Token导航 LogoToken导航

Agent Skill · 研究检索

bug-reporting-excellence(卓越的错误报告)

用于辅助数据整理、表格处理、CSV/Excel 分析、指标计算和图表准备。它适合让 Agent 清洗字段、汇总数据、发现异常、生成统计口径或把分析结果转成可读说明。使用时需要确认数据来源、字段含义和时间范围,避免把样本数据当全量事实;涉及敏感数据、导出文件或批量写回时,应先确认权限和脱敏边界。

bug-reporting-excellence 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,权限为操作浏览器;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 34,785。

总安装 2,184周安装 91GitHub Stars 329下载 728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:bug-reporting-excellence(卓越的错误报告)
来源仓库:https://github.com/proffesor-for-testing/agentic-qe
仓库路径:skills/bug-reporting-excellence
安装命令:
npx skills add https://github.com/proffesor-for-testing/agentic-qe --skill bug-reporting-excellence
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/proffesor-for-testing/agentic-qe --skill bug-reporting-excellence

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。

bug-reporting-excellence 提供结构化模板确保每份报告包含必要字段与逻辑完整性。适用于 QA 团队标准化缺陷提交流程,减少遗漏并提高开发侧响应速度。采用公式化标题与分级严重程度定义,强化报告的可读性与优先级判断依据。坚持“一个 bug 对应一份报告”原则,避免合并多个问题导致修复复杂度上升。

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/bug-reporting-excellence

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/proffesor-for-testing/agentic-qe --skill bug-r…;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

    它需要操作浏览器,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

bug-reporting-excellence 怎么安装?

在终端执行 npx skills add https://github.com/proffesor-for-testing/agentic-qe --skill bug-reporting-e…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

bug-reporting-excellence 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。

bug-reporting-excellence 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

bug-reporting-excellence 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。

bug-reporting-excellence 用的人多吗?

公开数据是累计安装 2,184 次,近一周安装 91 次,下载 728 次,GitHub 329 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。

bug-reporting-excellence 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
bug-reporting-excellence

卓越的错误报告 · 本页

2,184329操作浏览器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

Bug Reporting Excellence

<default_to_action> When reporting bugs:

  1. TITLE: [Component] fails [Condition] causing [Impact]
  2. DESCRIBE: Expected behavior → Actual behavior → Steps to reproduce
  3. INCLUDE: Environment, severity, screenshots/logs, business impact
  4. ISOLATE: Narrow down conditions (browser, user, amount thresholds)
  5. ONE BUG = ONE REPORT (don't combine issues)

Bug Report Formula:

## [Component] Issue Title
**Severity:** Critical/High/Medium/Low
**Environment:** Production/Staging/Dev

### Expected Behavior
What should happen

### Actual Behavior
What actually happens (with error messages)

### Steps to Reproduce
1. Step one
2. Step two
3. Observe issue

### Impact
How this affects users/business

Critical Success Factors:

  • Reproducible steps (100%)
  • Environment info (100%)
  • Business impact stated (90%)
  • Screenshots or logs (80%) </default_to_action>

Quick Reference Card

Severity Levels

LevelDefinitionExamples
CriticalSystem down, data loss, securityDB deleted, payments broken, credentials exposed
HighMajor feature broken, many usersCan't checkout, search broken, dashboard fails
MediumPartial break, workaround existsFilter broken (refresh works), slow export
LowCosmetic, rare edge caseButton wraps on mobile, tooltip wrong color

Title Formula

❌ Bad: "Checkout broken" ✅ Good: "Payment fails with Visa cards when order total > $1000"

Pattern: [Component] fails [Condition] causing [Impact]


Essential Information

Environment Details

Browser: Chrome 120.0.6099.109 (Windows)
OS: Windows 11 Pro
URL: https://example.com/checkout
Date/Time: 2025-10-17 14:23 UTC
User: test@example.com (ID: 12345)
Request ID: abc-123-def-456

Supporting Evidence

Error Messages:

{
  "error": "Payment service unavailable",
  "code": "GATEWAY_TIMEOUT",
  "requestId": "abc-123-def-456"
}

Console Logs:

[ERROR] PaymentGateway: Connection timeout after 30000ms
  at PaymentGateway.charge (gateway.js:145)

Example: Excellent Bug Report

## [Checkout] Payment processing times out for orders > $1000

**Severity:** High
**Environment:** Production
**Affected Users:** ~15% of premium purchases

### Expected Behavior
Payment completes within 5 seconds regardless of amount.

### Actual Behavior
For orders above $1000, payment gateway times out after 30 seconds.
User sees "Payment failed" error. Order not created.

### Steps to Reproduce
1. Add items totaling $1,050 to cart
2. Proceed to checkout
3. Enter payment: Visa 4532 1234 5678 9010
4. Click "Place Order"
5. Wait 30+ seconds
6. Observe timeout error

### Environment
- Browser: Chrome 120 (Windows 11)
- User: test@example.com
- Request ID: abc-123-def-456

### Evidence
Console error: `PaymentGateway timeout: 30000ms exceeded`
Network: /api/checkout: 30.14s (timeout)

### Impact
- Lost revenue: ~$15K/week from failed orders
- 23 support tickets this week
- Affects 15% of orders over $1000

### Additional Context
Started after Oct 15 deployment (v2.3.0)
Possibly related to PR #456 (fraud check)

Anti-Patterns

❌ BadProblem✅ Good
"Checkout is broken"What doesn't work?"Payment button doesn't respond when clicked"
"I saw an error"No reproduction stepsFull steps with conditions
"Page loads slowly"No specifics"Dashboard takes 12s to load (should be <3s)"
Multiple bugs in oneCan't track separatelyOne report per bug

Agent Integration

// Automated bug triage
const triage = await Task("Triage Bug", {
  title: 'Payment fails for orders > $1000',
  description: bugDescription,
  steps: reproductionSteps
}, "qe-quality-analyzer");

// Returns: { severity, priority, component, suggestedAssignee, relatedIssues }

// Duplicate detection
const dupeCheck = await Task("Check Duplicates", {
  bugReport: newBug,
  similarityThreshold: 0.85
}, "qe-quality-analyzer");

// Bug report enhancement
const enhanced = await Task("Enhance Report", {
  originalReport: userSubmittedBug,
  addMissingInfo: true,
  identifyRootCause: true
}, "qe-production-intelligence");

Agent Coordination Hints

Memory Namespace

aqe/bug-reports/
├── triaged/*          - Bug triage results
├── duplicates/*       - Duplicate detection
├── patterns/*         - Recurring bug patterns
└── root-cause/*       - Root cause analyses

Fleet Coordination

const bugFleet = await FleetManager.coordinate({
  strategy: 'bug-investigation',
  agents: [
    'qe-quality-analyzer',        // Triage and categorize
    'qe-flaky-test-hunter',       // Check if test-related
    'qe-production-intelligence'  // Check production logs
  ],
  topology: 'parallel'
});

Related Skills


Remember

Your bug report is the starting point for someone else's work. Make it complete (all info needed), clear (anyone can follow), concise (no noise), and actionable (developer knows next step).

Good bug reports = Faster fixes = Better product = Happier users

Skill Composition

  • After finding bug → Start with /test-failure-investigator for root cause
  • Prevent regression → Use /regression-testing to add test preventing recurrence
  • Track quality → Feed into /test-metrics-dashboard for trend analysis

Gotchas

  • Agent omits environment details (OS, browser version, node version) — these are critical for reproduction
  • "Steps to reproduce" that start with "1. Open the app" are useless — specify exact URL, user role, and state
  • Agent combines multiple bugs into one report — enforce ONE BUG = ONE REPORT strictly
  • Screenshots without annotations don't help — always highlight the actual error area
  • Severity assessment is often wrong — agent marks everything as "critical" or everything as "low"

平台分布

Claude Code

27.94%
按下载量换算203

Antigravity

23.9%
按下载量换算174

windsurf

18.45%
按下载量换算134

github-copilot

12.67%
按下载量换算92

Codex

8.36%
按下载量换算61

trae

3.29%
按下载量换算24

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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