.claude/skills/code-review/SKILL.md
Use before marking any task complete and before requesting a PR merge
npx skillsauth add mezivillager/hacer code-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Before calling any task "Done", you must execute the full local verification suite and confirm all checks pass. </instructions>
<rules> ### 1. Verification Requirements - **Linting**: `pnpm run lint` must exit with code 0 (ESLint + Typecheck). - **Unit Tests**: `pnpm run test:run` must pass all Vitest tests. - **Store E2E**: `pnpm run test:e2e:store` must pass all Playwright store tests. - **Build**: `pnpm run build` must succeed without errors.useCircuitStore(s => s.x).circuitActions.*() only.useMemo, useCallback, or React.memo (React Compiler handles this).message/notification instead of console.log.any types; use strict interfaces; JSDoc (@param, @returns) on all exports..cursorrules.REPO_MAP.md for structural changes.tasks/todo.md accurately reflects the implementation state.
</rules>
GateIcon into its own file per HACER conventions."useMemo detected; please remove it to let the React Compiler manage memoization."inputPinA might be clearer as leftInputPin to match the 3D layout."lint, test, build) passed?.cursorrules?any types or console.log remaining?development
A comprehensive verification system for Claude Code sessions.
development
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
tools
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
testing
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.