Generate and execute tests from a task spec's Test plan.
npx skills add https://github.com/ChazzCoin/claude-kit --skill auto-test-chazzcoin
Please help me install this Agent Skill. Skill: auto-test Source: https://github.com/ChazzCoin/claude-kit/tree/main/kit/skills/auto-test Command: npx skills add https://github.com/ChazzCoin/claude-kit --skill auto-test-chazzcoin
Writing and maintaining tests for tasks or features is time-consuming and error-prone; this skill derives test scenarios from the spec's test plan and automates test creation, execution, and result reporting to ensure alignment with intended behavior.
Provide a task spec and run the /auto-test command to generate, execute, and report tests autonomously.
High-intent search queries and answers about installing and using this skill.
Automating test generation from a task spec requires deriving scenarios directly from the test plan and acceptance criteria. This skill autonomously generates and executes those tests in the project's native framework, reporting pass/fail outcomes.
Autonomous test execution validates intended behavior by applying a test stamp model to the generated tests. It runs the tests in-context within the native testing framework and collects pass/fail results to confirm alignment with the task spec.
Yes, you can use this with your project's native testing framework. It writes and executes the generated tests in-context using that framework, applying the kit's test stamp model to ensure the tests run natively in your environment.
When the task spec is incomplete during automated test creation, the skill surfaces detailed reports that flag any assumptions it had to make. This ensures transparency regarding the derived test scenarios and the validated behavior.
You need a task spec containing a defined test plan to derive test scenarios properly. The skill relies on the task spec for defining expected behavior and uses autonomy-rules.md for gates and test-rules.md for stamping.
The best way to report pass/fail outcomes for QA automation is to execute the generated tests in-context and surface detailed reports. This approach flags assumptions when the spec is incomplete and ensures alignment with intended behavior.
ChazzCoinAudit a codebase for behavior-preserving improvements and generate tasks and a draft PR.
maksutovicExtract acceptance criteria and test plans to verify implementations against specifications.
japurcellBreak down project work into verifiable tasks with acceptance criteria and dependency ordering.
jmaglyValidate phase-gate criteria and generate pass/fail gate reports.
