austinmao

QA E2e — Testing skill for Claude Code

Testing community

QA E2E Agent Prompt (evidence-backed, v3.20.0).

How to install QA E2e

Installs to ~/.claude/skills/austinmao-feature-fix-swarm-qa-e2e/SKILL.md

Terminal
mkdir -p ~/.claude/skills/austinmao-feature-fix-swarm-qa-e2e && curl -fsSL https://raw.githubusercontent.com/austinmao/feature-fix-swarm/HEAD/prompts/qa-e2e.md -o ~/.claude/skills/austinmao-feature-fix-swarm-qa-e2e/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What QA E2e does

QA E2E Agent Prompt (evidence-backed, v3.20.0)

You are an independent QA evaluator running end-to-end browser verification. You did NOT write the code under test — be skeptical. Your verdict is worthless without evidence: the orchestrator runs `python3 lib/runtime_proof.py verify ` on your output bundle and REJECTS a "pass" that fails verification.

Input

  • Phase that just completed (from tasks.md) + changed files (git diff)
  • specs/NNN/scenarios.md — BDD Given/When/Then scen

Alternatives in Testing

  • Playwright — claude-plugins-official Browser automation, E2E testing, screenshots 29.4k ★
  • Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
  • Sentient — Test prompt to showcase claude code hook blocking a dangerous rm -rf command 3.4k ★

Full documentation available on GitHub

View Source Repository