Pair Programming

Coordinate AI pair programming with role switching, verification, and testing.

Updated Feb 24, 2026
One-click install
npx skills add https://github.com/FrekiManagarm/dunlo --skill pair-programming-frekimanagarm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Pair Programming
Source: https://github.com/FrekiManagarm/dunlo/tree/main/.claude/skills/pair-programming
Command: npx skills add https://github.com/FrekiManagarm/dunlo --skill pair-programming-frekimanagarm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill reduces the risk of writing incorrect, insecure, or under-tested code by coordinating an AI pair-programming workflow with continuous verification and structured collaboration.

Core Features & Use Cases

  • Multiple collaboration modes: Driver, Navigator, Switch, plus specialized TDD, Review, Mentor, and Debug workflows.
  • Real-time quality verification: Uses truth-score style verification with rollback behavior when results fail thresholds.
  • Testing and quality enforcement: Generates tests, tracks coverage, and continuously checks security, performance, linting, and complexity.
  • Role & session management: Automatically switches roles on a schedule, maintains session history, supports saving/exporting/recovery, and supports Git/CI-style integration.

Use Case Examples

  • Build a feature end-to-end: generate implementation, generate tests, run review/security checks, and commit with verification.
  • Fix a production bug: trace and analyze the issue, propose a root-cause fix, validate with tests, and review the change.
  • Refactor safely: apply refactor suggestions while maintaining behavioral coverage through continuous testing and strict quality gates.

Quick Start

Tell your AI partner to start a verified switch-mode pair session with continuous testing: "Start a claude-flow pair session in switch mode with verification enabled and require passing tests."

Frequently Asked Questions about Pair Programming

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

FAQPage Schema
How do I start an AI pair programming session with automated testing and code review?

AI pair programming coordinates driver and navigator roles to write, review, and verify code continuously. It applies role switching, real-time security checks, and automated test generation to ensure higher code quality during feature implementation or refactoring.

How does test-driven development workflow integrate with AI assisted coding?

Test-driven development integrates with AI assisted coding through a specialized TDD workflow that generates tests and tracks coverage. Truth-score style quality gating automatically rolls back changes when test results fail defined thresholds.

Can I use automated code review and security scanning during refactoring?

Yes, automated code review and security scanning run continuously during refactoring. The workflow applies refactor suggestions while maintaining behavioral coverage through continuous testing, linting, complexity checks, and strict quality gates.

What is the best way to debug production bugs with continuous code quality assurance?

The best way to debug production bugs with continuous code quality assurance is using a specialized debug workflow. It traces issues, proposes root-cause fixes, validates changes with generated tests, and enforces security checks before reviewing the commit.

Do I need to manually switch roles when doing feature implementation with an AI navigator?

No, role switching is automated during feature implementation. The session management automatically switches driver and navigator roles on a schedule, maintaining session history and supporting saving, exporting, and recovery throughout the workflow.