pair-programming
/pair-programming
AI-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 scanning, and performance optimization with truth-score verification. Use when pairing on code with driver/navigator roles, doing TDD, or wanting real-time review while building.
- Author
- frankxai ↗
- Repository
- claude-skills-library ↗
- Licence
- MIT
- Last repository change
- 26.10.2026
Assessment and security
- Files in this package
- 3
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
AI-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 scanning, and performance optimization with truth-score verification. Use when pairing on code with driver/navigator roles, doing TDD, or wanting real-time review while building.
Original author description
AI-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 scanning, and performance optimization with truth-score verification. Use when pairing on code with driver/navigator roles, doing TDD, or wanting real-time review while building.
How it works
- What This Skill Does
- Prerequisites
- Quick Start
- Reference
- Operations reference
SKILL.md preview
---
name: pair-programming
description: AI-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 scanning, and performance optimization with truth-score verification. Use when pairing on code with driver/navigator roles, doing TDD, or wanting real-time review while building.
---
# Pair Programming
Collaborative AI pair programming with intelligent role management, real-time quality monitoring, and comprehensive development workflows.
## What This Skill Does
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.
**Key Capabilities:**
- **Multiple Modes**: Driver, Navigator, Switch, TDD, Review, Mentor, Debug
- **Real-Time Verification**: Automatic quality scoring with rollback on failures
- **Role Management**: Seamless switching between driver/navigator roles
- **Testing Integration**: Auto-generate tests, track coverage, continuous testing
- **Code Review**: Security scanning, performance analysis, best practice enforcement
- **Session Persistence**: Auto-save, recovery, export, and sharing
## Prerequisites
**Required:**
- Claude Flow CLI installed (`npm install -g claude-flow@alpha`)
- Git repository (optional but recommended)
**Recommended:**
- Testing framework (Jest, pytest, etc.)
- Linter configured (ESLint, pylint, etc.)
- Code formatter (Prettier, Black, etc.)
## Quick Start
### Basic Session
```bash
# Start simple pair programming
claude-flow pair --start
```
### TDD Session
```bash
# Test-driven development
claude-flow pair --start \
--mode tdd \
--test-first \
--coverage 90
```
---
## Reference
The full detail lives in `references/` and loads only when needed:
- [`references/usage.md`](references/usage.md) — session control, modes, in-session commands & configuration.
- [`references/examples.md`](references/examples.md) — real-world examples, templates, session management & advanced features.
---
## Operations reference
### Best Practices
#### Session Practices
1. **Clear Goals** - Define session objectives upfront
2. **Appropriate Mode** - Choose based on task type
3. **Enable Verification** - For critical code paths
4. **Regular Testing** - Maintain quality continuously
5. **Session Notes** - Document important decisions
6. **Regular Breaks** - Take breaks every 45-60 minutes
#### Code Practices
1. **Test Early** - Run tests after each change
2. **Verify Before Commit** - Check truth scores
3. **Review Security** - Always for sensitive code
4. **Profile Performance** - Use `/perf` for optimization
5. **Save Sessions** - For complex work
6. **Learn from AI** - Ask questions frequently
#### Mode Selection
- **Driver Mode**: When learning, controlling implementation
- **Navigator Mode**: For rapid prototyping, generation
- **Switch Mode**: Long sessions, balanced collaboration
- **TDD Mode**: Building with tests
- **Review Mode**: Quality focus
- **Mentor Mode**: Learning priority
- **Debug Mode**: Fixing issues
### Troubleshooting
#### Session Won't Start
- Check agent availability
- Verify configuration file syntax
- Ensure clean workspace
- Review log files
#### Session Disconnected
- Use `--recover` to restore
- Check network connection
- Verify background processes
- Review auto-save files
#### Poor Performance
- Reduce verification threshold
- Disable continuous testing
- Check system resources
- Use lighter AI model
#### Configuration Issues
- Validate JSON syntax
- Check file permissions
- Review priority order (CLI > env > project > user > global)
- Run `claude-flow pair config validate`
### Quality Metrics
#### Truth Score Thresholds
```
Error: < 0.90 ❌
Warning: 0.90 - 0.95 ⚠️
Good: 0.95 - 0.98 ✅
Excellent: > 0.98 🌟
```
#### Coverage Thresholds
```
Error: < 70% ❌
Warning: 70% - 80% ⚠️
Good: 80% - 90% ✅
Excellent: > 90% 🌟
```
#### Complexity Thresholds
```
Error: > 15 ❌
Warning: 10 - 15 ⚠️
Good: 5 - 10 ✅
Excellent: < 5 🌟
```
### Environment Variables
Override configuration via environment:
```bash
export CLAUDE_PAIR_MODE=driver
export CLAUDE_PAIR_VERIFY=true
export CLAUDE_PAIR_THRESHOLD=0.98
export CLAUDE_PAIR_AGENT=senior-dev
export CLAUDE_PAIR_AUTO_TEST=true
```
### Command History
Navigate history:
- `↑/↓` - Navigate through command history
- `Ctrl+R` - Search command history
- `!!` - Repeat last command
- `!<n>` - Run command n from history
### Keyboard Shortcuts (Configurable)
Default shortcuts:
```json
{
"shortcuts": {
"switch": "ctrl+shift+s",
"suggest": "ctrl+space",
"review": "ctrl+r",
"test": "ctrl+t"
}
}
```
### Related Commands
- `claude-flow pair --help` - Show help
- `claude-flow pair config` - Manage configuration
- `claude-flow pair profile` - Manage profiles
- `claude-flow pair templates` - List templates
- `claude-flow pair agents` - List available agents
Files in this package (3)
- SKILL.md 5 KB
- references/examples.md 9 KB
- references/usage.md 11 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · frankxai/claude-skills-library | 100 | MIT |
| flurdy/agent-skills | 95 | MIT |
| staruhub/claudeskills | 95 | MIT |
| ctoforaday/special-circumstances | 86 | MIT |
Database snapshot: 13.11.2026 · package version 3f72c0375497 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90rseng-pair-programming
Covers the agent as an effective pair programmer and pull-request review buddy for research software: driver-navigator collaboration with think-aloud reasoning, ping-pong test-driven pairing, keeping the human in charge of scientific decisions, pre-review of pull requests before… - 100technical-mentoring-pair-programming-craft
Use this skill when mentor junior engineers effectively using collaborative pair programming and guided discovery. - 100superpowers-zh
Use when constraining AI coding with Chinese TDD methodology, systematic debugging, code review, and verification workflows. Superpowers-zh: Chinese adaptation of the Superpowers AI-assisted programming skills and methodologies. - 90programming
USE FOR: Programming/debugging: Bash, Python/Jupyter quality, Nix package workflow, Terraform with Checkov, Markdown, TDD/Tidy First, and root-cause isolation. DO NOT USE FOR: agent harness, data-platform, diagramming, or GitHub workflow work. - 100build-with-quality
Implement features with tests and quality gates, debug hard bugs, and stress-test designs. Use when building a feature with TDD/EDD, chasing a stubborn multi-function bug (feedback-loop-first), interrogating a design before coding, or running a coverage/security/accessibility… - 96tdd-workflows-tdd-cycle
Use when working with tdd workflows tdd cycle