spec-qe
Core skill for Quality Engineers in AI-native builder pods using spec-driven development with Claude Code. Use this skill whenever you need to: translate PM acceptance criteria into Claude-executable test assertions, run a spec drift detection pass on a completed build, generate a regression test suite from this sprint's spec, verify edge cases that Claude Code implementation may have gotten wrong despite looking correct, aggregate spec drift logs across pods for the monthly retrospective, or produce a release verification report. Trigger on any request involving test generation, acceptance verification, spec compliance checking, edge case testing, or quality gate decisions in the AI-native build pipeline. Quality in this system is verified against the spec — not discovered after shipping.
@qe-leadHow to install
This skill is part of the product-delta-force plugin. To use it, install the plugin via one of these methods:
Claude Code: git clone git@github.com:carousell/ct-builder-os.git ~/.builder-os && ~/.builder-os/scripts/bootstrap.sh <your-role>
Claude Desktop: Download product-delta-force.zip → Settings → Customization → Upload
Full skill source is available to team members with repository access.