Skip to content
Skills Library
Programming · Building & coding

pair-programming

/pair-programming

Use when working interactively with the human on code — driver/navigator roles, ping-pong test-driven development, adversarial review, and hold-on-submit.

Licence
MIT
Last repository change
27.10.2026

Assessment and security

86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content21 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when working interactively with the human on code — driver/navigator roles, ping-pong test-driven development, adversarial review, and hold-on-submit.

Original author description

Use when working interactively with the human on code — driver/navigator roles, ping-pong test-driven development, adversarial review, and hold-on-submit.

How it works

SKILL.md has no level-two headings · 14 lines, 244 words

SKILL.md preview
---
name: pair-programming
description: Use when working interactively with the human on code — driver/navigator roles, ping-pong test-driven development, adversarial review, and hold-on-submit.
disable-slash-command: true
user-invocable: false
---

# pair-programming

Partner and adversary at once.

- During pairing, you are usually the **Driver** (writing code, running commands) and the human the **Navigator** (steering design, catching edge cases). YOU MUST drive autonomously while the path is clear; YOU MUST yield the driver role when the human requests it; and when a decision would genuinely benefit from the human at the controls (taste, domain knowledge, ambiguous intent), YOU MUST offer it rather than push through.
- BEFORE generating a large body of code, YOU MUST propose the plan or architecture and align on it (see [[plan-act-reflect]]).
- During discussion, YOU MUST ask questions one at a time and wait for the answer; offer options where actionable. Prefer "how would you approach this?" over presenting a completed decision.
- As adversary, YOU MUST red-team the plan — edge cases, hidden assumptions, pushback on risk (see [[critical-stance]]). As partner, YOU MUST stay aligned on the goal while doing it.
- During test-driven development, YOU MUST follow [[test-driven-development]] — including the ping-pong variant when pairing.
- During pairing, the human may edit files concurrently; BEFORE acting on remembered file state that may have changed, YOU MUST re-read the file.
- AFTER tests pass, YOU MUST hold the change unsubmitted; YOU MUST NOT commit, push, or land until both partners explicitly agree it meets the bar (see [[semantic-consent]]).
- AFTER completing a task, YOU MUST propose the next step from the context you hold rather than waiting passively.

Versions

RepositoryScoreLicence
This page · ctoforaday/special-circumstances86MIT
frankxai/claude-skills-library100MIT
flurdy/agent-skills95MIT
staruhub/claudeskills95MIT

Database snapshot: 13.11.2026 · package version b9cb4214567d (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…
  • 86test-driven-development
    Use when building or changing behaviour that can be tested — red/green/refactor discipline, test-first contracts, and the ping-pong variant for pairing.
  • 100websockets
    Expert WebSockets assistance covering bidirectional full-duplex TCP connections, handshake upgrading, heartbeats/ping-pong, connection state management, and horizontal scaling with Redis Pub/Sub. Use when developing chat applications, live collaboration tools, or multiplayer games.
  • 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.
  • 100test-driven
    Test-Driven Development (TDD) across any supported language. Use when implementing features or fixes with TDD methodology, writing tests before code, or following XP-style development.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.