Loading...
Loading...
Found 38 Skills
Explain how to manually inspect and test the work just completed in this conversation, using PowerShell commands where commands are needed.
Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.
Build health audit worker (L3). Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build configuration issues. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.
Implement a project from its documentation and specification. Use when asked to "implement project", "continue implementation", "build from docs", "implement from spec", or when the user wants to progressively implement a documented project following a todo checklist. Reads docs/, creates implementation plans and todo lists, and implements incrementally with tests and commits.
Write the minimal production code needed to make all existing failing tests pass. No extra features, no test modifications, no refactoring. Use after tests are written and confirmed failing.
Evidence-based test debugging enforcing systematic root cause analysis. Use when tests are failing, pytest errors occur, test suite not passing, debugging test failures, or fixing broken tests. Prevents assumption-based fixes by enforcing proper diagnostic sequence. Works with Python (.py), JavaScript/TypeScript (.js/.ts), Go, Rust test files. Supports pytest, jest, vitest, mocha, go test, cargo test, and other frameworks.
Used to confirm that development is completed and ensure all tests/checks have passed
Implement one task or scoped change: make the change, add valuable tests, and verify it works.
Choose the smallest valuable automated test evidence and prove it can detect the defect it guards. TRIGGER when: behavior-changing work needs a test decision; adding, changing, deleting, or reviewing tests; a test may be vacuous. SKIP when: only running existing checks or completing live post-ship verification (use test-completed-plan).
Prove a claim of done, fixed, or passing by running the commands and reading the output before making it. Use before claiming work is complete, fixed, or tested, and before committing or opening a PR.
Before declaring work complete, checks for loose ends: unused imports, TODO comments created, missing tests, stale references, incomplete error handling. Activates after implementing features or fixes. The cleanup that always gets skipped.
Smoke test for alicloud-compute-swas-open. Validate minimal authentication, API reachability, and one read-only query path.