Browse the library

Composable skills that make AI coding assistants follow a design-first workflow from requirements to implementation and review, with project standards kept in a .lattice folder.

Claude Code plugin with 100+ skills, agents and hooks that enforce review gates and verifiable completion, with skills-only install for Codex, Cursor and others.

Allows AI agents to generate and configure CesiumJS 3D globe applications using specific domain skills for various API surfaces.

Official Sanity toolkit with an MCP server, agent skills and plugins that let agents work with Sanity content, schemas and best practices.

A set of agent skills for Spring Boot projects covering project generation, Spring Modulith verification, jSpecify, Java code review and applying Renovate PRs.

Allows Claude Code users to switch between and delegate tasks to ChatGPT, Cursor, OpenCode Zen, Antigravity, and Grok models within one session.

MCP server that indexes your repo across many languages and frameworks so agents get answers from the index, cutting input tokens when reviewing pull requests.

Provides a methodology and skills to build products with AI agents that remember, by turning documentation into a navigable knowledge graph.

A toolkit of three Agent Skills to mine workflows, personalize existing skills, and generalize personal skills for public sharing.

Provides reusable agentic loops as open-standard Agent Skills for tasks like autoresearch, data analysis, and code optimization.

An MCP server and Claude Code plugin that asks Codex, Gemini, Grok and OpenRouter models for second opinions or consensus reviews of plans and code.

A plugin of engineering-discipline skills for Claude Code, Codex and Gemini CLI covering research, quality gates, testing, deployment and evidence before claiming done.

Offers a collection of 23 agent skills and safety hooks for AI-driven software development across multiple coding agents.

Flompt is a visual AI prompt builder that lets users decompose prompts into a flowchart, edit them, and recompile into Claude-optimized XML.

Coder Eval is an agent-agnostic framework for evaluating and benchmarking AI coding agents and their skills using declarative YAML tasks and sandboxed execution.

codeArbiter provides an open-source governance layer and hard gates for AI coding agents to enforce tests, reviews, security checks, and durable project context.

A collection of on-demand skills for coding agents covering UI audits, typography, docs, PR review, releases and Next.js scaffolding.

Offers practical recommendations and plugins to enhance AI-assisted development workflows using Claude Code.

Generates paste-ready Power Apps Canvas App YAML from screenshots, mockups, or text descriptions directly within Claude Code.

An opinionated macOS bootstrap that sets up Claude Code and Codex with skills, plugins, rules, global CLAUDE.md/AGENTS.md and hardened dotfiles.

An Agent Skill that audits and, when authorized, removes test bloat, verification theater and speculative fallbacks while preserving real behavior.

Enables AI agents like Claude and Codex to query, monitor, and manage Unraid servers through GraphQL APIs and MCP tools.

Teaches AI coding agents to use TypeSafe AI's Jev for making typed decisions with calibrated confidence and leveraging prior art from community projects.

A set of skills that review specs, plans, architecture and branches with specialist agents, plus accessibility audits and a TDD-guarded small-fix mode.