Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器github未标认证来源可访问许可证需确认审计通过

qa-generating-bug-reportsqa 生成错误报告

Agent Skill

qa-generating-bug-reports 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。

总安装

192

周安装

8

GitHub Stars

5

下载量

64
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:qa-generating-bug-reports(qa 生成错误报告)
来源仓库:https://github.com/wizeline/sdlc-agents
仓库路径:skills/qa-generating-bug-reports
安装命令:
npx skills add https://github.com/wizeline/sdlc-agents --skill qa-generating-bug-reports
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/wizeline/sdlc-agents --skill qa-generating-bug-reports

简介

qa-generating-bug-reports 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。

  • 它支持基于关键词或任务场景的信息匹配,适用于错误报告生成前的资料准备阶段。
  • 通过安装命令 npx skills add https://github.com/wizeline/sdlc-agents --skill qa-generating-bug-reports 添加技能,具体用法可参考仓库中的 SKILL.md。
  • 安装前请确认权限范围、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。

SKILL.md

Generating Bug Reports

This skill standardizes bug report creation across all testing agents. Every discovered defect flows through this skill to ensure consistent, actionable, developer-friendly bug reports.

When to Use

  • Any agent discovers a defect during testing
  • You need to format findings for Jira, GitHub Issues, or similar trackers
  • You're compiling a QA report with multiple findings
  • You want to ensure reproduction steps are complete and unambiguous

Bug Report Structure

Every bug report MUST include these sections:

Required Fields

{
  "bug_id": "BUG-001",
  "title": "Short, specific summary (what + where)",
  "severity": "critical|high|medium|low|info",
  "type": "functional|visual|performance|security|ux|accessibility",
  "status": "new",
  "discovered_by": "agent-name",
  "discovered_at": "2025-01-15T10:30:00Z",

  "environment": {
    "url": "https://staging.example.com/checkout",
    "browser": "chromium 120",
    "viewport": "1440x900",
    "os": "Linux",
    "build": "staging-v2.3.1"
  },

  "description": "Full description of what's wrong and why it matters",

  "reproduction_steps": [
    "1. Navigate to /checkout",
    "2. Add item to cart",
    "3. Click 'Proceed to Payment'",
    "4. Leave the email field empty",
    "5. Click 'Submit Order'",
    "6. OBSERVE: Order submits successfully without email validation"
  ],

  "expected_behavior": "Form should show validation error on the email field",
  "actual_behavior": "Order submits with no email, confirmation page shows 'undefined'",

  "evidence": {
    "screenshots": ["screenshot-before.png", "screenshot-after.png"],
    "console_log": "TypeError: Cannot read property 'email' of undefined",
    "network_log": "POST /api/orders → 201 (should have been 400)",
    "har_file": "checkout-session.har"
  },

  "impact": "Users can place orders without email, breaking order confirmation flow",
  "suggested_fix": "Add server-side email validation in POST /api/orders endpoint"
}

Optional Fields

{
  "related_bugs": ["BUG-002", "BUG-005"],
  "affected_users": "All users on checkout flow",
  "frequency": "100% reproducible",
  "workaround": "Manually enter email before submitting",
  "regression": true,
  "regression_since": "v2.3.0",
  "jira_labels": ["checkout", "validation", "regression"],
  "assignee_suggestion": "backend-team"
}

Severity Classification

Use this guide consistently across all agents:

Critical — Application is unusable or data is at risk

  • Authentication bypass or security vulnerability
  • Data loss or corruption
  • Application crashes or is completely non-functional
  • Financial transaction errors (wrong charges, duplicate payments)

High — Major feature is broken with no workaround

  • Core user journey cannot be completed
  • Significant visual regression affecting usability
  • Performance degradation >5x normal
  • API returning incorrect data

Medium — Feature works but with notable issues

  • Non-critical UI elements broken
  • Error messages missing or unhelpful
  • Moderate performance issues (2-5x normal)
  • Cross-browser inconsistencies affecting UX

Low — Minor cosmetic or polish issues

  • Slight visual misalignment (<5px)
  • Minor typos in UI text
  • Inconsistent spacing or styling
  • Deprecated API warnings in console

Info — Observations, not defects

  • Potential improvements
  • Code quality observations
  • Performance optimization opportunities
  • Accessibility suggestions

Writing Good Bug Titles

The title should let a developer understand the issue at a glance:

Pattern: [Area] What happens + Where/When

Good examples:

  • "Checkout: Order submits without email validation on payment form"
  • "Dashboard: Chart data overlaps legend text at tablet viewport"
  • "API: POST /users returns 500 when name exceeds 255 characters"
  • "Login: Password field accepts paste but shows empty on Safari"

Bad examples:

  • "Bug in checkout" (too vague)
  • "Something wrong" (not descriptive)
  • "Form doesn't work" (which form? what doesn't work?)

Writing Reproduction Steps

Reproduction steps should be precise enough that any developer can follow them:

  1. Start from a known state — "Navigate to /checkout" not "Go to the page"
  2. Be specific about inputs — "Enter 'test@example.com'" not "Enter an email"
  3. One action per step — Don't combine "Click login and enter credentials"
  4. Mark the observation point — "OBSERVE:..." or "EXPECTED:... / ACTUAL:..."
  5. Include timing if relevant — "Wait 5 seconds" or "Quickly click 3 times"

Using the Bug Report Generator

python skills/qa-generating-bug-reports/scripts/generate_report.py \
  --template standard \
  --output bugs/BUG-001.json \
  --screenshots screenshot1.png screenshot2.png

Or generate from agent session data:

python skills/qa-generating-bug-reports/scripts/from_session.py \
  --session session-log.json \
  --output bugs/ \
  --agent-name qa-e2e-exploratory-agent

Markdown Report Format

For human-readable reports (e.g., summary documents):

## BUG-001: Checkout order submits without email validation [HIGH]

**Environment:** Chromium 120 / Desktop (1440×900) / staging-v2.3.1
**Discovered:** 2025-01-15 by qa-e2e-exploratory-agent
**Reproducible:** 100%

### Description
When submitting the checkout form with an empty email field, the order
processes successfully. The confirmation page shows "undefined" where
the email should appear.

### Steps to Reproduce
1. Navigate to /checkout
2. Add any item to cart
3. Click 'Proceed to Payment'
4. Leave the email field empty
5. Click 'Submit Order'
6. **OBSERVE:** Order submits, confirmation shows 'undefined' for email

### Expected vs Actual
- **Expected:** Form validation prevents submission, shows error on email field
- **Actual:** Order submits, confirmation page displays "undefined"

### Evidence
- Screenshot: [before-submit.png] [after-submit.png]
- Console: `TypeError: Cannot read property 'email' of undefined`
- Network: `POST /api/orders → 201` (expected 400)

### Impact
All users can place orders without email, breaking confirmation emails
and order tracking.

Deduplication

Before creating a new bug report, check existing reports for duplicates:

  1. Same URL + same error type = likely duplicate
  2. Same console error message = likely duplicate
  3. Same visual region affected = likely duplicate

If a duplicate is found, append the new evidence to the existing report rather than creating a new one. Add a duplicate_of field if merging.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.44%
按下载量换算23

Claude

30.6%
按下载量换算20

Cursor

15.98%
按下载量换算10

Gemini CLI

8.2%
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

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills