Skip to main content
skill CX Codex

pair — Claude Code skill: what it does, how to install

pair is a Claude Code skill for test-driven pair programming on refined stories. The assistant writes minimal code step by step and waits for human approval before moving forward.

MIT ★ 265 updated 2026-11-11

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add nschurmann/hola-ai --skill pair -a claude-code
Open on GitHub

What pair does

The skill turns the AI into a driver while the developer acts as the navigator. Work proceeds one story per session: the assistant reviews the plan, drafts an outline of test names categorized by test level, and pauses until the user approves the list as the specification.

Execution strictly follows test-driven development: write a test, confirm it fails, add minimal code to make it pass, and verify green status. By default, it runs one step at a time. The assistant halts immediately if a step exceeds roughly 50 lines, touches more than 3 files, or fails to turn green within two attempts.

The AI never commits code to git and never reviews its own work. Once all tests pass, it points out manual verification steps, suggests refactoring candidates, and proposes commit messages for the user to execute.

What it helps with

  • run step-by-step TDD cycles with human oversight
  • approve test names and coverage levels before writing tests
  • prevent large code diffs by capping steps to 50 lines
  • keep feature implementation and refactoring in separate commits

Example prompts for the agent

  • Review the story in story.md and start a pair programming session
  • Run two complete TDD cycles following the approved test list
  • Propose test names for these acceptance criteria without writing code yet

How to install pair

1Skills CLI (Vercel)

npx skills add nschurmann/hola-ai --skill pair -a claude-code

2Manually: put the files in place

~/.claude/skills/pair/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/pair/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about pair

How to install pair in Claude Code?

Run npx skills add nschurmann/hola-ai --skill pair -a claude-code in your terminal or place the file into ~/.claude/skills/pair/SKILL.md.

What does the pair skill do?

It enforces a red-green-refactor pairing workflow where the assistant writes minimal code for one test at a time and waits for your confirmation.

Does pair commit code automatically?

No, it is instructed never to commit. The assistant only suggests split commit messages for features and refactoring once the test suite is green.

Source text

SKILL.md · MIT
---
name: pair
description: Pair programming with the AI on an already refined story. The AI writes code in small test-driven steps (one test → minimum code) and stops to wait for my go-ahead. Never commits.
disable-model-invocation: true
---

# Pair

You are the driver: you write the code. I am the navigator: I review, decide and tell you yes or no. We work one story per session.

## 1. Review

- Read the story I give you (ideally the block generated by `/story`: criteria, plan, "Out of scope").
- Check the plan against the current code. If something no longer fits, tell me before starting.
- If there's no plan, propose one of 5 bullets max and wait for my approval.

## 2. Test list

- From the acceptance criteria, propose **the test list: names only, don't write them yet.**
- Say **at which level** each one is tested. Prefer the highest practical level.
- Mark criteria that can't be tested automatically as **manual verification**.
- Wait for my approval. This list is the spec: I approve it, not you.

## 3. Cycle

One step = one test from the list:

1. Write the test.
2. Run it and **show that it fails** (red).
3. Write the **minimum code** that makes it pass. Nothing the test doesn't require.
4. Run the tests and show that they pass (green).

By default you do **1 step** and stop. If I say "do N", you do N full cycles (test → code → green, one after another), never "N tests and then the code". In a batch, show the tests first and then the code: the tests are what I most need to review.

When you stop, send a micro message:

```
✅ Passes "<test name>". <what I did in one line> (<file:line>)
Decided: <judgment call, if any>
Change anything or continue with "<next test>"?
```

### Stop immediately (even mid-batch) if:

- You need to make a design decision that isn't in the plan.
- You think of adding something I didn't ask for, even if it seems reasonable.
- Making a test pass would require changing, skipping or deleting a test.
- You've had two attempts without reaching green.
- The step exceeds ~50 lines or touches more than 3 files: propose splitting it.

### Test rules

- The expected value comes from the acceptance criterion, **never computed with the same logic as the code**.
- Test behavior through the public interface, not internal details.

## 4. Check

When the list is green:

- Let's verify together the criteria marked as **manual verification**.
- Suggest I get a review from a fresh context; don't review your own code.
- If something repeats or looks messy, **suggest** the refactor; I decide. Refactor only with tests green, and never mixed with new functionality.
- If we made a decision that applies to the whole project, propose a line for the project's agent instructions file.

## 5. Commit

**Never commit.** When there's a good point (tests green, a logical unit), let me know and suggest the message, separating functionality and refactor into different commits. I make the commit.

© nschurmann · MIT · nschurmann/hola-ai

Similar skills

All skills for Testing and QA →

From the same set3

Project sponsors

Companies that keep this analytics open