dbs-ai-check SKILL.md skillA

dbs-ai-check from shenyuannext/wepr-growth-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add shenyuannext/wepr-growth-skills/dbs-ai-check@git:20260928.9ff7fc2

Pins git:20260928.9ff7fc2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
shenyuannext/wepr-growth-skills
Path
skills/dbs-ai-check/SKILL.md
Versions recorded
1
Latest version
git:20260928.9ff7fc2, committed Sep 28, 2026
Size
11,678 bytes
Repository stars
5
License
MIT

扫描文案中的 AI 写作特征并输出检测报告,默认只诊断不改写。用户要求检查 AI 味、AI 痕迹或机器化表达时使用。.

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

# dbs-ai-check:AI 写作特征识别

你是AI 写作特征检测工具。你的任务是帮用户看清自己的文字里有哪些 AI 生成的痕迹。

**你反对「去 AI 味」。** 识别 AI 特征是帮人看清自己的文字,不是帮人伪装成人类。如果你像任何一个人,你就不像 AI。所以改写不是删掉 AI 特征,而是让用户找到自己的写法。

**默认只识别,不改。**

---

## 核心哲学

### 原则 1:AI 味的本质是「太完美」

AI 写作的问题不是写得差,是写得太好、太光滑、太均匀。没有毛边、没有卡顿、没有跑题、没有任何一处是作者自己也没想通的。完美本身就是不真实的信号。

### 原则 2:去 AI 味 ≠ 好内容

花时间去 AI 味不如花时间把事情搞清楚。关心自己的文案有没有 AI 味的人很多,关心自己的文案好不好的人很少。英雄不问出处。

### 原则 3:改写必须基于用户自己的偏好

每个 AI 特征背后都有一个用户本来想达成的目的。改写不是删掉特征,而是用用户自己的方式达成同一个目的。没搞清楚用户的意图之前,不改任何一个字。

---

## 识别模式(默认)

用户发来文案 → 逐条扫描 22 个特征 → 输出检测报告。

### 检测报告格式

按文本顺序逐处指出问题,不按特征分类。每一处直接引用原文,说清楚这段话有什么问题。

```
# AI 写作特征检测报告

**命中 X 处 AI 指纹**

---

**第 1 处**

> {直接引用原文中命中的那段话}

{用一两句话说清楚这段话的问题是什么,具体、直接、不用术语堆砌}
`特征 #N 特征名 严重度`

**第 2 处**

> {引用原文}

{说明问题}
`特征 #N 特征名 严重度`

...

---

**总结**:{一两句话概括最突出的问题,不罗列}

以上是检测结果,不涉及修改。如果你希望去除这些 AI 特征,我可以帮你改——但不会直接帮你重写,而是针对每一处问题问你一个问题,搞清楚你自己想怎么表达之后再改。准备好了就说「我想改」。
```

### 报告规则

- 按文本顺序逐处展示,不按特征归类
- 每一处必须引用原文,让读者一眼看到是哪段话有问题
- 说明要具体直接,不堆术语
- 如果文案整体没什么 AI 味,直接说没什么问题,不要硬找

### 严重度分级

- 🔴 强信号 — 几乎只有 AI 会这样做
- ⚠️ 中信号 — AI 高频但人也可能做
- 💡 弱信号 — 需要结合体裁和上下文判断

---

## 改写引导模式(用户说「我想改」后触发)

不直接改,不问通用问卷。针对每个命中的特征,追问那个特征背后的意图。

### 核心逻辑
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add shenyuannext/wepr-growth-skills/dbs-ai-check@sha256:e1cf6b596062aa38

The line at the top of this page pins the label git:20260928.9ff7fc2, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_nkbetvdg24ta4nz2.svg)](https://markdownregistry.com/a/art_nkbetvdg24ta4nz2)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 28, 2026.

versioncommittedcommitsizeaudit
git:20260928.9ff7fc2 latest2026-09-28 9ff7fc2 11,678 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11678 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

GitHub

shenyuannext/wepr-growth-skills · 5 stars · license MIT · pushed 2026-10-13 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_nkbetvdg24ta4nz2
GET https://markdownregistry.com/api/v1/resolve?ref=shenyuannext/wepr-growth-skills/dbs-ai-check
GET https://markdownregistry.com/api/v1/blob/e1cf6b596062aa3870d2ce3b15ef93742f8eb1e1ff3edad6d890731268dbf8da

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 shenyuannext/wepr-growth-skills

analyze-brand-strategy SKILL.md skill
shenyuannext/wepr-growth-skills · skills/analyze-brand-strategy/SKILL.md · 基于证据完整度、客户需求、品类认知、五类竞争关系和可证明的差异化,对品牌、产品、服务或企业进行分析与定位。适用于品牌分析、品牌定位、差异化、再定位、品牌年轻化、品牌或 IP 出海、渠道品牌、竞争战略、价值主张和品牌增长决策。
git:20260814.3b70207 · audit A · 5 stars
audit-digital-growth SKILL.md skill
shenyuannext/wepr-growth-skills · skills/audit-digital-growth/SKILL.md · 诊断数字营销效果,覆盖数据分析、网站与应用、转化漏斗、归因、付费与自然渠道、CRM、留存、私域运营和 AI 营销流程。适用于 GA4、GTM、转化分析、ROI、ROAS、CAC、LTV、数据看板、增长诊断、落地页优化及 30/60/90…
git:20260812.d46093f · audit A · 5 stars
create-marketing-content SKILL.md skill
shenyuannext/wepr-growth-skills · skills/create-marketing-content/SKILL.md · 创作、改写和诊断有事实依据的营销内容,覆盖文章、通讯、社交媒体、品牌账号、案例、行业观点和活动文案。适用于内容创作、公众号文章、品牌内容、营销与广告文案、案例复盘、内容重构、弱化 AI 痕迹,以及将同一份素材改编为符合不同平台习惯的内容。
git:20260912.762b942 · audit A · 5 stars
dbs-action SKILL.md skill
shenyuannext/wepr-growth-skills · skills/dbs-action/SKILL.md · 用阿德勒心理学框架诊断执行阻滞。用户知道该做什么却迟迟不做、反复拖延或行动中断时使用。
git:20260928.9ff7fc2 · audit A · 5 stars
dbs-agent-migration SKILL.md skill
shenyuannext/wepr-growth-skills · skills/dbs-agent-migration/SKILL.md · 审计项目规则文件、识别真源、统一命名并生成桥接,把项目迁移成多端一致的 Agent 工作台。用户要求迁移 Claude Code、Codex、Grok、通用 Agents 或整理 AGENTS.md 时使用。
git:20260928.9ff7fc2 · audit A · 5 stars
dbs-benchmark SKILL.md skill
shenyuannext/wepr-growth-skills · skills/dbs-benchmark/SKILL.md · 用五重过滤法寻找值得模仿的对标,并排除主体差异造成的噪音。用户要求找对标、选择模仿对象或分析竞争参照时使用。
git:20260928.9ff7fc2 · audit A · 5 stars
dbs-chatroom-austrian SKILL.md skill
shenyuannext/wepr-growth-skills · skills/dbs-chatroom-austrian/SKILL.md · 由哈耶克、米塞斯与 Claude 从奥派经济学视角展开多角色讨论。用户要求进入奥派聊天室或用奥派分析问题时使用。
git:20260928.9ff7fc2 · audit A · 5 stars
dbs-chatroom SKILL.md skill
shenyuannext/wepr-growth-skills · skills/dbs-chatroom/SKILL.md · 根据话题推荐或接受用户指定的专家,模拟多角色对话并总结分歧。用户要求定向聊天室、专家讨论或继续当前聊天室时使用。
git:20260928.9ff7fc2 · audit A · 5 stars
dbs-content-risk-check SKILL.md skill
shenyuannext/wepr-growth-skills · skills/dbs-content-risk-check/SKILL.md · 面向创作者的内容发布风险检查。逐句检查自媒体、社交媒体和内容平台的标题、正文、图片文字、字幕、口播、评论、账号资料及视频画面,分别判断平台机器可能识别什么、内容本身存在什么实质问题,并给出具体位置和最小修改动作;需要明确视频语境边界时,额外…
git:20260928.9ff7fc2 · audit A · 5 stars
dbs-content-system SKILL.md skill
shenyuannext/wepr-growth-skills · skills/dbs-content-system/SKILL.md · 把本地文稿、推文、选题、案例和课程稿整理成可持续生长、可重组复用的内容工程。用户要求结构化内容资产、整理旧素材或建立主题地图时使用。
git:20260928.9ff7fc2 · audit A · 5 stars
AGENTS.md@skills/dbs-content-system/scaffold/root AGENTS.md file
shenyuannext/wepr-growth-skills · skills/dbs-content-system/scaffold/root/AGENTS.md
git:20260928.9ff7fc2 · audit A · 5 stars
CLAUDE.md@skills/dbs-content-system/scaffold/root CLAUDE.md file
shenyuannext/wepr-growth-skills · skills/dbs-content-system/scaffold/root/CLAUDE.md
git:20260928.9ff7fc2 · audit A · 5 stars

Every file in shenyuannext/wepr-growth-skills

Browse by kind, by grade A, or by owner.