pair-programming
starsforks
How to install pair-programming?
spencermarx/open-code-review/pair-programming
$npx -y skills add spencermarx/open-code-review --skill pair-programmingAI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scan
SKILL.md
| 1 | # Pair Programming |
| 2 | |
| 3 | Collaborative AI pair programming with intelligent role management, real-time quality monitoring, and comprehensive development workflows. |
| 4 | |
| 5 | ## What This Skill Does |
| 6 | |
| 7 | This skill provides professional pair programming capabilities with AI assistance, supporting multiple collaboration modes, continuous verification, and integrated testing. It manages driver/navigator roles, performs real-time code review, tracks quality metrics, and ensures high standards through truth-score verification. |
| 8 | |
| 9 | **Key Capabilities:** |
| 10 | - **Multiple Modes**: Driver, Navigator, Switch, TDD, Review, Mentor, Debug |
| 11 | - **Real-Time Verification**: Automatic quality scoring with rollback on failures |
| 12 | - **Role Management**: Seamless switching between driver/navigator roles |
| 13 | - **Testing Integration**: Auto-generate tests, track coverage, continuous testing |
| 14 | - **Code Review**: Security scanning, performance analysis, best practice enforcement |
| 15 | - **Session Persistence**: Auto-save, recovery, export, and sharing |
| 16 | |
| 17 | ## Prerequisites |
| 18 | |
| 19 | **Required:** |
| 20 | - Claude Flow CLI installed (`npm install -g claude-flow@alpha`) |
| 21 | - Git repository (optional but recommended) |
| 22 | |
| 23 | **Recommended:** |
| 24 | - Testing framework (Jest, pytest, etc.) |
| 25 | - Linter configured (ESLint, pylint, etc.) |
| 26 | - Code formatter (Prettier, Black, etc.) |
| 27 | |
| 28 | ## Quick Start |
| 29 | |
| 30 | ### Basic Session |
| 31 | ```bash |
| 32 | # Start simple pair programming |
| 33 | claude-flow pair --start |
| 34 | ``` |
| 35 | |
| 36 | ### TDD Session |
| 37 | ```bash |
| 38 | # Test-driven development |
| 39 | claude-flow pair --start \ |
| 40 | --mode tdd \ |
| 41 | --test-first \ |
| 42 | --coverage 90 |
| 43 | ``` |
| 44 | |
| 45 | --- |
| 46 | |
| 47 | ## Complete Guide |
| 48 | |
| 49 | ### Session Control Commands |
| 50 | |
| 51 | #### Starting Sessions |
| 52 | ```bash |
| 53 | # Basic start |
| 54 | claude-flow pair --start |
| 55 | |
| 56 | # Expert refactoring session |
| 57 | claude-flow pair --start \ |
| 58 | --agent senior-dev \ |
| 59 | --focus refactor \ |
| 60 | --verify \ |
| 61 | --threshold 0.98 |
| 62 | |
| 63 | # Debugging session |
| 64 | claude-flow pair --start \ |
| 65 | --agent debugger-expert \ |
| 66 | --focus debug \ |
| 67 | --review |
| 68 | |
| 69 | # Learning session |
| 70 | claude-flow pair --start \ |
| 71 | --mode mentor \ |
| 72 | --pace slow \ |
| 73 | --examples |
| 74 | ``` |
| 75 | |
| 76 | #### Session Management |
| 77 | ```bash |
| 78 | # Check status |
| 79 | claude-flow pair --status |
| 80 | |
| 81 | # View history |
| 82 | claude-flow pair --history |
| 83 | |
| 84 | # Pause session |
| 85 | /pause [--reason <reason>] |
| 86 | |
| 87 | # Resume session |
| 88 | /resume |
| 89 | |
| 90 | # End session |
| 91 | claude-flow pair --end [--save] [--report] |
| 92 | ``` |
| 93 | |
| 94 | ### Available Modes |
| 95 | |
| 96 | #### Driver Mode |
| 97 | You write code while AI provides guidance. |
| 98 | |
| 99 | ```bash |
| 100 | claude-flow pair --start --mode driver |
| 101 | ``` |
| 102 | |
| 103 | **Your Responsibilities:** |
| 104 | - Write actual code |
| 105 | - Implement solutions |
| 106 | - Make immediate decisions |
| 107 | - Handle syntax and structure |
| 108 | |
| 109 | **AI Navigator:** |
| 110 | - Strategic guidance |
| 111 | - Spot potential issues |
| 112 | - Suggest improvements |
| 113 | - Real-time review |
| 114 | - Track overall direction |
| 115 | |
| 116 | **Best For:** |
| 117 | - Learning new patterns |
| 118 | - Implementing familiar features |
| 119 | - Quick iterations |
| 120 | - Hands-on debugging |
| 121 | |
| 122 | **Commands:** |
| 123 | ``` |
| 124 | /suggest - Get implementation suggestions |
| 125 | /review - Request code review |
| 126 | /explain - Ask for explanations |
| 127 | /optimize - Request optimization ideas |
| 128 | /patterns - Get pattern recommendations |
| 129 | ``` |
| 130 | |
| 131 | #### Navigator Mode |
| 132 | AI writes code while you provide direction. |
| 133 | |
| 134 | ```bash |
| 135 | claude-flow pair --start --mode navigator |
| 136 | ``` |
| 137 | |
| 138 | **Your Responsibilities:** |
| 139 | - Provide high-level direction |
| 140 | - Review generated code |
| 141 | - Make architectural decisions |
| 142 | - Ensure business requirements |
| 143 | |
| 144 | **AI Driver:** |
| 145 | - Write implementation code |
| 146 | - Handle syntax details |
| 147 | - Implement your guidance |
| 148 | - Manage boilerplate |
| 149 | - Execute refactoring |
| 150 | |
| 151 | **Best For:** |
| 152 | - Rapid prototyping |
| 153 | - Boilerplate generation |
| 154 | - Learning from AI patterns |
| 155 | - Exploring solutions |
| 156 | |
| 157 | **Commands:** |
| 158 | ``` |
| 159 | /implement - Direct implementation |
| 160 | /refactor - Request refactoring |
| 161 | /test - Generate tests |
| 162 | /document - Add documentation |
| 163 | /alternate - See alternative approaches |
| 164 | ``` |
| 165 | |
| 166 | #### Switch Mode |
| 167 | Automatically alternates roles at intervals. |
| 168 | |
| 169 | ```bash |
| 170 | # Default 10-minute intervals |
| 171 | claude-flow pair --start --mode switch |
| 172 | |
| 173 | # 5-minute intervals (rapid) |
| 174 | claude-flow pair --start --mode switch --interval 5m |
| 175 | |
| 176 | # 15-minute intervals (deep focus) |
| 177 | claude-flow pair --start --mode switch --interval 15m |
| 178 | ``` |
| 179 | |
| 180 | **Handoff Process:** |
| 181 | 1. 30-second warning before switch |
| 182 | 2. Current driver completes thought |
| 183 | 3. Context summary generated |
| 184 | 4. Roles swap smoothly |
| 185 | 5. New driver continues |
| 186 | |
| 187 | **Best For:** |
| 188 | - Balanced collaboration |
| 189 | - Knowledge sharing |
| 190 | - Complex features |
| 191 | - Extended sessions |
| 192 | |
| 193 | #### Specialized Modes |
| 194 | |
| 195 | **TDD Mode** - Test-Driven Development: |
| 196 | ```bash |
| 197 | claude-flow pair --start \ |
| 198 | --mode tdd \ |
| 199 | --test-first \ |
| 200 | --coverage 100 |
| 201 | ``` |
| 202 | Workflow: Write failing test → Implement → Refactor → Repeat |
| 203 | |
| 204 | **Review Mode** - Continuous code review: |
| 205 | ```bash |
| 206 | claude-flow pair --start \ |
| 207 | --mode review \ |
| 208 | --strict \ |
| 209 | --security |
| 210 | ``` |
| 211 | Features: R |
People who liked this also viewed
6 picksType
- hyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, SkillsJul 2026
- request-refactor-planSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- analyze-projectRigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrSkillsMay 2026
- explore-codeRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated braSkillsMay 2026
- ubiquitous-languageSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- scaffold-exercisesSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
