Qa verify
Run scenario-based verification and regression checks for changed behavior, user flows, and bug fixes before delivery. Use after implementation or review whenever behavior changed or user-visible quality matters.From its SKILL.md
npx -y skills add keithhegit/ultra-orchestration --skill qa-verifyAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.0 KB, 167 tokens by cl100k_base, as published. Nobody here has run it
QA Verify
Validate behavior, not just code shape.
Treat QA as two-mode verification:
- Static baseline: reason over code, diffs, existing tests, and available evidence
- Dynamic verification: run tests or commands when the host environment allows it
Do not assume browser automation exists unless the environment explicitly provides it.
Check
- Happy path
- Error path
- Regression risk
- User-visible behavior
- Follow-up tests that should exist even if they are not added now
Failure handling
- If behavior is wrong but the plan is still valid, send the work back to
Execute. - If QA reveals a deeper architecture or requirement flaw, send the work back to
Plan.
Output
Return:
- scenarios exercised
- evidence collected
- pass or fail status
- residual risks
What ships with it: 1 file
249 B alongside SKILL.md
agents/
- openai.yaml249 B