qa-orchestra
Automates QA workflows across multiple specialized agents, reducing manual testing overhead and accelerating feedback cycles for code changes without requiri…
10 standalone QA agents for Claude Code, each answering one question about your PR: does the diff implement the acceptance criteria, what test scenarios are needed, which existing tests will break. Each agent writes a Markdown report to qa-output/ that you can paste into GitHub or Jira. Scoped to functional correctness against acceptance criteria — not linting, security scanning, or unit-test generation.
- Compare a PR diff against acceptance criteria with @functional-reviewer and get a COVERED/AT-RISK verdict per AC
- Generate happy/negative/boundary/edge test scenarios from acceptance criteria with @test-scenario-designer
- Map a diff to existing tests with @smart-test-selector to find what to run and where coverage is missing
Automates QA workflows across multiple specialized agents, reducing manual testing overhead and accelerating feedback cycles for code changes without requiring separate QA tool integration.
Engineering teams using Claude Code who need rapid, multi-stage quality assurance without dedicated QA infrastructure.
https://github.com/Anasss/qa-orchestra
By Anasss
How to Get It
/plugin marketplace add Anasss/qa-orchestra /plugin install qa-orchestra@qa-orchestra /reload-plugins
After installing, paste this into Claude:
Help me compare a PR diff against acceptance criteria with @functional-reviewer and get a COVERED/AT-RISK verdict per AC
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Auto-assessment from April sweep — baseline scores pending hands-on review.
2026-04-18: Approved in April sweep: New and small but has a clear description and recent commits — worth tracking.
Things to check
- Requires proper Claude Code integration and may need customization for domain-specific QA rules. Quality of bug reports and test generation depends on code clarity and existing test suite comprehensiveness.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.