Agent Skills Hub

memov

AI-assisted version control for code agents. Track prompts, context, and diffs automatically with MemoV to ensure full traceability without polluting your git history.

nav-task

Manage Navigator task documentation: create implementation plans, archive completed features, and maintain the task index for Claude Code workflows.

elegant-design

Build professional, accessible, and responsive user interfaces using React, Next.js, and modern design systems like shadcn/ui. Focuses on developer tools, chat interfaces, and real-time streaming components.

web3-testing

Comprehensive smart contract testing skill for Hardhat and Foundry, featuring unit tests, integration suites, gas optimization, fuzzing, and mainnet forking.

orchestrate

Multi-phase feature development workflow for complex tasks using research, planning, implementation, and review gates.

with-context-agent

Lints, validates, and auto-fixes AI agent configuration files like SKILL.md, CLAUDE.md, and MCP configs.

refactor

A specialized skill for surgical code refactoring. Improves maintainability, reduces technical debt, and applies design patterns without altering external behavior.

bunjs-architecture

Enforce clean architecture for Bun.js apps: layered patterns (routes/controllers/services/repos), camelCase naming conventions, Prisma schema design, and structured implementation workflows.

investigate-dependencies

Conduct thorough dependency audits to identify redundant code, unused features, and improper usage patterns. Ensures project modularity by leveraging existing dependencies instead of reinventing functionality.

nuxt

Nuxt framework disambiguation layer for optimizing project development, routing to the correct Nuxt pack, Vue guidance, or module-specific logic.

tailwind-design-system

Build scalable, production-ready design systems using Tailwind CSS v4, featuring CSS-first configuration, design tokens, component variants, and responsive patterns.

prompt-improver

Enriches vague prompts by performing codebase research and asking targeted questions to clarify user intent before execution.