QA Real World — Testing skill for Claude Code
Run free-form agent-based QA against real-world public repos.
How to install QA Real World
Installs to ~/.claude/commands/nirelbaz-promptpit-qa-real-world.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/nirelbaz/promptpit/HEAD/.claude/commands/qa-real-world.md -o ~/.claude/commands/nirelbaz-promptpit-qa-real-world.md Restart Claude Code, or start a new session, for it to be picked up.
What QA Real World does
Run free-form agent-based QA against real-world public repos. Each agent acts as a developer who just discovered pit and wants to try it on a project. The agent learns what pit is only from the README and CLI help, then explores organically.
Steps
**Build the CLI** so agents use the latest code:
npm run build**Launch 3 parallel agents** (3 repos each). Give each agent these instructions:
You are a developer who just found a CLI tool called `pit`. You've ne
Alternatives in Testing
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Playwright — Automate real browser interactions for navigation, forms, and scraping 14.6k ★
- Superpowers Evals — Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Ge 107 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Real Repo Testing
Use when testing buoy changes against real-world repos, validating drift detection accuracy, comparing before/
Mind World Map
Agent skill for engineering mind maps — closure standard a cold reader can verify, two generations of machine
Local Binary Swap
Publish and swap local netclaw/netclawd binaries for live integration testing. Activate when user says "swap b
AI Tester
End-to-end behavioral testing skills, bare system prompts, and any agent runtime — run real scenarios in an is
Dogfood
Exploratory web QA against a target URL — drives a real browser, captures evidence, writes a structured report
Selftest
Run the hardmode self-test — the real shipped hooks against planted failure modes in a throwaway sandbox, plus
Related Agents
Kimi Ask
Use this agent when the user wants Kimi to answer a free-form question about the repository in prose — explain
Docs Privacy Reviewer
Use after writing or editing any file under docs/. Reviews a documentation file for personal data and secrets
Zp Verifier
ZeroProtocol adversarial verifier. Use to try to REFUTE a candidate finding before it is written up - re-repro