bug-reporting-excellence
について
このClaudeスキルは、開発者が明確な再現手順と影響分析を確保する構造化テンプレートを使用して、効果的なバグ報告を作成するのを支援します。これは、問題報告、チームのトレーニング、またはバグ報告基準の設定のために設計されています。本スキルは、プロセスを最適化するために、品質分析、本番環境インテリジェンス、不安定なテスト検出のエージェントを提供します。
クイックインストール
Claude Code
推奨/plugin add https://github.com/proffesor-for-testing/agentic-qegit clone https://github.com/proffesor-for-testing/agentic-qe.git ~/.claude/skills/bug-reporting-excellenceこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
Bug Reporting Excellence
<default_to_action> When reporting bugs:
- TITLE:
[Component] fails [Condition] causing [Impact] - DESCRIBE: Expected behavior → Actual behavior → Steps to reproduce
- INCLUDE: Environment, severity, screenshots/logs, business impact
- ISOLATE: Narrow down conditions (browser, user, amount thresholds)
- 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
| Level | Definition | Examples |
|---|---|---|
| Critical | System down, data loss, security | DB deleted, payments broken, credentials exposed |
| High | Major feature broken, many users | Can't checkout, search broken, dashboard fails |
| Medium | Partial break, workaround exists | Filter broken (refresh works), slow export |
| Low | Cosmetic, rare edge case | Button 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: [email protected] (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: [email protected]
- 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
| ❌ Bad | Problem | ✅ Good |
|---|---|---|
| "Checkout is broken" | What doesn't work? | "Payment button doesn't respond when clicked" |
| "I saw an error" | No reproduction steps | Full steps with conditions |
| "Page loads slowly" | No specifics | "Dashboard takes 12s to load (should be <3s)" |
| Multiple bugs in one | Can't track separately | One 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
- technical-writing - Clear bug documentation
- exploratory-testing-advanced - Finding bugs
- sherlock-review - Root cause investigation
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
GitHub リポジトリ
関連スキル
Verification & Quality Assurance
その他This skill automatically verifies and scores the quality of code and agent outputs using a 0.95 accuracy threshold. It performs truth scoring, code correctness checks, and can instantly roll back changes that fail verification. Use it to ensure high-quality outputs and maintain codebase reliability in your development workflow.
Report Writer
その他The Report Writer skill generates professional reports from research and data, supporting technical, business, and academic styles. It structures input content with features like an optional table of contents and outputs formatted markdown. Use this skill to quickly transform raw findings into polished, audience-appropriate documentation.
test-reporting-analytics
その他This skill provides advanced test reporting and analytics dashboards for quality engineering metrics, including predictive analytics and trend analysis. It's designed for communicating quality status, tracking trends, and supporting data-driven decisions about software quality. Developers should use it when building automated reports or dashboards that highlight key metrics and actionable insights for teams or executives.
technical-writing
コミュニケーションThis Claude Skill helps developers create clear, engaging technical content like blog posts, documentation, and tutorials by providing structured guidance and best practices. It emphasizes leading with value, using concrete examples, and maintaining a scannable structure. Use it whenever you need to write or improve technical articles based on real experience.
