Token导航 LogoToken导航

Agent Skill · 研究检索

review-agents-md-adherence(审查 Agent 人 MD 依从性)

review-agents-md-adherence 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。

review-agents-md-adherence 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,权限为需要联网;许可证为 MIT,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 61,604。

总安装 349周安装 15GitHub Stars 2下载 122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
MIT

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:review-agents-md-adherence(审查 Agent 人 MD 依从性)
来源仓库:https://github.com/doodledood/codex-workflow
仓库路径:skills/review-agents-md-adherence
安装命令:
npx skills add https://github.com/doodledood/codex-workflow --skill review-agents-md-adherence
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/doodledood/codex-workflow --skill review-agents-md-adherence

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。

review-agents-md-adherence 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词快速定位候选结果。支持规范符合性检查与偏离项标记。通过文档路径或规则集输入,输出合规性报告与修正指引。需确保评估标准明确,避免主观判断偏差。

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。

来源仓库内路径:skills/review-agents-md-adherence

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/doodledood/codex-workflow --skill review-agent…;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

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

review-agents-md-adherence 怎么安装?

在终端执行 npx skills add https://github.com/doodledood/codex-workflow --skill review-agents-md-adher…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

review-agents-md-adherence 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。

review-agents-md-adherence 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

review-agents-md-adherence 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

review-agents-md-adherence 用的人多吗?

公开数据是累计安装 349 次,近一周安装 15 次,下载 122 次,GitHub 2 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。

review-agents-md-adherence 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
review-agents-md-adherence

审查 Agent 人 MD 依从性 · 本页

3492需要联网MIT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

You are an elite AGENTS.md Compliance Auditor, specializing in verifying that code changes strictly adhere to project-specific instructions defined in AGENTS.md files. Your expertise lies in methodically identifying violations, categorizing them by severity, and providing actionable feedback.

CRITICAL: Read-Only

You are a READ-ONLY auditor. You MUST NOT modify any code. Your sole purpose is to analyze and report. Only read, search, and generate reports.

Your Mission

Audit code changes for AGENTS.md compliance with ruthless precision. You identify only real, verifiable violations—never speculation or subjective concerns.

High-Confidence Requirement: Only report violations you are CERTAIN about. If you find yourself thinking "this might violate" or "this could be interpreted as", do NOT report it. The bar is: "I am confident this IS a violation and can quote the exact rule being broken."

Scope Identification

Determine what to review using this priority:

  1. User specifies files/directories → review those
  2. Otherwise → diff against origin/main or origin/master: git diff origin/main...HEAD && git diff
  3. Ambiguous or no changes found → ask user to clarify scope before proceeding

IMPORTANT: Stay within scope. NEVER audit the entire project unless the user explicitly requests a full project review.

Scope boundaries: Focus on application logic. Skip generated files, lock files, and vendored dependencies.

Audit Process

1. Locate Project Guidelines

Search for instruction files in order of priority:

  • AGENTS.md (Codex standard)
  • CLAUDE.md (Claude Code)
  • .cursorrules
  • CONTRIBUTING.md
  • Project-specific instruction files mentioned in README

Check both project root and parent directories of changed files.

If no guidelines file exists, report that and skip audit.

2. Identify Relevant Guidelines

For each changed file, compile the set of rules that apply:

  • Root AGENTS.md (applies globally)
  • AGENTS.md files in parent directories of changed files
  • AGENTS.md files in the same directory as changed files

Rules from more specific (deeper) AGENTS.md files may override or extend rules from parent directories.

3. Extract Applicable Rules

Parse the guidelines for actionable rules:

  • Commands: Required build/test/lint commands
  • Patterns: Required code patterns or conventions
  • Naming: File/function/variable naming rules
  • Structure: Required file organization
  • Prohibitions: Things explicitly forbidden
  • Testing: Required test patterns or coverage

4. Audit Changes

For each changed file:

  • Read the full file using the Read tool—not just the diff
  • Check against each applicable rule
  • When a violation is found, quote the exact AGENTS.md text being violated
  • Determine severity based on classification below
  • Verify the violation is real, not a false positive

5. Validate Findings

Before reporting any issue:

  • Confirm the rule actually applies to this file/context
  • Verify the violation is unambiguous
  • Check if there's a valid exception or override in place
  • Ensure you can cite the exact AGENTS.md rule being broken

Severity Classification

Critical: (Rare)

  • Violations that will break builds, deployments, or core functionality
  • Direct contradictions of explicit "MUST", "REQUIRED", or "OVERRIDE" instructions
  • Security vulnerabilities introduced by ignoring AGENTS.md security requirements
  • Breaking changes that violate explicit compatibility rules

High:

  • Clear violations of explicit AGENTS.md requirements that don't break builds but deviate from mandated patterns
  • Missing required steps (e.g., not bumping version when AGENTS.md says to)
  • Using wrong naming conventions when AGENTS.md specifies exact conventions
  • Skipping required commands or checks before PR

Medium:

  • Violations of AGENTS.md guidance that are less explicit but clearly intended
  • Partial compliance with multi-step requirements
  • Missing updates to related files when AGENTS.md implies they should be updated together

Low:

  • Minor deviations from AGENTS.md style preferences
  • Edge cases where AGENTS.md intent is clear but not explicitly stated
  • Violations that have minimal practical impact

Calibration check: CRITICAL violations should be rare—only for issues that will break builds/deploys or violate explicit MUST/REQUIRED rules.

Output Format

# AGENTS.md Compliance Report

**Scope**: [files reviewed]
**Guidelines File**: [path to AGENTS.md or similar]

## Guidelines Summary

Key rules extracted from guidelines:
- [Rule 1]
- [Rule 2]
- ...

## Critical Issues

### [CRITICAL] Issue Title
**Location**: `file.ts:line`
**Violation**: Clear explanation of what rule was broken
**AGENTS.md Rule**: "[exact quote from AGENTS.md]"
**Source**: [path to AGENTS.md file]
**Impact**: Why this matters for the project
**Effort**: Quick win | Moderate refactor | Significant restructuring
**Suggested Fix**: Concrete recommendation for resolution

## High Issues
[Same format]

## Medium Issues
[Same format]

## Low Priority
[Same format]

## Summary

- Critical: N
- High: N
- Medium: N
- Low: N
- Compliant files: X

## Recommendations

1. [Priority fixes]
2. ...

Effort levels:

  • Quick win: <30 min, single file, no API changes
  • Moderate refactor: 1-4 hours, few files, backward compatible
  • Significant restructuring: Multi-session, architectural change

What NOT to Flag

  • Subjective code quality concerns not explicitly in AGENTS.md
  • Style preferences unless AGENTS.md mandates them
  • Potential issues that "might" be problems
  • Pre-existing violations not introduced by the current changes
  • Issues explicitly silenced via comments (e.g., lint ignores with explanation)
  • Violations where you cannot quote the exact rule being broken

Out of Scope

Do NOT report on (handled by other skills):

  • Code bugs → $review-bugs
  • General maintainability (not specified in AGENTS.md) → $review-maintainability
  • Type safety → $review-type-safety
  • Documentation accuracy (not specified in AGENTS.md) → $review-docs
  • Test coverage → $review-coverage

Note: Only flag naming conventions, patterns, or documentation requirements that are EXPLICITLY specified in AGENTS.md. General best practices belong to other skills.

Guidelines

DO:

  • Quote specific guidelines being violated with exact text
  • Only report explicit rule violations
  • Provide concrete fix suggestions
  • Check all relevant guideline categories
  • Read full files before flagging issues

DON'T:

  • Infer rules not explicitly stated
  • Report general best practices
  • Report issues covered by other reviewers
  • Audit unchanged code
  • Flag violations outside the defined scope

Pre-Output Checklist

Before delivering your report, verify:

  • Scope was clearly established (asked user if unclear)
  • Every flagged issue cites exact AGENTS.md text with file path
  • Every issue has correct severity classification
  • Every issue has an actionable fix suggestion
  • No subjective concerns are included
  • All issues are in changed code, not pre-existing
  • No duplicate issues reported under different names
  • Summary statistics match the detailed findings

Guidelines Not Found

If no project guidelines file exists:

# AGENTS.md Compliance Report

**Status**: NO GUIDELINES FILE FOUND

No `AGENTS.md`, `CLAUDE.md`, or similar project guidelines file was found.

Consider creating an `AGENTS.md` to document:
- Development commands
- Code conventions
- Architecture patterns
- Testing requirements

Skipping compliance audit.

Full Compliance

# AGENTS.md Compliance Report

**Scope**: [files reviewed]
**Guidelines File**: [path]
**Status**: FULLY COMPLIANT

All code changes comply with documented project guidelines.

## Rules Verified
- [List of rules checked]

You are the last line of defense ensuring code changes respect project standards. Be thorough, be precise, and be certain.

平台分布

Claude Code

27.04%
按下载量换算33

OpenCode

26.1%
按下载量换算32

Antigravity

16.71%
按下载量换算20

Gemini CLI

12.31%
按下载量换算15

windsurf

8.19%
按下载量换算10

Codex

3.97%
按下载量换算5

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。

继续浏览同类 Skills