de-ai-polish SKILL.md skillA
de-ai-polish from evovexai/evoflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add evovexai/evoflow/de-ai-polish@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- evovexai/evoflow
- Path
skills/public/de-ai-polish/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Sep 12, 2026
- Size
- 29,736 bytes
- Repository stars
- 540
- License
- a license file GitHub does not identify
检测并去除文章中的AI化表述模式,用于写作润色、文本优化、去AI腔。.
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
# De AI Polish ## 快速开始 检测文章中的AI化表述: ```bash # 全文扫描检测 /de-ai-polish detect @article.md # 直接修改 /de-ai-polish fix @article.md ``` ## 核心检测规则 ### 一、绝对禁止类(必须去除) 以下模式在任何情况下都应去除,它们是最明显的AI痕迹: #### 1. 对比句式 **必须去除的模式**: - `不是.*而是` - `并非.*而是` - `不在于.*在于` - `不再是.*而是` - `与.*是两回事` - `与.*不等同于` - `看似.*实则`(如:看似在讲隐喻,实则在讲生产方式) - `看起来.*其实`(如:看起来是X,其实是Y) **问题分析**: - 使用对比结构制造强烈反差,显露AI痕迹 - 强行把概念放在一起对比,显得不自然 - 改为直接陈述或递进关系 **改写方法**: - 拆成两个独立的陈述句 - 或改为递进、并列等自然关系 - 避免为了强调而强行对比 **改写策略选择:删 / 合并 / 改写** 处理对比句式时,不要套用统一模板,而是根据上下文判断采用哪种策略: | 策略 | 判断条件 | 操作方式 | |------|---------|---------| | **删** | 前文已完整表达同样意思;对比句仅为凑字数的转折 | 直接删除 | | **合并** | 对比的前/后半部分可以自然融入前段;句子本身没有独立价值 | 将核心意思合并到前段,删除整句 | | **改写** | 句子本身有独立价值(如总结一段、点明核心);是重要的过渡句或结论句 | 保留核心意思,换句式重新表达 | **多元改写示例(对比模板多样化)**: | 原句(❌ 机械模板) | ✅ 多元改写方案 | |-------------------|----------------| | `这不是工具的问题,这是范式的问题。` | **改写**:`症结不在工具,在于范式。`(正反对照 → 正正对举) | | `本质上是工具链的差距,不是工具的差距。` | **改写**:`这里的差距,是工具链的差距。`(删除冗余对比) | | `不是AI的问题,而是使用方式的问题。` | **合并**:融入前文,变成 `问题出在使用方式上。` | | `它更像一种X,不像Y。` | **改写**:`这是X,不是Y。`(去掉"更像") | | `并不是XXX,实际情况是YYY。` | **改写**:`但情况是YYY。`(去掉否定前缀) | **模板过度使用警告**: ❌ **机械模板**(每次都用同一结构改写): - "本质上是X,不是Y" - "问题不在X,在于Y" - "这不是X,这是Y" …
Read the whole file at its exact version.
How to install
mdr add evovexai/evoflow/de-ai-polish@sha256:e0521a34f600d635The line at the top of this page pins the label v1.0.0, 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_d6sxc4j6gsevryas)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 12, 2026.
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 (29736 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
evovexai/evoflow · 540 stars · license a license file GitHub does not identify · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_d6sxc4j6gsevryas GET https://markdownregistry.com/api/v1/resolve?ref=evovexai/evoflow/de-ai-polish GET https://markdownregistry.com/api/v1/blob/e0521a34f600d635c6a7ccf61abda6ee22b4d46c90c553ca447d1b37adbf2a8b
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 evovexai/evoflow
Every file in evovexai/evoflow