skills

Use when the user says "drive the code", "/drive-code", "clean up the code in this PR", "make sure the touched files follow best practices", or asks Claude to do a code-quality pass on the files a PR (or working tree) touches. Evaluates each touched file for single-responsibility, modularity, service/repository pattern compliance, utility placement, naming, length, and runs the project's linter + formatter. Applies mechanical fixes automatically; proposes (with diff) any structural refactor before changing it. Does NOT verify the feature's behaviour (use /drive-feature) or its UX (use /drive-ux).

Use when the user says "drive the feature", "/drive-feature", "audit the feature logic", "is this feature complete", "check edge cases", or asks Claude to verify that a feature (typically the one in the current PR) is well built end-to-end. Reads any ADRs and specs that exist for the feature, traces the data flow from entry to exit, and checks edge cases, error handling, loading states, and side effects against the spec. Does NOT pass judgment on code style (use /drive-code) or click through the UX (use /drive-ux) - focuses on logic and completeness.

Use when the user says "drive this PR", "/drive-pr", asks to resolve all PR comments, get a PR green, address review feedback, or otherwise wants Claude to iterate on an open pull request until every trusted comment is resolved, CI is passing, and the PR description matches the code. Operates only on the current branch's PR or an explicitly passed PR number/URL.

Use when the user says "drive the security", "/drive-security", "security review", "is this safe", "check for vulnerabilities", or asks Claude to do a security-focused audit of the files a PR (or working tree) touches. Audits authn/authz on touched routes, scans for hardcoded secrets, checks input validation and output encoding at trust boundaries, runs dependency-vulnerability tools (npm audit / pip-audit / cargo audit / govulncheck) where available, and flags OWASP-top-10 smells. Applies safe mechanical fixes inline; surfaces judgment calls. Companion to /drive-code (code shape), /drive-feature (logic), /drive-test (tests).

Use when the user says "drive the tests", "/drive-test", "review the tests", "are the tests any good", "check test coverage", or asks Claude to audit test quality across the files a PR (or working tree) touches. Evaluates each touched file's tests for level (unit vs integration vs e2e), assertion quality, mock health, coverage of new code paths, and the classic smells (mocking the unit under test, snapshot churn, tests-that-can't-fail, etc.). Runs the test suite to confirm green, fixes mechanical issues, surfaces judgment calls. Companion to /drive-code (which checks code shape) and /drive-feature (which checks logic).