Token导航 LogoToken导航

Agent Skill · 研究检索

actionable-review-format-standards(可行的审查格式标准)

actionable-review-format-standards 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。

actionable-review-format-standards 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;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 65,351。

总安装 282周安装 12GitHub Stars 21下载 99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:actionable-review-format-standards(可行的审查格式标准)
来源仓库:https://github.com/thapaliyabikendra/ai-artifacts
仓库路径:skills/actionable-review-format-standards
安装命令:
npx skills add https://github.com/thapaliyabikendra/ai-artifacts --skill actionable-review-format-standards
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/thapaliyabikendra/ai-artifacts --skill actionable-review-format-standards

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。

actionable-review-format-standards 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果时使用。

通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 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操作。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/actionable-review-format-standards

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/thapaliyabikendra/ai-artifacts --skill actiona…;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

actionable-review-format-standards 怎么安装?

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

actionable-review-format-standards 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。

actionable-review-format-standards 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。

actionable-review-format-standards 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。

actionable-review-format-standards 用的人多吗?

公开数据是累计安装 282 次,近一周安装 12 次,下载 99 次,GitHub 21 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。

actionable-review-format-standards 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

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。

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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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。

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
actionable-review-format-standards

可行的审查格式标准 · 本页

28221需要联网未明确未通过

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

Actionable Review Format Standards

Standardized output format for code reviews ensuring consistent, actionable, and prioritized feedback across all reviewer agents.

When to Use This Skill

  • Generating code review reports
  • Formatting PR feedback
  • Creating security audit reports
  • Producing performance review outputs
  • Any review output requiring severity classification

Core Principles

  1. Every issue has a severity - Never leave findings unclassified
  2. Every issue has a location - Always include file:line references
  3. Every blocking issue has a fix - Provide code snippets for Critical/High
  4. Summary before details - Lead with counts and verdicts
  5. Categorize by concern - Group Security, Performance, Patterns separately

Severity Classification

Severity Levels

LevelIconCriteriaAction Required
CRITICAL🔴Security vulnerabilities, data loss risk, system crashesMust fix before merge
HIGH🟠Significant bugs, missing authorization, performance blockersShould fix before merge
MEDIUM🟡Code quality issues, minor bugs, missing validationFix soon, not blocking
LOW🟢Style issues, minor improvements, suggestionsNice to have
INFO💡Educational comments, alternative approachesNo action required

Severity Decision Tree

Is it a security vulnerability?
├── Yes → CRITICAL
└── No → Can it cause data loss or corruption?
         ├── Yes → CRITICAL
         └── No → Can it cause system crash/downtime?
                  ├── Yes → HIGH
                  └── No → Does it break functionality?
                           ├── Yes → HIGH
                           └── No → Does it affect performance significantly?
                                    ├── Yes → MEDIUM
                                    └── No → Is it a code quality issue?
                                             ├── Yes → MEDIUM/LOW
                                             └── No → LOW/INFO

Severity Examples

🔴 CRITICAL - Security
- SQL injection vulnerability
- Missing authorization on delete endpoint
- Hardcoded credentials in source code
- PII exposure in logs

🟠 HIGH - Must Fix
- Missing null checks causing NullReferenceException
- N+1 query in frequently called method
- Business logic error causing wrong calculations
- Missing input validation on public API

🟡 MEDIUM - Should Fix
- Blocking async call (.Result, .Wait())
- Missing error handling
- Inefficient LINQ query
- Duplicate code that should be extracted

🟢 LOW - Nice to Have
- Variable naming improvements
- Missing XML documentation
- Code formatting inconsistencies
- Minor refactoring opportunities

💡 INFO - Educational
- Alternative pattern suggestion
- Performance optimization tip
- Best practice recommendation

Location Format

Standard Format

{FilePath}:{LineNumber}

Examples

✅ Good:
- `src/Application/PatientAppService.cs:45`
- `src/Domain/Patient.cs:23-28` (range)
- `src/Application/Validators/CreatePatientDtoValidator.cs:12`

❌ Bad:
- `PatientAppService.cs` (missing path)
- `line 45` (missing file)
- `src/Application/` (missing file and line)

Multi-Location Issues

When an issue spans multiple files:

**[MEDIUM]** Duplicate validation logic
- `src/Application/PatientAppService.cs:45`
- `src/Application/DoctorAppService.cs:52`
- `src/Application/AppointmentAppService.cs:38`

**Suggestion**: Extract to shared `ValidationHelper` class.

Issue Format

Single Issue Template

**[{SEVERITY}]** `{file:line}` - {Category}

{Brief description of the issue}

**Problem**:

// Current code {problematic code}


**Fix**:

// Suggested fix {corrected code}


**Why**: {Explanation of impact/risk}

Compact Issue Format (for tables)

| Severity | Location | Category | Issue | Fix |
|----------|----------|----------|-------|-----|
| 🔴 CRITICAL | `File.cs:42` | Security | Missing `[Authorize]` | Add `[Authorize(Permissions.Delete)]` |
| 🟠 HIGH | `File.cs:67` | Performance | N+1 query in loop | Use `.Include()` or batch query |

Report Structure

Full Review Report Template

# Code Review: {PR Title}

**Date**: {YYYY-MM-DD}
**Reviewer**: {agent-name}
**Files Reviewed**: {count}
**Lines Changed**: +{added} / -{removed}

---

## Verdict

{✅ APPROVE | 💬 APPROVE WITH COMMENTS | 🔄 REQUEST CHANGES}

**Summary**: {1-2 sentence overview}

---

## Issue Summary

| Severity | Count | Blocking |
|----------|-------|----------|
| 🔴 CRITICAL | {n} | Yes |
| 🟠 HIGH | {n} | Yes |
| 🟡 MEDIUM | {n} | No |
| 🟢 LOW | {n} | No |

---

## 🔴 Critical Issues

{If none: "No critical issues found."}

### [CRITICAL] `{file:line}` - {Title}

{Description}

**Problem**:

{code}


**Fix**:

{code}


---

## 🟠 High Issues

{Issues in same format}

---

## 🟡 Medium Issues

{Issues in same format or table format for brevity}

---

## 🟢 Low Issues / Suggestions

- **`{file:line}`** [nit]: {suggestion}
- **`{file:line}`** [style]: {suggestion}

---

## 🔒 Security Summary

| Check | Status | Notes |
| --- | --- | --- |
| Authorization | ✅ Pass / ❌ Fail | {details} |
| Input Validation | ✅ Pass / ❌ Fail | {details} |
| Data Exposure | ✅ Pass / ❌ Fail | {details} |
| Secrets | ✅ Pass / ❌ Fail | {details} |

---

## ⚡ Performance Summary

| Check | Status | Notes |
| --- | --- | --- |
| N+1 Queries | ✅ Pass / ❌ Fail | {details} |
| Async Patterns | ✅ Pass / ❌ Fail | {details} |
| Pagination | ✅ Pass / ❌ Fail | {details} |
| Query Optimization | ✅ Pass / ❌ Fail | {details} |

---

## ✅ What's Good

- {Positive observation 1}
- {Positive observation 2}
- {Positive observation 3}

---

## Action Items

**Must fix before merge**:

- {Critical/High issue 1}
- {Critical/High issue 2}

**Should fix soon**:

- {Medium issue 1}
- {Medium issue 2}

---

## Technical Debt Noted

- {Future improvement 1}
- {Future improvement 2}

Category Labels

Use consistent category labels to classify issues:

CategoryDescriptionExamples
SecurityVulnerabilities, auth issuesMissing auth, SQL injection, XSS
PerformanceEfficiency issuesN+1, blocking async, missing pagination
DDDDomain design issuesPublic setters, anemic entities
ABPFramework pattern violationsWrong base class, missing GuidGenerator
ValidationInput validation issuesMissing validators, weak rules
Error HandlingException handling issuesSilent catch, wrong exception type
AsyncAsync/await issuesBlocking calls, missing cancellation
TestingTest quality issuesMissing tests, flaky tests
StyleCode style issuesNaming, formatting
DocumentationDoc issuesMissing comments, outdated docs

Feedback Language

Use Constructive Language

❌ Bad:
"This is wrong."
"You should know better."
"Why didn't you use X?"

✅ Good:
"Consider using X because..."
"This could cause Y. Here's a fix:"
"Have you considered X? It would improve Y."

Differentiate Blocking vs Non-Blocking

🚫 [blocking]: Must fix before merge
💭 [suggestion]: Consider for improvement
📝 [nit]: Minor style preference, not blocking
📚 [learning]: Educational note, no action needed

Quick Reference

Minimum Requirements

Every review output MUST include:

  1. Verdict - Approve/Request Changes
  2. Issue count by severity
  3. All Critical/High issues with fixes
  4. File:line references for all issues
  5. At least one positive observation

Severity Quick Guide

If you find...Severity
Security vulnerability🔴 CRITICAL
Missing authorization🔴 CRITICAL
Data corruption risk🔴 CRITICAL
Null reference exception🟠 HIGH
N+1 query pattern🟠 HIGH
Blocking async🟡 MEDIUM
Missing validation🟡 MEDIUM
Naming issues🟢 LOW
Missing docs🟢 LOW

Example Output

# Code Review: Add Patient CRUD API

**Date**: 2025-12-13
**Reviewer**: abp-code-reviewer
**Files Reviewed**: 5
**Lines Changed**: +245 / -12

---

## Verdict

🔄 REQUEST CHANGES

**Summary**: Good implementation of Patient CRUD with proper ABP patterns. Found 1 critical security issue (missing authorization) and 2 performance concerns that need attention.

---

## Issue Summary

| Severity | Count | Blocking |
|----------|-------|----------|
| 🔴 CRITICAL | 1 | Yes |
| 🟠 HIGH | 2 | Yes |
| 🟡 MEDIUM | 1 | No |
| 🟢 LOW | 2 | No |

---

## 🔴 Critical Issues

### [CRITICAL] `src/Application/PatientAppService.cs:67` - Security

**Missing authorization on DeleteAsync**

**Problem**:

public async Task DeleteAsync(Guid id) { await _repository.DeleteAsync(id); }


**Fix**:

[Authorize(ClinicManagementSystemPermissions.Patients.Delete)] public async Task DeleteAsync(Guid id) { await _repository.DeleteAsync(id); }


**Why**: Any authenticated user can delete patients without permission check.

---

## 🟠 High Issues

### [HIGH] `src/Application/PatientAppService.cs:34` - Performance

**N+1 query pattern in GetListAsync**

**Problem**:

foreach (var patient in patients) { patient.Appointments = await _appointmentRepository.GetListAsync(a => a.PatientId == patient.Id); }


**Fix**:

var patientIds = patients.Select(p => p.Id).ToList(); var appointments = await _appointmentRepository.GetListAsync(a => patientIds.Contains(a.PatientId)); var grouped = appointments.GroupBy(a => a.PatientId).ToDictionary(g => g.Key, g => g.ToList()); foreach (var patient in patients) { patient.Appointments = grouped.GetValueOrDefault(patient.Id, new List<Appointment>()); }


---

## 🔒 Security Summary

| Check | Status | Notes |
| --- | --- | --- |
| Authorization | ❌ Fail | DeleteAsync missing `[Authorize]` |
| Input Validation | ✅ Pass | FluentValidation in place |
| Data Exposure | ✅ Pass | DTOs properly scoped |
| Secrets | ✅ Pass | No hardcoded values |

---

## ⚡ Performance Summary

| Check | Status | Notes |
| --- | --- | --- |
| N+1 Queries | ❌ Fail | Loop in GetListAsync |
| Async Patterns | ✅ Pass | Proper async/await |
| Pagination | ✅ Pass | Using PageBy |
| Query Optimization | ✅ Pass | WhereIf pattern used |

---

## ✅ What's Good

- Excellent entity encapsulation with private setters
- Proper use of `GuidGenerator.Create()`
- Clean FluentValidation implementation
- Good separation of concerns

---

## Action Items

**Must fix before merge**:

- Add `[Authorize]` to DeleteAsync
- Fix N+1 query in GetListAsync

**Should fix soon**:

- Add XML documentation to public methods

平台分布

Codex

32.74%
按下载量换算32

Claude

29.85%
按下载量换算30

Cursor

17.92%
按下载量换算18

Gemini CLI

10.36%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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