Description
quality-playbook is an agent skill from the github/awesome-copilot collection that runs a complete quality engineering audit on a codebase. It works in phases, and the skill insists that the plan be read first, because each phase produces artifacts that the next one depends on. Phase 0 loads the findings of any earlier quality run as seed data, so re-runs build on what was learned. Phase 1 explores the code in three stages: open exploration driven by domain knowledge, a risk analysis based on that knowledge, and selected structured exploration patterns. Its findings are written to a quality/EXPLORATION.md file, which is the foundation for everything after. Phase 2 reads that file and generates the quality artifacts: behavioral requirements derived from the code, a constitution, functional tests traced back to those requirements, a code review protocol, integration tests, a specification audit protocol and a test-driven development protocol. The skill also includes a document intake step that reads reference documents the project supplies. The goal is to find where the code's behavior and its intent diverge, and to give the team tests and protocols that keep them aligned. A quality audit is only as good as the domain knowledge behind the exploration, so a team member who knows the system should check the requirements the skill derives from the code. The skill is installed with the skills CLI from the github/awesome-copilot repository. Its skills.sh page showed about 1.6K installs. At the time of the scan, Gen Agent Trust Hub returned a warning, while Socket and Snyk passed.…
Highlights
- Phased audit that reuses prior run findings
- Behavioral requirements derived from code
- Spec-traced functional tests
- Code review, integration, spec audit and TDD protocols
- Installs with the skills CLI
Ratings & Reviews
No ratings yet
Be the first to rate quality-playbook.
People also visit
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS
quality-playbook FAQ
What does the audit produce?
Behavioral requirements, a constitution, spec-traced functional tests, review and integration test protocols, a spec audit protocol and a TDD protocol.
Why does the order matter?
Each phase depends on the artifacts of the one before, so skipping a phase leaves later phases working from incomplete information.
Can I re-run it?
Yes. Findings from a prior run are loaded as seed data.
How do I install it?
Run npx skills add https://github.com/github/awesome-copilot --skill quality-playbook.
What security audits does it have?
skills.sh lists three audits: Gen Agent Trust Hub Warn, Socket Pass and Snyk Pass. A Warn or Fail is worth reading before you install.
What are the best quality-playbook alternatives?
Popular alternatives to quality-playbook include bats-testing-patterns, e2e-testing-patterns and eval-harness-first. See all quality-playbook alternatives