Token导航 LogoToken导航

Agent Skill · 研究检索

ai-anti-patterns(AI 反模式)

ai-anti-patterns 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

ai-anti-patterns 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 48,042。

总安装 706周安装 30GitHub Stars 9下载 247核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ai-anti-patterns(AI 反模式)
来源仓库:https://github.com/edwinhu/workflows
仓库路径:skills/ai-anti-patterns
安装命令:
npx skills add https://github.com/edwinhu/workflows --skill ai-anti-patterns
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/edwinhu/workflows --skill ai-anti-patterns

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。适合根据关键词或任务场景快速定位候选结果。通过 npx 命令从指定仓库安装,需确认权限与维护状态。注意可能触发联网、命令执行或文件读写操作。

ai-anti-patterns 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/ai-anti-patterns

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/edwinhu/workflows --skill ai-anti-patterns;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

ai-anti-patterns 怎么安装?

在终端执行 npx skills add https://github.com/edwinhu/workflows --skill ai-anti-patterns。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ai-anti-patterns 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ai-anti-patterns 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

ai-anti-patterns 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

ai-anti-patterns 用的人多吗?

公开数据是累计安装 706 次,近一周安装 30 次,下载 247 次,GitHub 9 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ai-anti-patterns 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ai-anti-patterns

AI 反模式 · 本页

7069只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

AI Writing Anti-Patterns

Field guide for detecting and revising AI-generated content indicators based on Wikipedia's "Signs of AI writing" guide.

When to Use

Invoke this skill:

  • Before finalizing ANY AI-assisted writing
  • When reviewing text for AI writing indicators
  • When editing content to sound more natural
  • After completing writing tasks (automatic via hooks)

The Iron Law

Check every piece of AI-assisted writing against these patterns before submission.

This is not optional. AI writing patterns are detectable and undermine credibility.

Quick Screening Order

Start with the most objective indicators:

PrioritySectionWhat to Check
1ChatGPT Artifactsturn0search0, oaicite, contentReference
2Citation ProblemsHallucinated DOIs, dead links, non-existent sources
3Prompt Refusals"As an AI language model...", "I hope this helps"
4Puffery"stands as", "plays a vital role", "rich tapestry"
5StructureSection summaries, "Despite challenges", rule of three

Critical Patterns to Avoid

CRITICAL Severity (Immediate Revision Required)

These patterns are unambiguous AI artifacts:

ChatGPT-Specific Artifacts:

  • turn0search0, turn1search2 (internal search references)
  • oaicite:X (citation placeholders)
  • contentReference[oaicite:X] (unresolved references)
  • JSON attribution blocks in output

Prompt Refusals:

  • "As an AI language model..."
  • "I cannot provide..."
  • "I hope this helps!"
  • "I hope this email finds you well"

HIGH Severity (Strong Revision Recommended)

Puffery and Exaggeration:

  • "stands as" (a testament/example/beacon)
  • "plays a vital/crucial/pivotal role"
  • "rich tapestry of"
  • "nestled in/among"
  • "it's important to note that"
  • "delves into"
  • "the landscape of"

Promotional Language:

  • "groundbreaking", "transformative", "revolutionary"
  • "unparalleled", "unprecedented"
  • "cutting-edge", "state-of-the-art"

MEDIUM Severity (Review and Consider)

Structural Patterns:

  • Section summaries that repeat the heading
  • "Despite [challenge], [positive outcome]" formula
  • Negative parallelisms: "However... Nevertheless..."
  • Rule of three: exactly three examples every time
  • Weasel wording: "some experts say", "it is believed"

Stylistic Quirks:

  • Elegant variation (synonym cycling to avoid repetition)
  • False ranges ("from X to Y" without real data)
  • Title Case In All Headings
  • Em dash overuse (—)
  • Excessive boldface for emphasis

User-Voice Lint (legal drafting)

Words/phrases the model reaches for that don't match the user's voice:

  • "has bite" / "bites" / "with bite" — model-reach for "has real effect." User never writes it. Replace with the specific effect: "raises the cost of X," "triggers quorum failure," "deters Y."
  • Caveat phrasings (candidates to replace with To be sure,): admittedly, granted,, of course,, that said,, to be clear,, no doubt,, we acknowledge that. Use To be sure, *only* when the next sentence rebuts the concession (concede-then-rebut). If the next sentence extends the disclaimer or frames scope, leave the original phrasing or rewrite without a caveat word at all.
  • Bridge repetitions — when writing the first paragraph of a new section, check whether it restates the thesis from the prior section. Rewrite to advance the argument. See writing-review/scripts/bridge_repetition_check.py for the detector.

How to Revise

For Puffery

AI PatternHuman Alternative
"stands as a testament to""shows" or "demonstrates"
"plays a vital role in""affects" or just state the effect
"rich tapestry of"describe specifically what it contains
"nestled in the heart of""in" or "located in"
"delves into""examines" or "covers"

For Structure

AI PatternHuman Alternative
Section summary of headingStart with substance, not meta-commentary
"Despite challenges..."State the reality directly without formula
Exactly three examplesUse the number that fits: 2, 4, 5, or just 1
"It's important to note"Just state the important thing

For Promotional Language

AI PatternHuman Alternative
"groundbreaking"describe what it actually does
"revolutionary"compare to what came before
"cutting-edge"specify the technology
"transformative"show the transformation with evidence

Reference Files

For detailed patterns and extensive examples, consult:

FileContents
references/_index.mdOverview and quick screening guide
references/01-puffery-and-exaggeration.md"Stands as", superficial analyses
references/02-promotional-language.md"Rich tapestry", disclaimers
references/03-structural-patterns.mdSection summaries, negative parallelisms
references/04-stylistic-quirks.mdElegant variation, false ranges
references/05-formatting-and-typography.mdBoldface, em dashes, emojis
references/06-communication-patterns.mdSubject lines, "I hope this helps"
references/07-template-artifacts.mdMad Libs patterns, placeholders
references/08-markup-issues.mdMarkdown vs wikitext confusion
references/09-chatgpt-specific-artifacts.mdturn0search, oaicite
references/10-citation-problems.mdHallucinated DOIs, dead links
references/11-meta-indicators.mdAbrupt cutoffs, style discrepancies

Automatic Detection

This plugin includes PostToolUse hooks that automatically scan Write/Edit output for anti-patterns. When patterns are detected:

  1. Hook emits a warning with specific patterns found
  2. Claude immediately revises the content
  3. Revision removes or replaces flagged patterns

The hook checks for all CRITICAL and HIGH severity patterns automatically.

Rationalization Table - STOP If You Think:

ExcuseRealityDo Instead
"This puffery is appropriate for the register"Puffery is never appropriate; precision always beats vaguenessREPLACE with concrete, specific language
"The user specifically requested this style"Users request outcomes, not AI-smellDELIVER the outcome without the patterns
"Bold emphasis is needed here for readability"If you need bold to make it readable, the sentence is weakREWRITE the sentence so it stands without formatting
"This hedge ('it's important to note') adds nuance"It adds nothing; state the point directlyDELETE the hedge, keep the point
"The transition phrase connects the ideas""Furthermore" and "Moreover" are filler, not connectionCUT the transition; if ideas connect, the reader sees it
"This summary paragraph is helpful"If the reader needs a summary of what you just said, you said it poorlyDELETE the summary, revise the original

Drive-Aligned Framing

Skimming instead of checking each sentence against the pattern list is NOT HELPFUL — the user submits AI-smelling text that damages their credibility. Skimming is not checking.

  • You let puffery pass because flagging it felt pedantic. The document reads as obviously AI-generated — your politeness destroyed the user's credibility.
  • You skipped the anti-pattern check to save time. The user submits AI-smelling text — your efficiency embarrassed them.

Red Flags - Stop If You Think

ThoughtWhy It's WrongDo Instead
"This sounds professional"AI puffery sounds generic, not professionalUse concrete, specific language
"I'll add emphasis""Very important" and bold are AI tellsLet content speak for itself
"Let me summarize the section"Section summaries are formulaicStart with substance
"Three examples is a good number"Rule of three is an AI patternUse the right number for the content

Key Principles

From Wikipedia's guide:

  1. These are signs, not proof - Multiple indicators strengthen the case
  2. Context matters - Some patterns appear in human writing too
  3. Focus on deeper issues - Surface defects point to synthesis and quality problems
  4. Don't rely on detection tools - Human judgment required

Related Skills

  • /writing - Core writing principles from Elements of Style
  • /writing-legal - Legal writing (Phase 2)
  • /writing-econ - Economics writing (Phase 2)

平台分布

Codex

38.2%
按下载量换算94

Claude

28.42%
按下载量换算70

Cursor

19.96%
按下载量换算49

Gemini CLI

8.93%
按下载量换算22

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills