hugin-cowork

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions for skill evaluation.

Automatically resolve TypeScript compilation and build errors systematically. Use when fixing build errors, TypeScript errors, compilation failures, tsc errors, or when the build is broken and needs to be fixed.

Semantic code review using project-specific rules

Review recently written code for best practices, architectural consistency, and system integration. Use when reviewing code, checking implementations, after completing significant code changes, or when asking for a code review.

Refactor code for better organization, cleaner architecture, and improved maintainability. Use when reorganizing code, cleaning up messy files, extracting components, splitting large files, or improving code structure.

Blind comparison of two outputs for skill evaluation. Judges quality without knowing which skill produced which output.

Create, update, or enhance documentation for any part of the codebase. Use when creating documentation, writing docs, updating README files, documenting APIs, or when something needs documentation.

Evaluate expectations against execution transcripts and outputs for skill evaluation. Grades assertions and critiques eval quality.

Review development plans before implementation to identify potential issues and missing considerations. Use when reviewing plans, validating strategies, before starting implementation, or when you want to make sure nothing is missed.

Apply rigorous first-principles engineering analysis to any technical task. Use when applying first-principles analysis, conducting architectural reviews, system design reviews, or trade-off analysis.

Analyze code structure and create comprehensive refactoring plans with risk assessment. Use when planning refactoring, analyzing technical debt, identifying code smells, or creating restructuring plans.

Verify task completion before finishing work. Spawn with task ID, location, and work summary.

Research information on the internet for debugging, finding solutions, and gathering comprehensive information. Use when researching solutions, debugging errors, finding best practices, comparing approaches, or looking up documentation.

This skill should be used when the user asks about accessibility concerns, including WCAG compliance (any success criterion including SC 1.3.5 autocomplete, SC 2.4.11 focus obscured), ARIA roles and attributes, screen reader behavior, axe-core or WAVE audit failures, color and non-text contrast, keyboard navigation, focus trapping and management, skip links, touch targets, VPAT reports, or accessible form patterns. Also triggers when the user asks whether a UI library such as shadcn or Radix handles keyboard interactions — but only if the question is specifically about accessibility behavior, not general usage.

This skill should be used when the user asks to write an ADR, create an ADR, document this decision, ADR for X, architecture decision record for X, record this decision, or document the decision to use X. It writes, validates, and commits Architecture Decision Records in MADR 4.0.0 format. Do NOT trigger on lookup or audit tasks such as what ADR covers X or check ADR compliance.

This skill provides automatic semantic code review triggered after file modifications. It is hook-driven — logging file changes via PostToolUse and running the automatic-code-reviewer agent on Stop. It should not be invoked directly by the user; it is triggered automatically by lifecycle hooks.

This skill should be used when the user asks to code connect, connect this component to code, connect Figma to code, map this component, link component to code, create code connect mapping, or add code connect. It connects Figma design components to code components using Code Connect.

This skill should be used when the user asks to visualize components, show component dependencies, dependency graph, component map, or what depends on what. It generates interactive HTML dependency graphs for React components.

This skill should be used when the user asks to create design system rules, generate rules for my project, set up design rules, or customize design system guidelines. It generates custom design system rules for the codebase to establish project-specific conventions for Figma-to-code workflows.

This skill should be used when the user asks to create tasks, define work items, break this down, or wants to convert requirements into actionable tasks and feature breakdowns for sprint planning. It creates well-formed tasks following a template that engineers can implement.

This skill should be used when the user provides Figma URLs or node IDs and asks to implement designs or components that must match Figma specs with 1:1 visual fidelity. It translates Figma nodes into production-ready code using the Figma MCP workflow for design context, screenshots, assets, and project-convention translation.

This skill should be used when the user provides Figma URLs or node IDs, asks about design-to-code implementation, or needs to set up or troubleshoot the Figma MCP server. It uses the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma and translate Figma nodes into production code.

This skill should be used when the user asks about Miro capabilities, wants to create content on Miro boards, or needs to work with Miro board data. It teaches how to use Miro MCP tools effectively for creating diagrams, documents, tables, and extracting context from Miro boards.

This skill should be used when the user is building Node.js backend services, APIs, or microservices. It covers core Node.js backend patterns for TypeScript applications including async/await error handling, middleware concepts, configuration management, testing strategies, and layered architecture principles.

This skill should be used when the user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing. It provides complete browser automation with Playwright including auto-detection of dev servers, writing clean test scripts, testing pages, filling forms, taking screenshots, checking responsive design, and validating UX.

This skill should be used when the user is working with Prisma database operations or schema definitions. It covers Prisma ORM patterns including Prisma Client usage, queries, mutations, relations, transactions, and schema management.

This skill should be used when the user is writing, reviewing, or refactoring React code to ensure optimal performance patterns. It provides React performance optimization guidelines from Vercel Engineering, covering tasks involving React components, data fetching, bundle optimization, or performance improvements.

This skill should be used when the user is working with React components, hooks, lazy loading, Suspense boundaries, or React-specific TypeScript patterns. It covers core React 19 patterns including hooks, Suspense, lazy loading, component structure, TypeScript best practices, and performance optimization.

This skill should be used when the user is testing HTTP API routes, working with authentication strategies, or writing integration tests. It covers framework-agnostic HTTP API route testing patterns, JWT cookie authentication, and other common auth patterns.

This skill should be used when the user says setup, check my setup, verify config, is everything configured, or wants to confirm their development environment is ready. It verifies that environment variables, MCP servers, and related tools are configured correctly.

This skill should be used when the user is working with shadcn/ui, component registries, presets, or any project with a components.json file. It manages shadcn components and projects including adding, searching, fixing, debugging, styling, and composing UI. Also triggers for shadcn init, creating apps with presets, or switching presets.

This skill should be used when the user is styling with Tailwind, adding utility classes, configuring Tailwind, setting up dark mode, or customizing the theme. It covers Tailwind CSS v4 utility-first styling patterns including responsive design, dark mode, and custom configuration.

This skill should be used when the user wants to verify task completion before finishing work. It checks acceptance criteria, catches incomplete work, bugs, and quality issues by spawning the task-check agent with a task ID, location, and work summary.

This skill should be used when the user asks to review my UI, check accessibility, audit design, review UX, or check my site against best practices. It reviews UI code for Web Interface Guidelines compliance.

This skill should be used when the user is writing, reviewing, or improving tests. Triggers on phrases like write tests, add tests, test naming, what should I test, edge cases, test structure, or assertion. Also triggers when the user shares a test and asks for review, asks about assertion best practices, or reports finding a bug and wants to know what else to test. Do NOT trigger for test runner configuration or CI/CD pipeline setup.

10 hooks across 5 events