Run eval fixtures against a skill to verify it produces correct output. Reads the skill's SKILL.md and tests/fixtures.json, simulates each scenario, and checks assertions. Use after /improve to verify fixes didn't break anything. Use when: "eval", "run evals", "test skill", "check fixtures", "regression test". Do NOT use when: running actual QA on an app (use /qa), improving a skill (use /improve), checking sprint status.
Generate and guide exploratory testing sessions. Produces a session charter, executes time-boxed unscripted testing using heuristic techniques, captures findings as new test scenarios, UX improvements, and missing coverage. Feeds discoveries back into the knowledge base and test cases. Use when: "exploratory test", "explore this feature", "charter for testing". Do NOT use when: executing formal test cases (use /qa), verifying a specific bug fix (use /verify-fix), planning tests (use /test-plan).
Meta-skill that improves other skills based on real usage failures. When an SDT reports a skill produced incorrect or unexpected output, this skill analyzes the root cause, generates a structured improvement proposal, applies the fix following CONTRIBUTING.md guidelines, and offers to create a PR or apply locally. Use when: "improve", "this didn't work", "fix this skill", "the output was wrong", "skill improvement", "qa-improve". Do NOT use when: giving content feedback on output (use option B at pause point), asking about QA methodology, running normal QA workflow.
SDT test execution skill. Executes test cases from the knowledge base, verifies acceptance criteria in the browser, files bugs in Jira for failures, and updates the KB with results. Works within sprint context: knows the ticket, the ACs, the test cases, and what needs to pass before the ticket moves forward. Optional --fix flag for teams where SDTs handle minor fixes. Use when: "qa", "test this ticket", "run test cases", "verify ACs", "does this pass?". Do NOT use when: asking about QA methodology, verifying a bug fix (use /verify-fix), just reporting without filing bugs (exploratory), checking sprint status.
Review a Jira ticket during backlog grooming or refinement. Audits the ticket for testability, AC completeness, missing edge cases, and potential blockers. Outputs a structured review the SDT can bring to the grooming session. Use when: "review this ticket", "check ACs", "testability review", "grooming". Do NOT use when: building a test plan for an epic (use /test-plan), writing test cases (use /test-cases), testing in the browser (use /qa).
First-run configuration wizard for QABuddy. Sets up context source (Jira, spec docs, chat, custom), team mode (solo vs PR-based), and project preferences. Writes .qabuddy.json to the project root. Re-run to reconfigure. Use when: "setup", "configure", "first time setup", "change settings". Do NOT use when: asking about QABuddy features, asking how to use a skill, mid-workflow.
Cross-feature testing dashboard for mid-sprint status checks. Pulls the current sprint from Jira, cross-references with local test knowledge base and QA reports, and shows what's tested, what's blocked, and where coverage gaps are. Use when: "sprint status", "what's tested", "coverage check", "testing dashboard". Do NOT use when: testing a specific ticket (use /qa), creating test artifacts, fixing bugs.
Guided end-to-end QA workflow. Chains test planning, ticket reviews, and test case generation in sequence, pausing after each phase for SDT review. Resumes from where it left off if interrupted. The main entry point for new epics. Use when: "start", "begin workflow", "qa workflow", "guided qa", "new epic". Do NOT use when: working on a single ticket (use individual skills), reconfiguring settings (use /setup), mid-sprint status check.