alexpalexpinne/qa-toolkit
Five software testing workflows: review requirements, design and review test cases, prepare test data, draft bug reports, and summarize results with gaps and unknowns made visible.
Guides testers and end users through writing clear, actionable defect reports: drafting a new report through a short interview, turning the current conversation into a report, or reviewing an existing report. Use only when the user explicitly invokes this skill or asks for it by name.
Reviews user stories, use cases, requirements, and acceptance criteria for testability before development starts: finds ambiguous wording, missing cases, contradictions, untestable criteria, and gaps against parent requirements, and turns them into concrete questions for the product owner. Use only when the user explicitly invokes this skill or asks for it by name.
Creates or updates a team's shared conventions file for the QA Toolkit skills (.qa-toolkit/conventions.md): languages, tracker, severity scale, and the rules for reviewing requirements, test cases, test data, bug reports, and test summaries. Asks a few questions at a time, shows the whole file, and writes it only after approval. Use only when the user explicitly invokes this skill or asks for it by name.
Designs test cases from user stories, use cases, requirements, and acceptance criteria, covering the main flow, error cases, boundaries, and invalid input, with each case traced to the criterion it covers. Can also review existing test cases for gaps and weaknesses, or restructure them into a clean, consistent format without changing what they test. Use only when the user explicitly invokes this skill or asks for it by name.
Creates safe, realistic test data for manual and automated testing: valid values, boundaries, invalid input, and international edge cases, from a requirement, a field list, a schema, or test cases with placeholders. Uses values reserved or documented for testing for contact, payment, and identity details, and labels invented names and addresses as fictional. Can also review an existing test data set for gaps and real-looking personal data. Use only when the user explicitly invokes this skill or asks for it by name.
Turns test results, defect lists, and notes into an honest test status report or test completion report for managers and stakeholders: what was tested, what passed, failed, was blocked, or was not run, which defects remain open, what was not tested, and an assessment against exit criteria. Can also review an existing test report for gaps and misleading figures. Use only when the user explicitly invokes this skill or asks for it by name.