skills.rest
wandreandrade2018-maker
wandreandrade2018-makerCOMMUNITY
Explore all skills by this author →
GitHub

Pair Programming

Runs AI-assisted pair programming sessions with role switching, verification, and testing.

Updated Aug 18, 2026
Search Tags:#testing#tdd#code review#refactoring#verification#pair programming#claude-flow
One-click install
npx skills add https://github.com/wandreandrade2018-maker/claude-config --skill pair-programming-wandreandrade2018-maker
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Pair Programming
Source: https://github.com/wandreandrade2018-maker/claude-config/tree/main/.claude/skills/pair-programming
Command: npx skills add https://github.com/wandreandrade2018-maker/claude-config --skill pair-programming-wandreandrade2018-maker

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires claude-flow.

What problem does it solve? Collaborative coding sessions often lack structure, consistent code review, and enforced quality gates, leading to untested changes and missed defects. This Skill orchestrates structured pair programming sessions with an AI partner, managing driver/navigator roles, continuous verification, and integrated testing. ## Core Features & Use Cases - Multiple Collaboration Modes: Driver, Navigator, Switch, TDD, Review, Mentor, and Debug modes with automatic role switching at configurable intervals. - Real-Time Verification: Truth-score quality gates with automatic rollback, pre-commit checks, and configurable thresholds. - Testing and Review Integration: Test generation, coverage tracking, security scanning, performance profiling, and linting during the session. - Use Case: A developer fixing a memory leak starts a debug session with the debugger-expert agent, profiles memory usage, receives a fix suggestion, implements cleanup code, and commits only after tests pass and the truth score exceeds the threshold. ## Quick Start Start a pair programming session in TDD mode with test-first enabled and a 90 percent coverage target.

Frequently Asked Questions about Pair Programming

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I start a pair programming session with claude-flow?▼

Run claude-flow pair --start to begin a basic session. Add flags like --mode tdd, --agent senior-dev, or --verify to customize the mode, AI partner, and verification behavior.

What pair programming modes does claude-flow support?▼

It supports driver, navigator, switch, TDD, review, mentor, and debug modes. Switch mode alternates roles automatically at configurable intervals such as 5, 10, or 15 minutes.

How does truth-score verification work in pair sessions?▼

Verification assigns a quality score to changes and can block or roll back commits below a configurable threshold, such as 0.95. Scores above 0.98 are rated excellent, while scores below 0.90 are treated as errors.

Can I enforce test coverage during a TDD session?▼

Yes. Start with --mode tdd --test-first --coverage 90 to write failing tests first and enforce a minimum coverage target. Coverage below 70 percent is flagged as an error in the quality metrics.

Why won't my pair programming session start?▼

Check that the claude-flow CLI is installed, the agent is available, and the .claude-flow/pair-config.json file has valid JSON syntax. Also confirm the workspace is clean and review the log files for errors.

Can I save and resume a pair programming session?▼

Yes. Sessions support auto-save at configurable intervals, manual saving with --save, recovery after disconnection, and export or report generation for completed sessions.

Related Skills

Explore More Software Engineering Skills→
MaelwalserMaelwalser

plankton-code-quality

Run formatters and linters on every file edit with Claude subprocess remediation.

Community
Advanced
SSiertsemaSSiertsema

quality-gate-definition

Define and enforce quality gates across CI/CD pipeline stages.

Community
Advanced
lxh755818-botlxh755818-bot

requesting-code-review

Automate pre-commit code review with security scans, linting, and testing.

Community
Advanced
amadeus-dlcamadeus-dlc
5

amadeus-nfr-design

Execute the AI-DLC nfr-design stage in isolation without advancing the main workflow.

Official
Intermediate