[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXKDNXWGR34AVKGVSHA5FD":3,"skill-same:01M6BXKDNXWGR34AVKGVSHA5FD":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":31,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6BXKDNXWGR34AVKGVSHA5FD","Pair Programming",null,"AI-assisted pair programming with multiple modes (driver\u002Fnavigator\u002Fswitch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.","diegopacheco\u002Fai-playground","diegopacheco","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121278?v=4","01M6BXCP8P7GGSJ8M1W2MFDTGT","Diego Pacheco","01M6BXCPD3WM51H465XW9YM4BV",21,"Unlicense","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fclaude-flow-fun\u002F.claude\u002Fskills\u002Fpair-programming\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[5,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"verification","performance optimization","refactoring","learning","real-time","Optimization","navigator","monitoring","code review","code","debugging","sessions","tdd","performance","security","review","testing","2026-11-10 10:12:30",false,"---\nname: Pair Programming\ndescription: AI-assisted pair programming with multiple modes (driver\u002Fnavigator\u002Fswitch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.\n---\n\n# Pair Programming\n\nCollaborative AI pair programming with intelligent role management, real-time quality monitoring, and comprehensive development workflows.\n\n## What This Skill Does\n\nThis skill provides professional pair programming capabilities with AI assistance, supporting multiple collaboration modes, continuous verification, and integrated testing. It manages driver\u002Fnavigator roles, performs real-time code review, tracks quality metrics, and ensures high standards through truth-score verification.\n\n**Key Capabilities:**\n- **Multiple Modes**: Driver, Navigator, Switch, TDD, Review, Mentor, Debug\n- **Real-Time Verification**: Automatic quality scoring with rollback on failures\n- **Role Management**: Seamless switching between driver\u002Fnavigator roles\n- **Testing Integration**: Auto-generate tests, track coverage, continuous testing\n- **Code Review**: Security scanning, performance analysis, best practice enforcement\n- **Session Persistence**: Auto-save, recovery, export, and sharing\n\n## Prerequisites\n\n**Required:**\n- Claude Flow CLI installed (`npm install -g claude-flow@alpha`)\n- Git repository (optional but recommended)\n\n**Recommended:**\n- Testing framework (Jest, pytest, etc.)\n- Linter configured (ESLint, pylint, etc.)\n- Code formatter (Prettier, Black, etc.)\n\n## Quick Start\n\n### Basic Session\n```bash\n# Start simple pair programming\nclaude-flow pair --start\n```\n\n### TDD Session\n```bash\n# Test-driven development\nclaude-flow pair --start \\\n  --mode tdd \\\n  --test-first \\\n  --coverage 90\n```\n\n---\n\n## Complete Guide\n\n### Session Control Commands\n\n#### Starting Sessions\n```bash\n# Basic start\nclaude-flow pair --start\n\n# Expert refactoring session\nclaude-flow pair --start \\\n  --agent senior-dev \\\n  --focus refactor \\\n  --verify \\\n  --threshold 0.98\n\n# Debugging session\nclaude-flow pair --start \\\n  --agent debugger-expert \\\n  --focus debug \\\n  --review\n\n# Learning session\nclaude-flow pair --start \\\n  --mode mentor \\\n  --pace slow \\\n  --examples\n```\n\n#### Session Management\n```bash\n# Check status\nclaude-flow pair --status\n\n# View history\nclaude-flow pair --history\n\n# Pause session\n\u002Fpause [--reason \u003Creason>]\n\n# Resume session\n\u002Fresume\n\n# End session\nclaude-flow pair --end [--save] [--report]\n```\n\n### Available Modes\n\n#### Driver Mode\nYou write code while AI provides guidance.\n\n```bash\nclaude-flow pair --start --mode driver\n```\n\n**Your Responsibilities:**\n- Write actual code\n- Implement solutions\n- Make immediate decisions\n- Handle syntax and structure\n\n**AI Navigator:**\n- Strategic guidance\n- Spot potential issues\n- Suggest improvements\n- Real-time review\n- Track overall direction\n\n**Best For:**\n- Learning new patterns\n- Implementing familiar features\n- Quick iterations\n- Hands-on debugging\n\n**Commands:**\n```\n\u002Fsuggest     - Get implementation suggestions\n\u002Freview      - Request code review\n\u002Fexplain     - Ask for explanations\n\u002Foptimize    - Request optimization ideas\n\u002Fpatterns    - Get pattern recommendations\n```\n\n#### Navigator Mode\nAI writes code while you provide direction.\n\n```bash\nclaude-flow pair --start --mode navigator\n```\n\n**Your Responsibilities:**\n- Provide high-level direction\n- Review generated code\n- Make architectural decisions\n- Ensure business requirements\n\n**AI Driver:**\n- Write implementation code\n- Handle syntax details\n- Implement your guidance\n- Manage boilerplate\n- Execute refactoring\n\n**Best For:**\n- Rapid prototyping\n- Boilerplate generation\n- Learning from AI patterns\n- Exploring solutions\n\n**Commands:**\n```\n\u002Fimplement   - Direct implementation\n\u002Frefactor    - Request refactoring\n\u002Ftest        - Generate tests\n\u002Fdocument    - Add documentation\n\u002Falternate   - See alternative approaches\n```\n\n#### Switch Mode\nAutomatically alternates roles at intervals.\n\n```bash\n# Default 10-minute intervals\nclaude-flow pair --start --mode switch\n\n# 5-minute intervals (rapid)\nclaude-flow pair --start --mode switch --interval 5m\n\n# 15-minute intervals (deep focus)\nclaude-flow pair --start --mode switch --interval 15m\n```\n\n**Handoff Process:**\n1. 30-second warning before switch\n2. Current driver completes thought\n3. Context summary generated\n4. Roles swap smoothly\n5. New driver continues\n\n**Best For:**\n- Balanced collaboration\n- Knowledge sharing\n- Complex features\n- Extended sessions\n\n#### Specialized Modes\n\n**TDD Mode** - Test-Driven Development:\n```bash\nclaude-flow pair --start \\\n  --mode tdd \\\n  --test-first \\\n  --coverage 100\n```\nWorkflow: Write failing test → Implement → Refactor → Repeat\n\n**Review Mode** - Continuous code review:\n```bash\nclaude-flow pair --start \\\n  --mode review \\\n  --strict \\\n  --security\n```\nFeatures: Real-time feedback, security scanning, performance analysis\n\n**Mentor Mode** - Learning-focused:\n```bash\nclaude-flow pair --start \\\n  --mode mentor \\\n  --explain-all \\\n  --pace slow\n```\nFeatures: Detailed explanations, step-by-step guidance, pattern teaching\n\n**Debug Mode** - Problem-solving:\n```bash\nclaude-flow pair --start \\\n  --mode debug \\\n  --verbose \\\n  --trace\n```\nFeatures: Issue identification, root cause analysis, fix suggestions\n\n### In-Session Commands\n\n#### Code Commands\n```\n\u002Fexplain [--level basic|detailed|expert]\n  Explain the current code or selection\n\n\u002Fsuggest [--type refactor|optimize|security|style]\n  Get improvement suggestions\n\n\u002Fimplement \u003Cdescription>\n  Request implementation (navigator mode)\n\n\u002Frefactor [--pattern \u003Cpattern>] [--scope function|file|module]\n  Refactor selected code\n\n\u002Foptimize [--target speed|memory|both]\n  Optimize code for performance\n\n\u002Fdocument [--format jsdoc|markdown|inline]\n  Add documentation to code\n\n\u002Fcomment [--verbose]\n  Add inline comments\n\n\u002Fpattern \u003Cpattern-name> [--example]\n  Apply a design pattern\n```\n\n#### Testing Commands\n```\n\u002Ftest [--watch] [--coverage] [--only \u003Cpattern>]\n  Run test suite\n\n\u002Ftest-gen [--type unit|integration|e2e]\n  Generate tests for current code\n\n\u002Fcoverage [--report html|json|terminal]\n  Check test coverage\n\n\u002Fmock \u003Ctarget> [--realistic]\n  Generate mock data or functions\n\n\u002Ftest-watch [--on-save]\n  Enable test watching\n\n\u002Fsnapshot [--update]\n  Create test snapshots\n```\n\n#### Review Commands\n```\n\u002Freview [--scope current|file|changes] [--strict]\n  Perform code review\n\n\u002Fsecurity [--deep] [--fix]\n  Security analysis\n\n\u002Fperf [--profile] [--suggestions]\n  Performance analysis\n\n\u002Fquality [--detailed]\n  Check code quality metrics\n\n\u002Flint [--fix] [--config \u003Cconfig>]\n  Run linters\n\n\u002Fcomplexity [--threshold \u003Cvalue>]\n  Analyze code complexity\n```\n\n#### Navigation Commands\n```\n\u002Fgoto \u003Cfile>[:line[:column]]\n  Navigate to file or location\n\n\u002Ffind \u003Cpattern> [--regex] [--case-sensitive]\n  Search in project\n\n\u002Frecent [--limit \u003Cn>]\n  Show recent files\n\n\u002Fbookmark [add|list|goto|remove] [\u003Cname>]\n  Manage bookmarks\n\n\u002Fhistory [--limit \u003Cn>] [--filter \u003Cpattern>]\n  Show command history\n\n\u002Ftree [--depth \u003Cn>] [--filter \u003Cpattern>]\n  Show project structure\n```\n\n#### Git Commands\n```\n\u002Fdiff [--staged] [--file \u003Cfile>]\n  Show git diff\n\n\u002Fcommit [--message \u003Cmsg>] [--amend]\n  Commit with verification\n\n\u002Fbranch [create|switch|delete|list] [\u003Cname>]\n  Branch operations\n\n\u002Fstash [save|pop|list|apply] [\u003Cmessage>]\n  Stash operations\n\n\u002Flog [--oneline] [--limit \u003Cn>]\n  View git log\n\n\u002Fblame [\u003Cfile>]\n  Show git blame\n```\n\n#### AI Partner Commands\n```\n\u002Fagent [switch|info|config] [\u003Cagent-name>]\n  Manage AI agent\n\n\u002Fteach \u003Cpreference>\n  Teach the AI your preferences\n\n\u002Ffeedback [positive|negative] \u003Cmessage>\n  Provide feedback to AI\n\n\u002Fpersonality [professional|friendly|concise|verbose]\n  Adjust AI personality\n\n\u002Fexpertise [add|remove|list] [\u003Cdomain>]\n  Set AI expertise focus\n```\n\n#### Metrics Commands\n```\n\u002Fmetrics [--period today|session|week|all]\n  Show session metrics\n\n\u002Fscore [--breakdown]\n  Show quality scores\n\n\u002Fproductivity [--chart]\n  Show productivity metrics\n\n\u002Fleaderboard [--personal|team]\n  Show improvement leaderboard\n```\n\n#### Role & Mode Commands\n```\n\u002Fswitch [--immediate]\n  Switch driver\u002Fnavigator roles\n\n\u002Fmode \u003Ctype>\n  Change mode (driver|navigator|switch|tdd|review|mentor|debug)\n\n\u002Frole\n  Show current role\n\n\u002Fhandoff\n  Prepare role handoff\n```\n\n### Command Shortcuts\n\n| Alias | Full Command |\n|-------|-------------|\n| `\u002Fs` | `\u002Fsuggest` |\n| `\u002Fe` | `\u002Fexplain` |\n| `\u002Ft` | `\u002Ftest` |\n| `\u002Fr` | `\u002Freview` |\n| `\u002Fc` | `\u002Fcommit` |\n| `\u002Fg` | `\u002Fgoto` |\n| `\u002Ff` | `\u002Ffind` |\n| `\u002Fh` | `\u002Fhelp` |\n| `\u002Fsw` | `\u002Fswitch` |\n| `\u002Fst` | `\u002Fstatus` |\n\n### Configuration\n\n#### Basic Configuration\nCreate `.claude-flow\u002Fpair-config.json`:\n\n```json\n{\n  \"pair\": {\n    \"enabled\": true,\n    \"defaultMode\": \"switch\",\n    \"defaultAgent\": \"auto\",\n    \"autoStart\": false,\n    \"theme\": \"professional\"\n  }\n}\n```\n\n#### Complete Configuration\n\n```json\n{\n  \"pair\": {\n    \"general\": {\n      \"enabled\": true,\n      \"defaultMode\": \"switch\",\n      \"defaultAgent\": \"senior-dev\",\n      \"language\": \"javascript\",\n      \"timezone\": \"UTC\"\n    },\n\n    \"modes\": {\n      \"driver\": {\n        \"enabled\": true,\n        \"suggestions\": true,\n        \"realTimeReview\": true,\n        \"autoComplete\": false\n      },\n      \"navigator\": {\n        \"enabled\": true,\n        \"codeGeneration\": true,\n        \"explanations\": true,\n        \"alternatives\": true\n      },\n      \"switch\": {\n        \"enabled\": true,\n        \"interval\": \"10m\",\n        \"warning\": \"30s\",\n        \"autoSwitch\": true,\n        \"pauseOnIdle\": true\n      }\n    },\n\n    \"verification\": {\n      \"enabled\": true,\n      \"threshold\": 0.95,\n      \"autoRollback\": true,\n      \"preCommitCheck\": true,\n      \"continuousMonitoring\": true,\n      \"blockOnFailure\": true\n    },\n\n    \"testing\": {\n      \"enabled\": true,\n      \"autoRun\": true,\n      \"framework\": \"jest\",\n      \"onSave\": true,\n      \"coverage\": {\n        \"enabled\": true,\n        \"minimum\": 80,\n        \"enforce\": true,\n        \"reportFormat\": \"html\"\n      }\n    },\n\n    \"review\": {\n      \"enabled\": true,\n      \"continuous\": true,\n      \"preCommit\": true,\n      \"security\": true,\n      \"performance\": true,\n      \"style\": true,\n      \"complexity\": {\n        \"maxComplexity\": 10,\n        \"maxDepth\": 4,\n        \"maxLines\": 100\n      }\n    },\n\n    \"git\": {\n      \"enabled\": true,\n      \"autoCommit\": false,\n      \"commitTemplate\": \"feat: {message}\",\n      \"signCommits\": false,\n      \"pushOnEnd\": false,\n      \"branchProtection\": true\n    },\n\n    \"session\": {\n      \"autoSave\": true,\n      \"saveInterval\": \"5m\",\n      \"maxDuration\": \"4h\",\n      \"idleTimeout\": \"15m\",\n      \"breakReminder\": \"45m\",\n      \"metricsInterval\": \"1m\"\n    },\n\n    \"ai\": {\n      \"model\": \"advanced\",\n      \"temperature\": 0.7,\n      \"maxTokens\": 4000,\n      \"personality\": \"professional\",\n      \"expertise\": [\"backend\", \"testing\", \"security\"],\n      \"learningEnabled\": true\n    }\n  }\n}\n```\n\n#### Built-in Agents\n\n```json\n{\n  \"agents\": {\n    \"senior-dev\": {\n      \"expertise\": [\"architecture\", \"patterns\", \"optimization\"],\n      \"style\": \"thorough\",\n      \"reviewLevel\": \"strict\"\n    },\n    \"tdd-specialist\": {\n      \"expertise\": [\"testing\", \"mocks\", \"coverage\"],\n      \"style\": \"test-first\",\n      \"reviewLevel\": \"comprehensive\"\n    },\n    \"debugger-expert\": {\n      \"expertise\": [\"debugging\", \"profiling\", \"tracing\"],\n      \"style\": \"analytical\",\n      \"reviewLevel\": \"focused\"\n    },\n    \"junior-dev\": {\n      \"expertise\": [\"learning\", \"basics\", \"documentation\"],\n      \"style\": \"questioning\",\n      \"reviewLevel\": \"educational\"\n    }\n  }\n}\n```\n\n#### CLI Configuration\n```bash\n# Set configuration\nclaude-flow pair config set defaultMode switch\nclaude-flow pair config set verification.threshold 0.98\n\n# Get configuration\nclaude-flow pair config get\nclaude-flow pair config get defaultMode\n\n# Export\u002FImport\nclaude-flow pair config export > config.json\nclaude-flow pair config import config.json\n\n# Reset\nclaude-flow pair config reset\n```\n\n#### Profile Management\n\nCreate reusable profiles:\n\n```bash\n# Create profile\nclaude-flow pair profile create refactoring \\\n  --mode driver \\\n  --verify true \\\n  --threshold 0.98 \\\n  --focus refactor\n\n# Use profile\nclaude-flow pair --start --profile refactoring\n\n# List profiles\nclaude-flow pair profile list\n```\n\nProfile configuration:\n```json\n{\n  \"profiles\": {\n    \"refactoring\": {\n      \"mode\": \"driver\",\n      \"verification\": {\n        \"enabled\": true,\n        \"threshold\": 0.98\n      },\n      \"focus\": \"refactor\"\n    },\n    \"debugging\": {\n      \"mode\": \"navigator\",\n      \"agent\": \"debugger-expert\",\n      \"trace\": true,\n      \"verbose\": true\n    },\n    \"learning\": {\n      \"mode\": \"mentor\",\n      \"pace\": \"slow\",\n      \"explanations\": \"detailed\",\n      \"examples\": true\n    }\n  }\n}\n```\n\n### Real-World Examples\n\n#### Example 1: Feature Implementation\n\nImplementing user authentication with JWT tokens:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode switch \\\n  --agent senior-dev \\\n  --focus implement \\\n  --verify \\\n  --test\n```\n\n**Session Flow:**\n```\n? Starting pair programming for authentication feature...\n\n[DRIVER: You - 10 minutes]\n\u002Fexplain JWT authentication flow\n> AI explains JWT concepts and best practices\n\n\u002Fsuggest implementation approach\n> AI suggests using middleware pattern with refresh tokens\n\n# You write the basic auth middleware structure\n\n[SWITCH TO NAVIGATOR]\n\n[NAVIGATOR: AI - 10 minutes]\n\u002Fimplement JWT token generation with refresh tokens\n> AI generates secure token implementation\n\n\u002Ftest-gen\n> AI creates comprehensive test suite\n\n[SWITCH TO DRIVER]\n\n[DRIVER: You - 10 minutes]\n# You refine the implementation\n\u002Freview --security\n> AI performs security review, suggests improvements\n\n\u002Fcommit --message \"feat: JWT authentication with refresh tokens\"\n✅ Truth Score: 0.98 - Committed successfully\n```\n\n#### Example 2: Bug Fixing\n\nDebugging a memory leak in Node.js:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode navigator \\\n  --agent debugger-expert \\\n  --focus debug \\\n  --trace\n```\n\n**Session Flow:**\n```\n? Starting debugging session...\n\n\u002Fstatus\n> Analyzing application for memory issues...\n\n\u002Fperf --profile\n> Memory usage growing: 150MB → 450MB over 10 minutes\n\n\u002Ffind \"new EventEmitter\" --regex\n> Found 3 instances of EventEmitter creation\n\n\u002Finspect eventEmitters --deep\n> Discovering listeners not being removed\n\n\u002Fsuggest fix for memory leak\n> AI suggests: \"Add removeListener in cleanup functions\"\n\n\u002Fimplement cleanup functions for all event emitters\n> AI generates proper cleanup code\n\n\u002Ftest\n> Memory stable at 150MB ✅\n\n\u002Fcommit --message \"fix: memory leak in event emitters\"\n```\n\n#### Example 3: TDD Session\n\nBuilding shopping cart with test-driven development:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode tdd \\\n  --agent tdd-specialist \\\n  --test-first\n```\n\n**Session Flow:**\n```\n? TDD Session: Shopping Cart Feature\n\n[RED PHASE]\n\u002Ftest-gen \"add item to cart\"\n> AI writes failing test:\n  ✗ should add item to cart\n  ✗ should update quantity for existing item\n  ✗ should calculate total price\n\n[GREEN PHASE]\n\u002Fimplement minimal cart functionality\n> You write just enough code to pass tests\n\n\u002Ftest\n> Tests passing: 3\u002F3 ✅\n\n[REFACTOR PHASE]\n\u002Frefactor --pattern repository\n> AI refactors to repository pattern\n\n\u002Ftest\n> Tests still passing: 3\u002F3 ✅\n\n[NEXT CYCLE]\n\u002Ftest-gen \"remove item from cart\"\n> AI writes new failing tests...\n```\n\n#### Example 4: Code Refactoring\n\nModernizing legacy code:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode driver \\\n  --focus refactor \\\n  --verify \\\n  --threshold 0.98\n```\n\n**Session Flow:**\n```\n? Refactoring Session: Modernizing UserService\n\n\u002Fanalyze UserService.js\n> AI identifies:\n  - Callback hell (5 levels deep)\n  - No error handling\n  - Tight coupling\n  - No tests\n\n\u002Fsuggest refactoring plan\n> AI suggests:\n  1. Convert callbacks to async\u002Fawait\n  2. Add error boundaries\n  3. Extract dependencies\n  4. Add unit tests\n\n\u002Ftest-gen --before-refactor\n> AI generates tests for current behavior\n\n\u002Frefactor callbacks to async\u002Fawait\n# You refactor with AI guidance\n\n\u002Ftest\n> All tests passing ✅\n\n\u002Freview --compare\n> AI shows before\u002Fafter comparison\n> Code complexity: 35 → 12\n> Truth score: 0.99 ✅\n\n\u002Fcommit --message \"refactor: modernize UserService with async\u002Fawait\"\n```\n\n#### Example 5: Performance Optimization\n\nOptimizing slow React application:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode switch \\\n  --agent performance-expert \\\n  --focus optimize \\\n  --profile\n```\n\n**Session Flow:**\n```\n? Performance Optimization Session\n\n\u002Fperf --profile\n> React DevTools Profiler Results:\n  - ProductList: 450ms render\n  - CartSummary: 200ms render\n  - Unnecessary re-renders: 15\n\n\u002Fsuggest optimizations for ProductList\n> AI suggests:\n  1. Add React.memo\n  2. Use useMemo for expensive calculations\n  3. Implement virtualization for long lists\n\n\u002Fimplement React.memo and useMemo\n# You implement with AI guidance\n\n\u002Fperf --profile\n> ProductList: 45ms render (90% improvement!) ✅\n\n\u002Fimplement virtualization with react-window\n> AI implements virtual scrolling\n\n\u002Fperf --profile\n> ProductList: 12ms render (97% improvement!) ✅\n> FPS: 60 stable ✅\n\n\u002Fcommit --message \"perf: optimize ProductList with memoization and virtualization\"\n```\n\n#### Example 6: API Development\n\nBuilding RESTful API with Express:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode navigator \\\n  --agent backend-expert \\\n  --focus implement \\\n  --test\n```\n\n**Session Flow:**\n```\n? API Development Session\n\n\u002Fdesign REST API for blog platform\n> AI designs endpoints:\n  POST   \u002Fapi\u002Fposts\n  GET    \u002Fapi\u002Fposts\n  GET    \u002Fapi\u002Fposts\u002F:id\n  PUT    \u002Fapi\u002Fposts\u002F:id\n  DELETE \u002Fapi\u002Fposts\u002F:id\n\n\u002Fimplement CRUD endpoints with validation\n> AI implements with Express + Joi validation\n\n\u002Ftest-gen --integration\n> AI generates integration tests\n\n\u002Fsecurity --api\n> AI adds:\n  - Rate limiting\n  - Input sanitization\n  - JWT authentication\n  - CORS configuration\n\n\u002Fdocument --openapi\n> AI generates OpenAPI documentation\n\n\u002Ftest --integration\n> All endpoints tested: 15\u002F15 ✅\n```\n\n### Session Templates\n\n#### Quick Start Templates\n\n```bash\n# Refactoring template\nclaude-flow pair --template refactor\n# Focus: Code improvement\n# Verification: High (0.98)\n# Testing: After each change\n# Review: Continuous\n\n# Feature template\nclaude-flow pair --template feature\n# Focus: Implementation\n# Verification: Standard (0.95)\n# Testing: On completion\n# Review: Pre-commit\n\n# Debug template\nclaude-flow pair --template debug\n# Focus: Problem solving\n# Verification: Moderate (0.90)\n# Testing: Regression tests\n# Review: Root cause\n\n# Learning template\nclaude-flow pair --template learn\n# Mode: Mentor\n# Pace: Slow\n# Explanations: Detailed\n# Examples: Many\n```\n\n### Session Management\n\n#### Session Status\n\n```bash\nclaude-flow pair --status\n```\n\n**Output:**\n```\n? Pair Programming Session\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nSession ID: pair_1755021234567\nDuration: 45 minutes\nStatus: Active\n\nPartner: senior-dev\nCurrent Role: DRIVER (you)\nMode: Switch (10m intervals)\nNext Switch: in 3 minutes\n\n? Metrics:\n├── Truth Score: 0.982 ✅\n├── Lines Changed: 234\n├── Files Modified: 5\n├── Tests Added: 12\n├── Coverage: 87% ↑3%\n└── Commits: 3\n\n? Focus: Implementation\n? Current File: src\u002Fauth\u002Flogin.js\n```\n\n#### Session History\n\n```bash\nclaude-flow pair --history\n```\n\n**Output:**\n```\n? Session History\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n1. 2024-01-15 14:30 - 16:45 (2h 15m)\n   Partner: expert-coder\n   Focus: Refactoring\n   Truth Score: 0.975\n   Changes: +340 -125 lines\n\n2. 2024-01-14 10:00 - 11:30 (1h 30m)\n   Partner: tdd-specialist\n   Focus: Testing\n   Truth Score: 0.991\n   Tests Added: 24\n\n3. 2024-01-13 15:00 - 17:00 (2h)\n   Partner: debugger-expert\n   Focus: Bug Fixing\n   Truth Score: 0.968\n   Issues Fixed: 5\n```\n\n#### Session Persistence\n\n```bash\n# Save session\nclaude-flow pair --save [--name \u003Cname>]\n\n# Load session\nclaude-flow pair --load \u003Csession-id>\n\n# Export session\nclaude-flow pair --export \u003Csession-id> [--format json|md]\n\n# Generate report\nclaude-flow pair --report \u003Csession-id>\n```\n\n#### Background Sessions\n\n```bash\n# Start in background\nclaude-flow pair --start --background\n\n# Monitor background session\nclaude-flow pair --monitor\n\n# Attach to background session\nclaude-flow pair --attach \u003Csession-id>\n\n# End background session\nclaude-flow pair --end \u003Csession-id>\n```\n\n### Advanced Features\n\n#### Custom Commands\n\nDefine in configuration:\n\n```json\n{\n  \"customCommands\": {\n    \"tdd\": \"\u002Ftest-gen && \u002Ftest --watch\",\n    \"full-review\": \"\u002Flint --fix && \u002Ftest && \u002Freview --strict\",\n    \"quick-fix\": \"\u002Fsuggest --type fix && \u002Fimplement && \u002Ftest\"\n  }\n}\n```\n\nUse custom commands:\n```\n\u002Fcustom tdd\n\u002Fcustom full-review\n```\n\n#### Command Chaining\n\n```\n\u002Ftest && \u002Fcommit && \u002Fpush\n\u002Flint --fix && \u002Ftest && \u002Freview --strict\n```\n\n#### Session Recording\n\n```bash\n# Start with recording\nclaude-flow pair --start --record\n\n# Replay session\nclaude-flow pair --replay \u003Csession-id>\n\n# Session analytics\nclaude-flow pair --analytics \u003Csession-id>\n```\n\n#### Integration Options\n\n**With Git:**\n```bash\nclaude-flow pair --start --git --auto-commit\n```\n\n**With CI\u002FCD:**\n```bash\nclaude-flow pair --start --ci --non-interactive\n```\n\n**With IDE:**\n```bash\nclaude-flow pair --start --ide vscode\n```\n\n### Best Practices\n\n#### Session Practices\n1. **Clear Goals** - Define session objectives upfront\n2. **Appropriate Mode** - Choose based on task type\n3. **Enable Verification** - For critical code paths\n4. **Regular Testing** - Maintain quality continuously\n5. **Session Notes** - Document important decisions\n6. **Regular Breaks** - Take breaks every 45-60 minutes\n\n#### Code Practices\n1. **Test Early** - Run tests after each change\n2. **Verify Before Commit** - Check truth scores\n3. **Review Security** - Always for sensitive code\n4. **Profile Performance** - Use `\u002Fperf` for optimization\n5. **Save Sessions** - For complex work\n6. **Learn from AI** - Ask questions frequently\n\n#### Mode Selection\n- **Driver Mode**: When learning, controlling implementation\n- **Navigator Mode**: For rapid prototyping, generation\n- **Switch Mode**: Long sessions, balanced collaboration\n- **TDD Mode**: Building with tests\n- **Review Mode**: Quality focus\n- **Mentor Mode**: Learning priority\n- **Debug Mode**: Fixing issues\n\n### Troubleshooting\n\n#### Session Won't Start\n- Check agent availability\n- Verify configuration file syntax\n- Ensure clean workspace\n- Review log files\n\n#### Session Disconnected\n- Use `--recover` to restore\n- Check network connection\n- Verify background processes\n- Review auto-save files\n\n#### Poor Performance\n- Reduce verification threshold\n- Disable continuous testing\n- Check system resources\n- Use lighter AI model\n\n#### Configuration Issues\n- Validate JSON syntax\n- Check file permissions\n- Review priority order (CLI > env > project > user > global)\n- Run `claude-flow pair config validate`\n\n### Quality Metrics\n\n#### Truth Score Thresholds\n```\nError:   \u003C 0.90 ❌\nWarning: 0.90 - 0.95 ⚠️\nGood:    0.95 - 0.98 ✅\nExcellent: > 0.98 ?\n```\n\n#### Coverage Thresholds\n```\nError:   \u003C 70% ❌\nWarning: 70% - 80% ⚠️\nGood:    80% - 90% ✅\nExcellent: > 90% ?\n```\n\n#### Complexity Thresholds\n```\nError:   > 15 ❌\nWarning: 10 - 15 ⚠️\nGood:    5 - 10 ✅\nExcellent: \u003C 5 ?\n```\n\n### Environment Variables\n\nOverride configuration via environment:\n\n```bash\nexport CLAUDE_PAIR_MODE=driver\nexport CLAUDE_PAIR_VERIFY=true\nexport CLAUDE_PAIR_THRESHOLD=0.98\nexport CLAUDE_PAIR_AGENT=senior-dev\nexport CLAUDE_PAIR_AUTO_TEST=true\n```\n\n### Command History\n\nNavigate history:\n- `↑\u002F↓` - Navigate through command history\n- `Ctrl+R` - Search command history\n- `!!` - Repeat last command\n- `!\u003Cn>` - Run command n from history\n\n### Keyboard Shortcuts (Configurable)\n\nDefault shortcuts:\n```json\n{\n  \"shortcuts\": {\n    \"switch\": \"ctrl+shift+s\",\n    \"suggest\": \"ctrl+space\",\n    \"review\": \"ctrl+r\",\n    \"test\": \"ctrl+t\"\n  }\n}\n```\n\n### Related Commands\n\n- `claude-flow pair --help` - Show help\n- `claude-flow pair config` - Manage configuration\n- `claude-flow pair profile` - Manage profiles\n- `claude-flow pair templates` - List templates\n- `claude-flow pair agents` - List available agents\n","# Pair Programming\n\nCollaborative AI pair programming with intelligent role management, real-time quality monitoring, and comprehensive development workflows.\n\n## What This Skill Does\n\nThis skill provides professional pair programming capabilities with AI assistance, supporting multiple collaboration modes, continuous verification, and integrated testing. It manages driver\u002Fnavigator roles, performs real-time code review, tracks quality metrics, and ensures high standards through truth-score verification.\n\n**Key Capabilities:**\n- **Multiple Modes**: Driver, Navigator, Switch, TDD, Review, Mentor, Debug\n- **Real-Time Verification**: Automatic quality scoring with rollback on failures\n- **Role Management**: Seamless switching between driver\u002Fnavigator roles\n- **Testing Integration**: Auto-generate tests, track coverage, continuous testing\n- **Code Review**: Security scanning, performance analysis, best practice enforcement\n- **Session Persistence**: Auto-save, recovery, export, and sharing\n\n## Prerequisites\n\n**Required:**\n- Claude Flow CLI installed (`npm install -g claude-flow@alpha`)\n- Git repository (optional but recommended)\n\n**Recommended:**\n- Testing framework (Jest, pytest, etc.)\n- Linter configured (ESLint, pylint, etc.)\n- Code formatter (Prettier, Black, etc.)\n\n## Quick Start\n\n### Basic Session\n```bash\n# Start simple pair programming\nclaude-flow pair --start\n```\n\n### TDD Session\n```bash\n# Test-driven development\nclaude-flow pair --start \\\n  --mode tdd \\\n  --test-first \\\n  --coverage 90\n```\n\n---\n\n## Complete Guide\n\n### Session Control Commands\n\n#### Starting Sessions\n```bash\n# Basic start\nclaude-flow pair --start\n\n# Expert refactoring session\nclaude-flow pair --start \\\n  --agent senior-dev \\\n  --focus refactor \\\n  --verify \\\n  --threshold 0.98\n\n# Debugging session\nclaude-flow pair --start \\\n  --agent debugger-expert \\\n  --focus debug \\\n  --review\n\n# Learning session\nclaude-flow pair --start \\\n  --mode mentor \\\n  --pace slow \\\n  --examples\n```\n\n#### Session Management\n```bash\n# Check status\nclaude-flow pair --status\n\n# View history\nclaude-flow pair --history\n\n# Pause session\n\u002Fpause [--reason \u003Creason>]\n\n# Resume session\n\u002Fresume\n\n# End session\nclaude-flow pair --end [--save] [--report]\n```\n\n### Available Modes\n\n#### Driver Mode\nYou write code while AI provides guidance.\n\n```bash\nclaude-flow pair --start --mode driver\n```\n\n**Your Responsibilities:**\n- Write actual code\n- Implement solutions\n- Make immediate decisions\n- Handle syntax and structure\n\n**AI Navigator:**\n- Strategic guidance\n- Spot potential issues\n- Suggest improvements\n- Real-time review\n- Track overall direction\n\n**Best For:**\n- Learning new patterns\n- Implementing familiar features\n- Quick iterations\n- Hands-on debugging\n\n**Commands:**\n```\n\u002Fsuggest     - Get implementation suggestions\n\u002Freview      - Request code review\n\u002Fexplain     - Ask for explanations\n\u002Foptimize    - Request optimization ideas\n\u002Fpatterns    - Get pattern recommendations\n```\n\n#### Navigator Mode\nAI writes code while you provide direction.\n\n```bash\nclaude-flow pair --start --mode navigator\n```\n\n**Your Responsibilities:**\n- Provide high-level direction\n- Review generated code\n- Make architectural decisions\n- Ensure business requirements\n\n**AI Driver:**\n- Write implementation code\n- Handle syntax details\n- Implement your guidance\n- Manage boilerplate\n- Execute refactoring\n\n**Best For:**\n- Rapid prototyping\n- Boilerplate generation\n- Learning from AI patterns\n- Exploring solutions\n\n**Commands:**\n```\n\u002Fimplement   - Direct implementation\n\u002Frefactor    - Request refactoring\n\u002Ftest        - Generate tests\n\u002Fdocument    - Add documentation\n\u002Falternate   - See alternative approaches\n```\n\n#### Switch Mode\nAutomatically alternates roles at intervals.\n\n```bash\n# Default 10-minute intervals\nclaude-flow pair --start --mode switch\n\n# 5-minute intervals (rapid)\nclaude-flow pair --start --mode switch --interval 5m\n\n# 15-minute intervals (deep focus)\nclaude-flow pair --start --mode switch --interval 15m\n```\n\n**Handoff Process:**\n1. 30-second warning before switch\n2. Current driver completes thought\n3. Context summary generated\n4. Roles swap smoothly\n5. New driver continues\n\n**Best For:**\n- Balanced collaboration\n- Knowledge sharing\n- Complex features\n- Extended sessions\n\n#### Specialized Modes\n\n**TDD Mode** - Test-Driven Development:\n```bash\nclaude-flow pair --start \\\n  --mode tdd \\\n  --test-first \\\n  --coverage 100\n```\nWorkflow: Write failing test → Implement → Refactor → Repeat\n\n**Review Mode** - Continuous code review:\n```bash\nclaude-flow pair --start \\\n  --mode review \\\n  --strict \\\n  --security\n```\nFeatures: Real-time feedback, security scanning, performance analysis\n\n**Mentor Mode** - Learning-focused:\n```bash\nclaude-flow pair --start \\\n  --mode mentor \\\n  --explain-all \\\n  --pace slow\n```\nFeatures: Detailed explanations, step-by-step guidance, pattern teaching\n\n**Debug Mode** - Problem-solving:\n```bash\nclaude-flow pair --start \\\n  --mode debug \\\n  --verbose \\\n  --trace\n```\nFeatures: Issue identification, root cause analysis, fix suggestions\n\n### In-Session Commands\n\n#### Code Commands\n```\n\u002Fexplain [--level basic|detailed|expert]\n  Explain the current code or selection\n\n\u002Fsuggest [--type refactor|optimize|security|style]\n  Get improvement suggestions\n\n\u002Fimplement \u003Cdescription>\n  Request implementation (navigator mode)\n\n\u002Frefactor [--pattern \u003Cpattern>] [--scope function|file|module]\n  Refactor selected code\n\n\u002Foptimize [--target speed|memory|both]\n  Optimize code for performance\n\n\u002Fdocument [--format jsdoc|markdown|inline]\n  Add documentation to code\n\n\u002Fcomment [--verbose]\n  Add inline comments\n\n\u002Fpattern \u003Cpattern-name> [--example]\n  Apply a design pattern\n```\n\n#### Testing Commands\n```\n\u002Ftest [--watch] [--coverage] [--only \u003Cpattern>]\n  Run test suite\n\n\u002Ftest-gen [--type unit|integration|e2e]\n  Generate tests for current code\n\n\u002Fcoverage [--report html|json|terminal]\n  Check test coverage\n\n\u002Fmock \u003Ctarget> [--realistic]\n  Generate mock data or functions\n\n\u002Ftest-watch [--on-save]\n  Enable test watching\n\n\u002Fsnapshot [--update]\n  Create test snapshots\n```\n\n#### Review Commands\n```\n\u002Freview [--scope current|file|changes] [--strict]\n  Perform code review\n\n\u002Fsecurity [--deep] [--fix]\n  Security analysis\n\n\u002Fperf [--profile] [--suggestions]\n  Performance analysis\n\n\u002Fquality [--detailed]\n  Check code quality metrics\n\n\u002Flint [--fix] [--config \u003Cconfig>]\n  Run linters\n\n\u002Fcomplexity [--threshold \u003Cvalue>]\n  Analyze code complexity\n```\n\n#### Navigation Commands\n```\n\u002Fgoto \u003Cfile>[:line[:column]]\n  Navigate to file or location\n\n\u002Ffind \u003Cpattern> [--regex] [--case-sensitive]\n  Search in project\n\n\u002Frecent [--limit \u003Cn>]\n  Show recent files\n\n\u002Fbookmark [add|list|goto|remove] [\u003Cname>]\n  Manage bookmarks\n\n\u002Fhistory [--limit \u003Cn>] [--filter \u003Cpattern>]\n  Show command history\n\n\u002Ftree [--depth \u003Cn>] [--filter \u003Cpattern>]\n  Show project structure\n```\n\n#### Git Commands\n```\n\u002Fdiff [--staged] [--file \u003Cfile>]\n  Show git diff\n\n\u002Fcommit [--message \u003Cmsg>] [--amend]\n  Commit with verification\n\n\u002Fbranch [create|switch|delete|list] [\u003Cname>]\n  Branch operations\n\n\u002Fstash [save|pop|list|apply] [\u003Cmessage>]\n  Stash operations\n\n\u002Flog [--oneline] [--limit \u003Cn>]\n  View git log\n\n\u002Fblame [\u003Cfile>]\n  Show git blame\n```\n\n#### AI Partner Commands\n```\n\u002Fagent [switch|info|config] [\u003Cagent-name>]\n  Manage AI agent\n\n\u002Fteach \u003Cpreference>\n  Teach the AI your preferences\n\n\u002Ffeedback [positive|negative] \u003Cmessage>\n  Provide feedback to AI\n\n\u002Fpersonality [professional|friendly|concise|verbose]\n  Adjust AI personality\n\n\u002Fexpertise [add|remove|list] [\u003Cdomain>]\n  Set AI expertise focus\n```\n\n#### Metrics Commands\n```\n\u002Fmetrics [--period today|session|week|all]\n  Show session metrics\n\n\u002Fscore [--breakdown]\n  Show quality scores\n\n\u002Fproductivity [--chart]\n  Show productivity metrics\n\n\u002Fleaderboard [--personal|team]\n  Show improvement leaderboard\n```\n\n#### Role & Mode Commands\n```\n\u002Fswitch [--immediate]\n  Switch driver\u002Fnavigator roles\n\n\u002Fmode \u003Ctype>\n  Change mode (driver|navigator|switch|tdd|review|mentor|debug)\n\n\u002Frole\n  Show current role\n\n\u002Fhandoff\n  Prepare role handoff\n```\n\n### Command Shortcuts\n\n| Alias | Full Command |\n|-------|-------------|\n| `\u002Fs` | `\u002Fsuggest` |\n| `\u002Fe` | `\u002Fexplain` |\n| `\u002Ft` | `\u002Ftest` |\n| `\u002Fr` | `\u002Freview` |\n| `\u002Fc` | `\u002Fcommit` |\n| `\u002Fg` | `\u002Fgoto` |\n| `\u002Ff` | `\u002Ffind` |\n| `\u002Fh` | `\u002Fhelp` |\n| `\u002Fsw` | `\u002Fswitch` |\n| `\u002Fst` | `\u002Fstatus` |\n\n### Configuration\n\n#### Basic Configuration\nCreate `.claude-flow\u002Fpair-config.json`:\n\n```json\n{\n  \"pair\": {\n    \"enabled\": true,\n    \"defaultMode\": \"switch\",\n    \"defaultAgent\": \"auto\",\n    \"autoStart\": false,\n    \"theme\": \"professional\"\n  }\n}\n```\n\n#### Complete Configuration\n\n```json\n{\n  \"pair\": {\n    \"general\": {\n      \"enabled\": true,\n      \"defaultMode\": \"switch\",\n      \"defaultAgent\": \"senior-dev\",\n      \"language\": \"javascript\",\n      \"timezone\": \"UTC\"\n    },\n\n    \"modes\": {\n      \"driver\": {\n        \"enabled\": true,\n        \"suggestions\": true,\n        \"realTimeReview\": true,\n        \"autoComplete\": false\n      },\n      \"navigator\": {\n        \"enabled\": true,\n        \"codeGeneration\": true,\n        \"explanations\": true,\n        \"alternatives\": true\n      },\n      \"switch\": {\n        \"enabled\": true,\n        \"interval\": \"10m\",\n        \"warning\": \"30s\",\n        \"autoSwitch\": true,\n        \"pauseOnIdle\": true\n      }\n    },\n\n    \"verification\": {\n      \"enabled\": true,\n      \"threshold\": 0.95,\n      \"autoRollback\": true,\n      \"preCommitCheck\": true,\n      \"continuousMonitoring\": true,\n      \"blockOnFailure\": true\n    },\n\n    \"testing\": {\n      \"enabled\": true,\n      \"autoRun\": true,\n      \"framework\": \"jest\",\n      \"onSave\": true,\n      \"coverage\": {\n        \"enabled\": true,\n        \"minimum\": 80,\n        \"enforce\": true,\n        \"reportFormat\": \"html\"\n      }\n    },\n\n    \"review\": {\n      \"enabled\": true,\n      \"continuous\": true,\n      \"preCommit\": true,\n      \"security\": true,\n      \"performance\": true,\n      \"style\": true,\n      \"complexity\": {\n        \"maxComplexity\": 10,\n        \"maxDepth\": 4,\n        \"maxLines\": 100\n      }\n    },\n\n    \"git\": {\n      \"enabled\": true,\n      \"autoCommit\": false,\n      \"commitTemplate\": \"feat: {message}\",\n      \"signCommits\": false,\n      \"pushOnEnd\": false,\n      \"branchProtection\": true\n    },\n\n    \"session\": {\n      \"autoSave\": true,\n      \"saveInterval\": \"5m\",\n      \"maxDuration\": \"4h\",\n      \"idleTimeout\": \"15m\",\n      \"breakReminder\": \"45m\",\n      \"metricsInterval\": \"1m\"\n    },\n\n    \"ai\": {\n      \"model\": \"advanced\",\n      \"temperature\": 0.7,\n      \"maxTokens\": 4000,\n      \"personality\": \"professional\",\n      \"expertise\": [\"backend\", \"testing\", \"security\"],\n      \"learningEnabled\": true\n    }\n  }\n}\n```\n\n#### Built-in Agents\n\n```json\n{\n  \"agents\": {\n    \"senior-dev\": {\n      \"expertise\": [\"architecture\", \"patterns\", \"optimization\"],\n      \"style\": \"thorough\",\n      \"reviewLevel\": \"strict\"\n    },\n    \"tdd-specialist\": {\n      \"expertise\": [\"testing\", \"mocks\", \"coverage\"],\n      \"style\": \"test-first\",\n      \"reviewLevel\": \"comprehensive\"\n    },\n    \"debugger-expert\": {\n      \"expertise\": [\"debugging\", \"profiling\", \"tracing\"],\n      \"style\": \"analytical\",\n      \"reviewLevel\": \"focused\"\n    },\n    \"junior-dev\": {\n      \"expertise\": [\"learning\", \"basics\", \"documentation\"],\n      \"style\": \"questioning\",\n      \"reviewLevel\": \"educational\"\n    }\n  }\n}\n```\n\n#### CLI Configuration\n```bash\n# Set configuration\nclaude-flow pair config set defaultMode switch\nclaude-flow pair config set verification.threshold 0.98\n\n# Get configuration\nclaude-flow pair config get\nclaude-flow pair config get defaultMode\n\n# Export\u002FImport\nclaude-flow pair config export > config.json\nclaude-flow pair config import config.json\n\n# Reset\nclaude-flow pair config reset\n```\n\n#### Profile Management\n\nCreate reusable profiles:\n\n```bash\n# Create profile\nclaude-flow pair profile create refactoring \\\n  --mode driver \\\n  --verify true \\\n  --threshold 0.98 \\\n  --focus refactor\n\n# Use profile\nclaude-flow pair --start --profile refactoring\n\n# List profiles\nclaude-flow pair profile list\n```\n\nProfile configuration:\n```json\n{\n  \"profiles\": {\n    \"refactoring\": {\n      \"mode\": \"driver\",\n      \"verification\": {\n        \"enabled\": true,\n        \"threshold\": 0.98\n      },\n      \"focus\": \"refactor\"\n    },\n    \"debugging\": {\n      \"mode\": \"navigator\",\n      \"agent\": \"debugger-expert\",\n      \"trace\": true,\n      \"verbose\": true\n    },\n    \"learning\": {\n      \"mode\": \"mentor\",\n      \"pace\": \"slow\",\n      \"explanations\": \"detailed\",\n      \"examples\": true\n    }\n  }\n}\n```\n\n### Real-World Examples\n\n#### Example 1: Feature Implementation\n\nImplementing user authentication with JWT tokens:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode switch \\\n  --agent senior-dev \\\n  --focus implement \\\n  --verify \\\n  --test\n```\n\n**Session Flow:**\n```\n? Starting pair programming for authentication feature...\n\n[DRIVER: You - 10 minutes]\n\u002Fexplain JWT authentication flow\n> AI explains JWT concepts and best practices\n\n\u002Fsuggest implementation approach\n> AI suggests using middleware pattern with refresh tokens\n\n# You write the basic auth middleware structure\n\n[SWITCH TO NAVIGATOR]\n\n[NAVIGATOR: AI - 10 minutes]\n\u002Fimplement JWT token generation with refresh tokens\n> AI generates secure token implementation\n\n\u002Ftest-gen\n> AI creates comprehensive test suite\n\n[SWITCH TO DRIVER]\n\n[DRIVER: You - 10 minutes]\n# You refine the implementation\n\u002Freview --security\n> AI performs security review, suggests improvements\n\n\u002Fcommit --message \"feat: JWT authentication with refresh tokens\"\n✅ Truth Score: 0.98 - Committed successfully\n```\n\n#### Example 2: Bug Fixing\n\nDebugging a memory leak in Node.js:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode navigator \\\n  --agent debugger-expert \\\n  --focus debug \\\n  --trace\n```\n\n**Session Flow:**\n```\n? Starting debugging session...\n\n\u002Fstatus\n> Analyzing application for memory issues...\n\n\u002Fperf --profile\n> Memory usage growing: 150MB → 450MB over 10 minutes\n\n\u002Ffind \"new EventEmitter\" --regex\n> Found 3 instances of EventEmitter creation\n\n\u002Finspect eventEmitters --deep\n> Discovering listeners not being removed\n\n\u002Fsuggest fix for memory leak\n> AI suggests: \"Add removeListener in cleanup functions\"\n\n\u002Fimplement cleanup functions for all event emitters\n> AI generates proper cleanup code\n\n\u002Ftest\n> Memory stable at 150MB ✅\n\n\u002Fcommit --message \"fix: memory leak in event emitters\"\n```\n\n#### Example 3: TDD Session\n\nBuilding shopping cart with test-driven development:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode tdd \\\n  --agent tdd-specialist \\\n  --test-first\n```\n\n**Session Flow:**\n```\n? TDD Session: Shopping Cart Feature\n\n[RED PHASE]\n\u002Ftest-gen \"add item to cart\"\n> AI writes failing test:\n  ✗ should add item to cart\n  ✗ should update quantity for existing item\n  ✗ should calculate total price\n\n[GREEN PHASE]\n\u002Fimplement minimal cart functionality\n> You write just enough code to pass tests\n\n\u002Ftest\n> Tests passing: 3\u002F3 ✅\n\n[REFACTOR PHASE]\n\u002Frefactor --pattern repository\n> AI refactors to repository pattern\n\n\u002Ftest\n> Tests still passing: 3\u002F3 ✅\n\n[NEXT CYCLE]\n\u002Ftest-gen \"remove item from cart\"\n> AI writes new failing tests...\n```\n\n#### Example 4: Code Refactoring\n\nModernizing legacy code:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode driver \\\n  --focus refactor \\\n  --verify \\\n  --threshold 0.98\n```\n\n**Session Flow:**\n```\n? Refactoring Session: Modernizing UserService\n\n\u002Fanalyze UserService.js\n> AI identifies:\n  - Callback hell (5 levels deep)\n  - No error handling\n  - Tight coupling\n  - No tests\n\n\u002Fsuggest refactoring plan\n> AI suggests:\n  1. Convert callbacks to async\u002Fawait\n  2. Add error boundaries\n  3. Extract dependencies\n  4. Add unit tests\n\n\u002Ftest-gen --before-refactor\n> AI generates tests for current behavior\n\n\u002Frefactor callbacks to async\u002Fawait\n# You refactor with AI guidance\n\n\u002Ftest\n> All tests passing ✅\n\n\u002Freview --compare\n> AI shows before\u002Fafter comparison\n> Code complexity: 35 → 12\n> Truth score: 0.99 ✅\n\n\u002Fcommit --message \"refactor: modernize UserService with async\u002Fawait\"\n```\n\n#### Example 5: Performance Optimization\n\nOptimizing slow React application:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode switch \\\n  --agent performance-expert \\\n  --focus optimize \\\n  --profile\n```\n\n**Session Flow:**\n```\n? Performance Optimization Session\n\n\u002Fperf --profile\n> React DevTools Profiler Results:\n  - ProductList: 450ms render\n  - CartSummary: 200ms render\n  - Unnecessary re-renders: 15\n\n\u002Fsuggest optimizations for ProductList\n> AI suggests:\n  1. Add React.memo\n  2. Use useMemo for expensive calculations\n  3. Implement virtualization for long lists\n\n\u002Fimplement React.memo and useMemo\n# You implement with AI guidance\n\n\u002Fperf --profile\n> ProductList: 45ms render (90% improvement!) ✅\n\n\u002Fimplement virtualization with react-window\n> AI implements virtual scrolling\n\n\u002Fperf --profile\n> ProductList: 12ms render (97% improvement!) ✅\n> FPS: 60 stable ✅\n\n\u002Fcommit --message \"perf: optimize ProductList with memoization and virtualization\"\n```\n\n#### Example 6: API Development\n\nBuilding RESTful API with Express:\n\n```bash\n# Session setup\nclaude-flow pair --start \\\n  --mode navigator \\\n  --agent backend-expert \\\n  --focus implement \\\n  --test\n```\n\n**Session Flow:**\n```\n? API Development Session\n\n\u002Fdesign REST API for blog platform\n> AI designs endpoints:\n  POST   \u002Fapi\u002Fposts\n  GET    \u002Fapi\u002Fposts\n  GET    \u002Fapi\u002Fposts\u002F:id\n  PUT    \u002Fapi\u002Fposts\u002F:id\n  DELETE \u002Fapi\u002Fposts\u002F:id\n\n\u002Fimplement CRUD endpoints with validation\n> AI implements with Express + Joi validation\n\n\u002Ftest-gen --integration\n> AI generates integration tests\n\n\u002Fsecurity --api\n> AI adds:\n  - Rate limiting\n  - Input sanitization\n  - JWT authentication\n  - CORS configuration\n\n\u002Fdocument --openapi\n> AI generates OpenAPI documentation\n\n\u002Ftest --integration\n> All endpoints tested: 15\u002F15 ✅\n```\n\n### Session Templates\n\n#### Quick Start Templates\n\n```bash\n# Refactoring template\nclaude-flow pair --template refactor\n# Focus: Code improvement\n# Verification: High (0.98)\n# Testing: After each change\n# Review: Continuous\n\n# Feature template\nclaude-flow pair --template feature\n# Focus: Implementation\n# Verification: Standard (0.95)\n# Testing: On completion\n# Review: Pre-commit\n\n# Debug template\nclaude-flow pair --template debug\n# Focus: Problem solving\n# Verification: Moderate (0.90)\n# Testing: Regression tests\n# Review: Root cause\n\n# Learning template\nclaude-flow pair --template learn\n# Mode: Mentor\n# Pace: Slow\n# Explanations: Detailed\n# Examples: Many\n```\n\n### Session Management\n\n#### Session Status\n\n```bash\nclaude-flow pair --status\n```\n\n**Output:**\n```\n? Pair Programming Session\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nSession ID: pair_1755021234567\nDuration: 45 minutes\nStatus: Active\n\nPartner: senior-dev\nCurrent Role: DRIVER (you)\nMode: Switch (10m intervals)\nNext Switch: in 3 minutes\n\n? Metrics:\n├── Truth Score: 0.982 ✅\n├── Lines Changed: 234\n├── Files Modified: 5\n├── Tests Added: 12\n├── Coverage: 87% ↑3%\n└── Commits: 3\n\n? Focus: Implementation\n? Current File: src\u002Fauth\u002Flogin.js\n```\n\n#### Session History\n\n```bash\nclaude-flow pair --history\n```\n\n**Output:**\n```\n? Session History\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n1. 2024-01-15 14:30 - 16:45 (2h 15m)\n   Partner: expert-coder\n   Focus: Refactoring\n   Truth Score: 0.975\n   Changes: +340 -125 lines\n\n2. 2024-01-14 10:00 - 11:30 (1h 30m)\n   Partner: tdd-specialist\n   Focus: Testing\n   Truth Score: 0.991\n   Tests Added: 24\n\n3. 2024-01-13 15:00 - 17:00 (2h)\n   Partner: debugger-expert\n   Focus: Bug Fixing\n   Truth Score: 0.968\n   Issues Fixed: 5\n```\n\n#### Session Persistence\n\n```bash\n# Save session\nclaude-flow pair --save [--name \u003Cname>]\n\n# Load session\nclaude-flow pair --load \u003Csession-id>\n\n# Export session\nclaude-flow pair --export \u003Csession-id> [--format json|md]\n\n# Generate report\nclaude-flow pair --report \u003Csession-id>\n```\n\n#### Background Sessions\n\n```bash\n# Start in background\nclaude-flow pair --start --background\n\n# Monitor background session\nclaude-flow pair --monitor\n\n# Attach to background session\nclaude-flow pair --attach \u003Csession-id>\n\n# End background session\nclaude-flow pair --end \u003Csession-id>\n```\n\n### Advanced Features\n\n#### Custom Commands\n\nDefine in configuration:\n\n```json\n{\n  \"customCommands\": {\n    \"tdd\": \"\u002Ftest-gen && \u002Ftest --watch\",\n    \"full-review\": \"\u002Flint --fix && \u002Ftest && \u002Freview --strict\",\n    \"quick-fix\": \"\u002Fsuggest --type fix && \u002Fimplement && \u002Ftest\"\n  }\n}\n```\n\nUse custom commands:\n```\n\u002Fcustom tdd\n\u002Fcustom full-review\n```\n\n#### Command Chaining\n\n```\n\u002Ftest && \u002Fcommit && \u002Fpush\n\u002Flint --fix && \u002Ftest && \u002Freview --strict\n```\n\n#### Session Recording\n\n```bash\n# Start with recording\nclaude-flow pair --start --record\n\n# Replay session\nclaude-flow pair --replay \u003Csession-id>\n\n# Session analytics\nclaude-flow pair --analytics \u003Csession-id>\n```\n\n#### Integration Options\n\n**With Git:**\n```bash\nclaude-flow pair --start --git --auto-commit\n```\n\n**With CI\u002FCD:**\n```bash\nclaude-flow pair --start --ci --non-interactive\n```\n\n**With IDE:**\n```bash\nclaude-flow pair --start --ide vscode\n```\n\n### Best Practices\n\n#### Session Practices\n1. **Clear Goals** - Define session objectives upfront\n2. **Appropriate Mode** - Choose based on task type\n3. **Enable Verification** - For critical code paths\n4. **Regular Testing** - Maintain quality continuously\n5. **Session Notes** - Document important decisions\n6. **Regular Breaks** - Take breaks every 45-60 minutes\n\n#### Code Practices\n1. **Test Early** - Run tests after each change\n2. **Verify Before Commit** - Check truth scores\n3. **Review Security** - Always for sensitive code\n4. **Profile Performance** - Use `\u002Fperf` for optimization\n5. **Save Sessions** - For complex work\n6. **Learn from AI** - Ask questions frequently\n\n#### Mode Selection\n- **Driver Mode**: When learning, controlling implementation\n- **Navigator Mode**: For rapid prototyping, generation\n- **Switch Mode**: Long sessions, balanced collaboration\n- **TDD Mode**: Building with tests\n- **Review Mode**: Quality focus\n- **Mentor Mode**: Learning priority\n- **Debug Mode**: Fixing issues\n\n### Troubleshooting\n\n#### Session Won't Start\n- Check agent availability\n- Verify configuration file syntax\n- Ensure clean workspace\n- Review log files\n\n#### Session Disconnected\n- Use `--recover` to restore\n- Check network connection\n- Verify background processes\n- Review auto-save files\n\n#### Poor Performance\n- Reduce verification threshold\n- Disable continuous testing\n- Check system resources\n- Use lighter AI model\n\n#### Configuration Issues\n- Validate JSON syntax\n- Check file permissions\n- Review priority order (CLI > env > project > user > global)\n- Run `claude-flow pair config validate`\n\n### Quality Metrics\n\n#### Truth Score Thresholds\n```\nError:   \u003C 0.90 ❌\nWarning: 0.90 - 0.95 ⚠️\nGood:    0.95 - 0.98 ✅\nExcellent: > 0.98 ?\n```\n\n#### Coverage Thresholds\n```\nError:   \u003C 70% ❌\nWarning: 70% - 80% ⚠️\nGood:    80% - 90% ✅\nExcellent: > 90% ?\n```\n\n#### Complexity Thresholds\n```\nError:   > 15 ❌\nWarning: 10 - 15 ⚠️\nGood:    5 - 10 ✅\nExcellent: \u003C 5 ?\n```\n\n### Environment Variables\n\nOverride configuration via environment:\n\n```bash\nexport CLAUDE_PAIR_MODE=driver\nexport CLAUDE_PAIR_VERIFY=true\nexport CLAUDE_PAIR_THRESHOLD=0.98\nexport CLAUDE_PAIR_AGENT=senior-dev\nexport CLAUDE_PAIR_AUTO_TEST=true\n```\n\n### Command History\n\nNavigate history:\n- `↑\u002F↓` - Navigate through command history\n- `Ctrl+R` - Search command history\n- `!!` - Repeat last command\n- `!\u003Cn>` - Run command n from history\n\n### Keyboard Shortcuts (Configurable)\n\nDefault shortcuts:\n```json\n{\n  \"shortcuts\": {\n    \"switch\": \"ctrl+shift+s\",\n    \"suggest\": \"ctrl+space\",\n    \"review\": \"ctrl+r\",\n    \"test\": \"ctrl+t\"\n  }\n}\n```\n\n### Related Commands\n\n- `claude-flow pair --help` - Show help\n- `claude-flow pair config` - Manage configuration\n- `claude-flow pair profile` - Manage profiles\n- `claude-flow pair templates` - List templates\n- `claude-flow pair agents` - List available agents\n",{"name":5,"description":7},"main","90d379e95fcc23dd9759654c345424e1752b0f3a","pocs\u002Fclaude-flow-fun\u002F.claude\u002Fskills\u002Fpair-programming",9,"https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground","https:\u002F\u002Fgithub.com\u002Fdiegopacheco","http:\u002F\u002Fdiego-pacheco.blogspot.com","Brazilian Hands-on Software Architect | 20+ years in Tech | Author | Father. Opinions are my own!","2026-11-13 23:52:43",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add diegopacheco\u002Fai-playground --skill \"Pair Programming\"",{"tool":69,"command":70},"bunx","bunx skills add diegopacheco\u002Fai-playground --skill \"Pair Programming\"",{"tool":72,"command":73},"pnpm","pnpm dlx skills add diegopacheco\u002Fai-playground --skill \"Pair Programming\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fclaude-flow-fun\u002F.claude\u002Fskills\u002Fpair-programming\u002FSKILL.md",true,[],[78,94,104,117,133,152],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":87,"publishedAt":49},"01M6WJ537DN520XY8MSW9ZV0RP","word-count","Counts the words, lines and characters of a text or a file.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Ftext-skills\u002Fword-count\u002FSKILL.md",[84],{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",[88,89,90,91,92,93],"count","word count","Word","characters","text","file",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":49},"01M6WJ4Y2GT5SECWAKKYHGES4F","slugify","Turns a title or a sentence into a URL slug, lowercase words joined by hyphens with accents removed.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Ftext-skills\u002Fslugify\u002FSKILL.md",[],[96,101,102,103],"title","with","URL",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":49},"01M6WJ4V9CWHT9NVCD441VK5MH","json-format","Validates a JSON file and pretty prints it with two space indentation, or reports where the JSON is invalid.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Fdev-skills\u002Fjson-format\u002FSKILL.md",[],[111,112,113,93,114,115,116,102],"json","format","json format","reports","invalid","it",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":49},"01M6WJ4QMRKW8EFP71F4KS2DHE","commit-message","Writes a conventional commit message for the staged git changes.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Fdev-skills\u002Fcommit-message\u002FSKILL.md",[],[124,125,126,127,128,129,130,131,132],"commit","commit message","message","git","conventional commit","for","changes","staged","conventional commit message",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":49},"01M6WJ4MAM2CJH0GWYXFBB9GQC","skills-gateway","Gateway and router to a catalog of skills that are not registered directly. Use it before any task a specialized skill could handle, such as text, JSON or git chores. It finds the right skill and loads its instructions.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002F.claude\u002Fskills\u002Fskills-gateway\u002FSKILL.md",[],[140,141,116,142,143,127,144,111,92,145,146,147,148,149,150,151],"skills gateway","gateway","task","loads","Bash","node","specialized","instructions","catalog","use","router","as",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":49},"01M6M2PYJJQKMWGX7XT7ZJK0H3","decision-log","Record, list, show and supersede architecture decisions that persist across sessions in the shared agent infra state store. Use when the user says \"record this decision\", \"log an ADR\", \"what did we decide about\", \"list decisions\", or \"supersede decision\".","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fagent-skills-infra-poc\u002Fskills\u002Fdecision-log\u002FSKILL.md",[],[159,160,161,162,163,164,165,166,167,168,149,169,170,171,172,173,174,175,176,43],"decision log","log","decision","persist","architecture","state","adr","decide","decisions","list","show","infra","record","across","shared","store","about","supersede"]