Loading...
Loading...
Found 759 Skills
Orchestrator that runs scope then language then framework then library then cognitive review skills in order and aggregates all findings into one report. Does not perform analysis itself.
Simulates a Senior Engineer PR review to teach professional communication and industry naming standards. Use to prepare students for professional engineering environments and code review cultures.
Review SQL and query code for injection risk, parameterization, indexing and performance, transactions, NULL and constraints, and dialect portability. Language-only atomic skill; output is a findings list.
[Frontend] Review UI code for web interface design compliance covering WCAG 2.2/3.0 accessibility, responsive design, performance, usability, and modern best practices. Use when asked to 'review my UI', 'check accessibility', 'audit design', 'review UX', 'check responsive design', or 'check my site against best practices'. Actions: review, check, audit, analyze, validate. Topics: accessibility, WCAG, ARIA, semantic HTML, focus states, forms, animation, typography, content handling, images, performance, Core Web Vitals, navigation, touch interaction, responsive design, mobile-first, dark mode, internationalization, hydration.
Universal code quality rules. Extends nothing — this is the base skill every project should include. Use when writing or reviewing any code.
Check work and detect drift before committing. A second opinion that catches misalignment early. Use at natural pause points, before PRs, or when something feels off.
Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini operations.
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Use Slopwatch to detect LLM reward hacking in .NET code changes. Run after every code modification to catch disabled tests, suppressed warnings, empty catch blocks, and other shortcuts that mask real problems.
Multi-agent code review with specialized perspectives (security, performance, patterns, simplification, tests)
Configure which review agents run for your project. Auto-detects stack and writes compound-engineering.local.md.