $0.00030 | $0.01005 |
| Haiku 4.5 | $0.00015 | $0.00503 |
Grade A, and why
de-ai-writing 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文本去AI味 / De-AI Writing
真实可靠的文风指令。不输出一套新腔调替换旧腔调，而是教你找出机器味、删掉空话、校准到自己的声音。
相关 / 分工
本技能是「去 AI 味」的唯一真源（single source of truth）。snowflake-novel-writer（references/anti-ai-writing.md）与 wechat-article-writer（references/avoid-ai-writing.md）内嵌了本指南的本地副本，便于离线/自包含引用；如需更新去 AI 味规则，请以本技能为准并同步上述副本。
核心认知
AI味的本质不是"用词太AI"，而是"没有具体的人在里面"。
干净但没灵魂，还是机器味。每句话长度一样、没有观点、只做中立报道、不承认复杂感受、没有幽默、没有锋芒——这些也算没修好。
AI 的根本问题是回归统计平均值，而人类是具体、奇怪、不稳定的。去AI味不是洗成"通用人类腔"，而是把文字放回一个具体的人身上。
核心原则（来自 PasPrompt 反AI写作系统）
写任何东西之前，记住这些规则：
绝不使用：
- 泛化开头和泛化结尾
- 空洞的过渡句
- 企业套话
- 励志填充物
- 过度解释
- 可预测的句式
- 显而易见的观察
- 不必要的背景铺垫
- 证据明显倾向一边却假装中立
始终做到：
- 先甩出最重要的观点
- 洞察优先于解释
- 具体优先于抽象
- 句子节奏自然多变
- 包含有意义的判断
- 必要时挑战假设
- 带着确信感写
- 砍掉所有不创造价值的文字
- 听起来像一个对主题有深度理解的人
写完后自问：这段话删掉，文章损失什么？什么都不损失 = 删。
使用方式
用户贴一段文字，按五步法执行。目标文本可以是任何类型：自媒体文章、职场周报、个人随笔、产品文案、朋友圈、小红书笔记、邮件等。
五步去AI味工作流
第1步：检测 → 不要急着改写
先输出 AI味检测报告，不改文本。按以下11类逐项标记：
1. 意义膨胀 — 把普通事实包装成重大事件
- 标志词：标志着、反映了更广泛的趋势、为未来奠定基础、关键转折点、深刻变革
- 改法：摘帽子，说这东西到底是什么、做了什么、影响了谁
2. 宣传腔 — 像旅游手册和融资新闻稿的杂交
- 标志词：充满活力的、丰富的、深刻的、开创性的、令人叹为观止的、卓越的
- 改法：不要形容词，给事实。别说"充满活力的社区"，说你亲眼看见的
3. 模糊归因 — 冒充有来源的空壳引用
- 标志词：专家认为、行业报告显示、观察者指出、有数据显示、研究表明
- 改法：要么说清哪个专家、哪份报告、哪一年，要么直接删
4. 公式结构 — 同一种模具倒出来的水泥块
- 三连词：创新/效率/增长、认知/行动/结果
- 否定排比："不是A，而是B""这不仅是A，更是B"
- 万能开头："在当今时代""随着XX的发展""本文将从XX角度""本文将深入探讨"
5. AI高频词（中文）
- 赋能、认知升级、长期主义、底层逻辑、关键抓手、闭环、深度链接、价值沉淀、颗粒度、抓手、对齐、重构、升维、降维打击、顶层设计、范式转移、破局、破圈、穿透、倒逼、解法、路径、场域、体感、温差
- 发现3个以上，整段重写
6. 风格痕迹
- 破折号泛滥（每500字超过1个）
- 粗体加粗滥用
- 列表项目都是"关键词：解释"格式
- 小标题像培训课件
- 开头"本文将"、结尾"希望这对你有帮助"
7. 聊天残留
- 当然、你说得对、请告诉我、希望这对你有帮助
- 首先/其次/再次/最后（连环用）
- 此外、值得注意的是、真正重要的是
- 综上所述、总而言之
8. 统计层面
- 句长是否过于均匀（大部分句子15-25字 = 机器人节奏）
- 同段是否同义词轮换（开发者→工程师→技术人员，重复一个词比强行变化更像人）
- 段落长度是否全都3-5句（刻意变化：有1句的短段，也有长段）
- 全文是否有观点倾向（全篇中立描述 = 没灵魂）
9. 缺乏判断力 — AI 回避立场，人类天然会判断
- 特征：只说"一方面……另一方面……"但不表态；列出观点但不区分优先级；不敢说哪个更重要
- 标志句："这取决于具体情况""每个人看法不同""没有绝对的对错"
- 改法：给判断。说"这条比那三条加起来都重要"。表达置信度——"我基本确定""这个我不太有把握但""数据指向一个方向"。指出弱点。质疑假设。提到权衡。展示合理的怀疑。
10. 解释代替洞察 — 在复述常识而不是提供新知
- 特征：每个段落都在解释一个大多数人已经知道的概念，像教科书而不是文章
- 自检问题：读完这段，读者学到了什么他们之前不知道的东西？如果答案是"没有"，这段就是解释而非洞察
- 改法：删掉解释性内容。保留揭示、挑战、质疑、对比、重新框定的内容。读者看完应该感觉学到了新东西。
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.
- 11d ago First seen · 337 lines · 150 tokens per session scan A e67670959109
de-ai-writing is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 5,026 once invoked, about $0.0007 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
imagegen-frontend-mobile
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured…
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…