Loading...
Loading...
Found 35 Skills
Systematically find blind spots in code, architecture, APIs, and deployment — structured critique that catches what familiarity hides
Iterative codebase quality audit with multi-agent validation and escalating-depth SEEK/VALIDATE/FIX/RECURSE cycle. Use for quality audit, code audit, codebase review, technical debt audit, refactoring opportunities, module quality check, or architecture review.
LOAD THIS SKILL when: reviewing code before PR, user mentions 'code review', 'review', 'pre-PR check', 'code quality audit'. Contains project-specific review checklist covering TRPC, TanStack, Drizzle, security, performance, and Effect patterns.
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations.
Detect AI-generated code patterns ("slop") in PHP/Laravel and TypeScript/React source — comment narration, generic naming, premature interfaces, defensive overdose, mock-everything tests, and the absence of human "scars". Use when reviewing AI-assisted PRs, auditing code for taste/quality (not metrics — that's technical-debt), or hardening a code-review checklist. Triggers on "review for AI slop", "find AI patterns", "check code feels human", "audit code-quality taste".
Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.
Scans the codebase against another skill's criteria using a parallel agent team. Use when the user says /scan <skill-name> to audit code quality, find violations, or assess conformance to best practices.
Run comprehensive 3-wave review against all source files in the repo, producing a prioritized issue backlog. Use for "full repo review", "review entire repo", "codebase health check", "review all files", "full codebase review". Do NOT use for PR-scoped reviews (use comprehensive-review) or single-concern reviews (use individual agents).
Automate lifecycle checks for migration code (TODO(migration)). Detect expired or insufficiently documented migration code and output results in report format. It is used for checking remaining TODO(migration) entries in the codebase, cleaning up expired migration code, and taking inventory of technical debt. This is a mechanism to prevent leaving "to be deleted later" code unattended.
Comprehensive pull request review using specialized agents
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target