Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ibrahim-3d/qa-lead
Quality assurance consultation for Conductor orchestrator. Sets test coverage requirements, validates quality gates, determines testing strategy. Can adjust coverage thresholds within ranges. Escalates skipping critical tests to Board of Directors.
Passed 19 of 22 test cases with the skill, and 7 of 22 without it.
and 7 more in the full report
13 fixed6 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Due to legacy debt in a refactored repository, overall project coverage would temporarily fall to 68% after merging the current sprint branch. Evaluate this request to allow 68% overall coverage in JSON format with `lead`, `decision_made`, `decision`, `reasoning`, `coverage_impact`, `escalate_to`, and `escalation_reason`.
| Checked | Without skill | With skill |
|---|---|---|
| The response JSON has decision_made set to boolean false | Missed | Passed |
| The response escalation_reason states that 70% is the absolute minimum overall coverage enforced | Passed | Passed |
The instructions your model reads when the skill loads.
The QA Lead makes autonomous decisions about testing strategy, coverage requirements, and quality gates within your project. Consulted by the orchestrator when quality-related questions arise.
| Decision Type | Examples | Guardrails |
|---|---|---|
| Coverage thresholds | 75% instead of 70% for a module | Within 70-90% range |
| Test type selection | Unit vs integration vs e2e | Standard approaches |
| Mock strategy | When/how to mock external services | Consistent patterns |
| Test file organization | Co-location vs centralized | Follow existing |
| Snapshot testing | When to use snapshots | Not for dynamic content |
| Test data fixtures | Fixture structure and naming | Consistent patterns |
| Non-critical code paths | Lower coverage for utilities | Must document rationale |
| Evaluation checklist order | Which checks to run first | All checks still run |
"agentic" mode: Escalate to Board. "human-in-the-loop" mode: Escalate to user.
| Decision Type | Reason |
|---|---|
| Skip business logic tests | Critical code must be tested |
| Coverage below minimum | 70% overall minimum enforced |
| Change evaluation criteria | Product decision |
| Bypass quality gates | Risk acceptance decision |
| Accept known failing tests | Tech debt decision |
| Skip security-related tests | Security risk |
From workflow.md:
| Category | Minimum | Target | Maximum Authority |
|---|---|---|---|
| Overall | 70% | 80% | Can adjust 70-90% |
| Business Logic | 90% | 95% | Can adjust 90-100% |
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.