Code Quality Skill Leaderboard

A set of engineering skills for domain modeling, architectural design, bug diagnosis, and standards-based code review.

Behavioral guidance for writing, reviewing, and refactoring code with explicit assumptions, minimal scope, and verifiable success criteria.

A code quality toolkit for performing repository audits, identifying deletable code, and tracking technical debt.

A token optimization toolkit that compresses LLM prompts and agent communications to reduce consumption by up to 65%.

A set of engineering skills for AI agents covering API design, interface contracts, and context engineering.

A knowledge graph tool for visualizing codebase structure, extracting domain flows, and analyzing pull request risks.

A prompt repository for automating codebase documentation, routing agentic workflow requests, and performing maintainability reviews.

A code review methodology that identifies actionable defects by verifying implementation against boundary agreements and forcing violating executions.

Conducts security audits and vulnerability research across codebases, APIs, services, and CLI tools.

A suite of skills for fixing UI layout issues, auditing HTML accessibility, and documenting design languages in DESIGN.md files.

Design skills for auditing WCAG 2.2 accessibility and generating semantic color tokens and palettes.

Converts formal or AI-style Korean commit messages into natural developer language while preserving Conventional Commits types and scopes.

A collection of vendored Oxlint plugins for rejecting low-evidence TypeScript and JavaScript patterns.

Filters generic AI output to enforce higher standards for code comments, UI accessibility, and copywriting.

Reviews SwiftUI code for modern API compliance, performance best practices, and the identification of deprecated patterns.

Tools for designing agentic control loops and deploying iterated coding-agent workflows via GitHub Actions.

Technical patterns for Node.js and React development, ClickHouse query optimization, and eval-driven development frameworks.

A set of developer tools for generating user-facing release notes from git tags and performing read-only root-cause analysis for bugs.

A set of skills for systematic book study and expert code review focusing on knowledge retention and software architecture.

Scans Apple's SwiftUI documentation to identify deprecated APIs and provide modern replacement guidance.

A collection of design engineering principles for implementing polished UI components, animations, and visual details.

Provides specialized skills for Go performance profiling, benchmarking, and the development of structured CLI applications.

Engineering tools for systematic bug diagnosis and the documentation of root cause analyses.

Provides AI agents with rule-based guidance for Clean Architecture, Domain-Driven Design, and software complexity management.

Provides auditing and optimization skills for WCAG 2.2 accessibility, SEO visibility, and Core Web Vitals performance.

A collection of Vue 3 skills covering composable design, component architecture, reactivity debugging, Pinia state management, Vue Router patterns, and testing with Vitest and Playwright.

An agent orchestration skill that uses independent Claude and Codex reviews to validate and harden complex technical implementation plans.

A meta-skill for engineering, evaluating, and governing the lifecycle of reusable AI agent skills from workflows and SOPs.

An 86-skill toolkit covering commits, standup updates, Jira, architecture diagrams, test plans, design systems, database schemas, and professional communication for software teams.

A skill guard that prevents AI agents from introducing speculative defenses, overengineering, and scope creep during coding tasks.

Diagnose-first guidance for Terraform/OpenTofu: identifies failure modes, proposes risk-controlled remediation, and enforces a response contract with validation and rollback plans.

A security review toolkit for AI agents featuring skills for vulnerability chaining, risk calibration, and automated remediation.

A 45-skill kit for Claude Code covering backend development, databases, authentication, devops, multimodal AI, document editing, and debugging.

Provides multi-language code review guidance covering architecture, security audits, and performance analysis for pull requests.

Creates and reviews technical documentation structured by the Diátaxis framework, specializing in tutorials, how-to guides, reference docs, and explanation pages.

Generates animated architecture and data-flow diagrams from code changes to assist in pull request reviews.

A set of tools and guides for designing, testing, and refining AI skills and agents using context engineering and evaluation metrics.

Software engineering tools for architectural sketching, type signature design, and jargon-free communication.

Diagnoses Swift Concurrency issues and guides the refactoring of callback-based code to async/await for Swift 6 migration.

A suite of skills for automating device interactions and performing systematic QA testing on mobile and Apple platform apps.

Verifies review comments, referee reports, and AI-generated findings against source files to ensure fixes are accurate.

An architecture audit and technical debt assessment tool with automated remediation capabilities for codebase maintenance.

A set of skills for applying Rust coding guidelines, naming conventions, and style best practices.

A set of developer tools for designing technical specifications and generating AGENTS.md context files to bootstrap AI-assisted development.

Provides specialized skills for codebase analysis, REST and GraphQL API design, and backend architecture optimization.

Applies behavioral constraints to AI coding tasks to avoid superficial fixes, stale edits, and maintainability issues.

Scans Xcode projects for App Store rejection patterns using app-type checklists and asc CLI metadata. Outputs severity-ordered reports with fix suggestions for metadata, subscriptions, privacy, entitlements, and design compliance.

A collection of skills for AI agents to perform architecture-aware brainstorming, plan execution, and anti-entropy governance in complex codebases.

A skill collection that turns AI coding assistants into SAST scanners for 15+ vulnerability classes including injection, authentication, and business logic flaws.

Detects and removes AI-generated design patterns, default semantic palettes, and machine-voice copy from web projects.