MCP HubMCP Hub
スキル一覧に戻る

xp-practices

proffesor-for-testing
更新日 Today
179 閲覧
99
21
99
GitHubで表示
その他xpagilepair-programmingtddcontinuous-integrationcollaboration

について

このスキルは、TDD、ペアプログラミング、継続的インテグレーションなどのエクストリーム・プログラミング手法を開発者が実践する支援をします。チームコラボレーションの向上、技術的卓越性の導入、持続可能なアジャイルワークフローの確立にご活用ください。また、中核となるXPプラクティスの優先順位付けと適応に関する実践的なガイダンスを提供し、即座に価値を得られるようにします。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/proffesor-for-testing/agentic-qe
Git クローン代替
git clone https://github.com/proffesor-for-testing/agentic-qe.git ~/.claude/skills/xp-practices

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

Extreme Programming (XP) Practices

<default_to_action> When applying XP practices:

  1. START with practices that give immediate value
  2. BUILD supporting practices gradually
  3. ADAPT to your context
  4. MEASURE results

Core XP Practices (Prioritized):

PracticeStart HereWhy First
TDD✅ YesFoundation for everything
Continuous Integration✅ YesFast feedback
Pair Programming✅ YesKnowledge sharing
Collective OwnershipAfter CI+TDDNeeds safety net
Small ReleasesAfter CIInfrastructure dependent

Pairing Quick Start:

Driver-Navigator (Classic):
- Driver: Writes code
- Navigator: Reviews, thinks ahead
- Rotate every 20-30 min

Ping-Pong (with TDD):
A: Write failing test
B: Make test pass + refactor
B: Write next failing test
A: Make test pass + refactor

</default_to_action>

Quick Reference Card

The Five XP Values

ValueMeaningPractice
CommunicationEveryone knows what everyone doesDaily standups, pairing
SimplicitySimplest thing that worksYAGNI, small design
FeedbackGet feedback early and oftenTDD, CI, short iterations
CourageTell truth, adaptRefactor, admit mistakes
RespectEveryone contributes valueSustainable pace, pairing

Core Practices

PracticeDescriptionBenefit
Pair ProgrammingTwo devs, one workstationQuality + knowledge sharing
TDDRed-Green-RefactorConfidence + design
CIIntegrate multiple times/dayFast feedback
Collective OwnershipAnyone can change anythingNo bottlenecks
Sustainable Pace40-hour weeksLong-term productivity
Small ReleasesShip frequentlyRisk reduction

Pair Programming

When to Pair

ContextPair?Why
Complex/risky code✅ AlwaysNeeds multiple perspectives
New technology✅ AlwaysLearning accelerator
Onboarding✅ AlwaysKnowledge transfer
Critical bugs✅ AlwaysTwo heads better
Simple tasks❌ SkipNot worth overhead
Research spikes❌ SkipPair to discuss findings

Pairing Dos and Don'ts

Do:

  • ✅ Switch roles every 20-30 min
  • ✅ Take breaks together
  • ✅ Think out loud
  • ✅ Ask questions
  • ✅ Keep sessions 2-4 hours max

Don't:

  • ❌ Grab keyboard without asking
  • ❌ Check phone while pairing
  • ❌ Dominate conversation
  • ❌ Pair all day (exhausting)

Ensemble (Mob) Programming

Setup: 3+ developers, one screen, rotating driver

[Screen]
   ↓
[Driver] ← Directions from navigators
   ↑
[Navigator 1] [Navigator 2] [Navigator 3]

Rotation: Driver switches every 5-10 min

Best for:

  • Complex problem solving
  • Architectural decisions
  • Learning new frameworks
  • Resolving blockers

Continuous Integration

CI Workflow:

1. Pull latest from main
2. Make small change (<2 hrs work)
3. Run tests locally (all pass)
4. Commit and push
5. CI runs tests automatically
6. If fail → fix immediately

Best Practices:

  • Commit frequently (small changes)
  • Keep build fast (<10 min)
  • Fix broken builds immediately
  • Never commit to broken build

Four Rules of Simple Design

(In priority order)

  1. Passes all tests - Works correctly
  2. Reveals intention - Clear, expressive code
  3. No duplication - DRY principle
  4. Fewest elements - No speculative code

Agent Integration

// Agent-human pair testing
const charter = "Test payment edge cases";
const tests = await Task("Generate Tests", { charter }, "qe-test-generator");
const reviewed = await human.review(tests);
await Task("Implement", { tests: reviewed }, "qe-test-generator");

// Continuous integration with agents
await Task("Risk Analysis", { prDiff }, "qe-regression-risk-analyzer");
await Task("Generate Tests", { changes: prDiff }, "qe-test-generator");
await Task("Execute Tests", { scope: 'affected' }, "qe-test-executor");

// Sustainable pace: agents handle grunt work
const agentWork = ['regression', 'data-generation', 'coverage-analysis'];
const humanWork = ['exploratory', 'risk-assessment', 'strategy'];

Agent Coordination Hints

Memory Namespace

aqe/xp-practices/
├── pairing-sessions/*   - Pair/ensemble session logs
├── ci-metrics/*         - CI health metrics
├── velocity/*           - Team velocity data
└── retrospectives/*     - XP retrospective notes

Fleet Coordination

const xpFleet = await FleetManager.coordinate({
  strategy: 'xp-workflow',
  agents: [
    'qe-test-generator',   // TDD support
    'qe-test-executor',    // CI integration
    'qe-code-reviewer'     // Collective ownership
  ],
  topology: 'parallel'
});

Common Objections

ObjectionResponse
"Pairing is 2x slower"15% slower writing, 15% fewer bugs, net positive
"No time for TDD"Debugging takes longer than testing
"CI is hard to setup"Start simple: one action, one test
"Collective ownership = chaos"Only without tests + CI

Related Skills


Remember

XP practices work as a system. Don't cherry-pick randomly:

  • TDD enables collective ownership
  • CI enables small releases
  • Pairing enables collective ownership
  • Sustainable pace enables everything

With Agents: Agents amplify XP. Pair humans with agents. Agents handle repetitive work, humans provide judgment and creativity.

GitHub リポジトリ

proffesor-for-testing/agentic-qe
パス: .claude/skills/xp-practices
agenticqeagenticsfoundationagentsquality-engineering

関連スキル

sparc-methodology

開発

The SPARC methodology provides a systematic development framework with 17 specialized modes for comprehensive software development from specification to completion. It integrates multi-agent orchestration to handle complex development workflows including architecture design, testing, and deployment. Use this skill when you need structured guidance throughout the entire development lifecycle with automated agent coordination.

スキルを見る

sparc-methodology

開発

The SPARC methodology provides a systematic, multi-agent framework for comprehensive software development. It structures projects through five phases—Specification, Pseudocode, Architecture, Refinement, and Completion—with 17 specialized modes. Developers should use this skill when they need an orchestrated, end-to-end workflow from initial research to deployment and monitoring.

スキルを見る

tdd-london-chicago

その他

This skill helps developers apply London (mock-based) and Chicago (state-based) TDD approaches when practicing test-driven development. It guides style selection based on code type—using Chicago for domain logic and London for external dependencies—and provides structured support through the Red-Green-Refactor cycle. Key capabilities include generating, implementing, and refactoring tests with optimized agents for each phase.

スキルを見る

github-project-management

その他

This GitHub project management skill enables developers to automate issue tracking, project boards, and sprint planning using AI swarm coordination. It's ideal for teams needing synchronized project management across multiple repositories with automated workflows. The skill requires GitHub CLI access and integrates with Claude Flow or RUV swarm MCP servers.

スキルを見る