Code Quality Skill Leaderboard
A set of engineering skills for domain modeling, architectural design, bug diagnosis, and specification-based code reviews.
Audits repositories for over-engineering and aggregates shortcut comments into a technical debt ledger.
A set of structured engineering skills for AI agents covering API design, context optimization, and production-grade code quality.
A set of AI skills for full-stack development, including Angular 17+ architecture, .NET Core expertise, and system design documentation.
A six-phase research workflow that synthesizes unfamiliar domains and source bundles into publish-ready reference material.
Systematic SwiftUI code review covering modern APIs, accessibility, performance, data flow, and code hygiene, with line-level fixes and a prioritized summary.
Installs and configures opinionated Oxlint plugins to detect and reject low-evidence patterns in TypeScript and JavaScript repositories.
Provides auditing and optimization skills for WCAG 2.2 accessibility, SEO visibility, and Core Web Vitals performance.
Provides code review guidance, security audits, and performance checks for multiple languages and frameworks including React 19, Vue 3, Rust, and TypeScript.
Technical patterns for Node.js and React development, ClickHouse query optimization, and eval-driven development frameworks.
A code quality toolkit for performing architecture audits, assessing technical debt, and automating health monitoring.
Developer skills for AI systems, data pipelines, APIs, architecture, accessibility, security, performance, and framework migration.
Applies behavioral constraints to AI coding tasks to avoid superficial fixes, stale edits, and maintainability issues.
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never grades it.
A secure coding guide for web application development and audit, covering major vulnerability classes with patterns, bypass prevention, and checklists.
Five guard skills for reviewing AI-generated code, documentation, tests, WordPress plugins, and WooCommerce extensions against systematic failure modes.
A development harness for Claude Code featuring spec-driven workflows, quality gates, and standardized Go engineering patterns.
A collection of skills for AI agents to perform anti-entropy governance, architecture brainstorming, and parallel agent dispatching.
A design-centric skill for creating cinematic websites and multi-screen product systems with automated visual quality gates.
Adversarial courtroom review and direct editing for CS-conference papers in LaTeX or Markdown, with multi-round review, trial verdicts, and author-gated revisions.
Audits codebases for AI-introduced security issues: exposed secrets, broken access control, insecure payments, and authentication flaws in vibe-coded applications.
A set of TypeScript conventions for naming, function design, React prop typing, and the implementation of discriminated unions.
Eight skills that codify 37signals’ opinionated Rails conventions for architecture, realtime, jobs, migrations, security, testing, and webhooks.
Provides a systematic method for designing, modifying, and reviewing HTTP/JSON API endpoints, request/response shapes, and versioning strategies.
AI rules for Flutter development focusing on feature-first architectural patterns and WCAG accessibility standards.
Performs a file-cited codebase audit covering nine debt dimensions, producing a report with severity, effort estimates, and a required section for false positives.
Enforces TDD, SOLID, and clean code practices during coding, refactoring, and design to produce senior-engineer-quality software.
A set of skills for documenting existing system architecture, building design baselines, and recording architectural decisions.
A library of agent skills for enforcing SOLID principles, clean code patterns, and language-specific best practices in AI-generated code.
A suite of AI skills for Elixir/Phoenix development featuring A/B codex reviews for Ecto and LiveView and a plugin development workflow.
Reviews Swift concurrency code for actor reentrancy, structured concurrency violations, cancellation issues, and async/await pitfalls with reference-backed guidance.
Technical skills for optimizing Jetpack Compose performance, focusing on Lazy layout stability, R8 configuration, and recomposition audits.
An adversarial code audit tool for detecting security and logic defects using deterministic risk triage and a multi-role review process.
A set of engineering skills for auditing AI agent security in GitHub Actions and optimizing project-rules for agent context.
A comprehensive set of 265 prioritized Rust coding rules for AI agents, covering ownership, error handling, async, unsafe code, API design, memory optimization, performance, and testing, sourced from official guidelines and real-world codebases.
A Rails architecture guide for auditing layer boundaries, reviewing changes, selecting patterns, and planning gradual refactors.
Implements boundaries for AI agents to prevent scope creep, unnecessary hashing, and speculative changes during coding tasks.
A set of skills for AI agents to analyze pull request status, resolve review comments, and verify submission requirements across multiple version control systems.
A cybersecurity practice library covering audits, penetration testing, SOC operations, threat hunting, incident response, and compliance against OWASP, NIST, PCI, HIPAA, and AI RMF.
A security review skill that applies OWASP Top 10:2025, ASVS 5.0, and AI-specific security standards to code analysis.
A library of 22 skills for TDD, design review, honest communication, concise output, debugging, code organization, and task creation in AI-assisted development.
A set of skills for detecting workflow friction and managing model escalation governance in AI agent environments.
Automation tools for VLM-driven image screening, visual regression testing, and Cloudflare infrastructure deployment.
A set of prompting skills for identifying project blindspots and designing self-documenting interfaces for AI agents.
A set of engineering skills for auditing Xcode security settings, implementing C bounds-safety, and modernizing UIKit apps for SwiftUI and multi-window support.
A general-purpose SAST skill for analyzing source code vulnerabilities across 34 classes using taint tracking and pattern matching.
AI coding guidelines inspired by Linus Torvalds: data structure first, no speculative abstractions, testable claims, and a built-in bogus-shit detector.
A security scanner that detects common vulnerabilities in Go, PHP, Python, TypeScript, and .NET code with bilingual reporting.
Analyzes Ruby on Rails applications for security, testing practices, and code design to produce a categorized audit report with severity levels.
Conducts maintainability audits by scanning for code and test smells, measuring structure metrics, and reporting technical debt with evidence.