Browse the library

A CLI that A/B tests SKILL.md, .cursorrules, CLAUDE.md and system prompts with blind grading to tell whether they help, do nothing or harm.

This project provides 54 production architecture rules as drop-in files for Claude Code and Cursor, enabling AI agents to follow clean code and best practices for FastAPI, Next.js, and Go projects.

This Claude Code plugin allows agents to build and manage code-native integrations and custom connectors for the Prismatic.io platform through conversational commands.

This tool generates custom Cursor AI rules from GitHub repositories or local codebases, providing codebase-specific intelligence for better code suggestions and reduced AI hallucinations.

This Claude Code plugin enables autonomous software development through a six-phase workflow (Explore, Research, Plan, Act, Validate, Compound) with classifier-driven routing and a self-improving memory system.

Provides an installable AI coding workflow for agents like Claude Code and Cursor, focusing on risk-based routing, scoped sub-agents, and evidence-backed completion.

Routes tasks to specialized AI agents and manages their independent work within Codex sessions, allowing the main task to progress uninterrupted.

This Claude Code plugin orchestrates AI agents, using a top-tier model as a tech lead for high-level decisions and cheaper subagents for routine tasks, optimizing token usage.

This Claude Code plugin provides an AI-powered running coach that generates personalized training plans, analyzes workout data, and offers evidence-based coaching guidance.

Enables AI agents to recursively break down tasks into parallelizable subtasks and execute them without conflicts using a directory isolation protocol.

Provides strong frontend design judgment and guidance as a single skill for AI agents, promoting coherent visual direction and practical UI decisions.

Updates AI coding agents with current technology knowledge, syntax, and APIs to overcome LLM knowledge cutoff limitations, ensuring accurate and modern code generation.

Turns architectural decisions and ADRs into deterministic guardrails that keep coding agents and CI from drifting away from your architecture.

This tool analyzes your AI coding sessions to create a personalized, persistent memory profile for your agent, improving its understanding of your preferences and workflow.

This plugin uses seven adversarial AI agents to refine your resume and cover letter against job descriptions, helping you proactively identify and fix weaknesses before recruiters do.

This skill teaches AI coding agents to write and debug Zod v4 schemas correctly, preventing common errors and following best practices for schema design and type safety.

A curated list showcasing modern Cursor Rules configurations in MDC format, providing examples for various testing frameworks and development scenarios.

A Claude Code plugin that guides users through an 8-step pipeline to complete Korean job application self-introductions, from company research to final review.

Enables AI agents to deploy code to any cloud provider using plain English prompts, automatically configuring infrastructure like servers, DNS, and SSL certificates.

An Astro x Strapi starter template that comes with pre-configured AGENTS.md, Agent Skills, and Cursor rules for an AI-native web development workflow.

cursor-rules

Kabi10

Provides a CLI tool that scans project dependencies and auto-generates tailored AI editor rules as AGENTS.md or .mdc files for Cursor, Copilot, Codex, and Claude Code.

Augments Claude Code with 109 specialized components, including agents, commands, and skills, for deep reasoning, autonomous development loops, and Git automation.

A comprehensive Cursor Skill system comprising 95 skills, 32 rules, and 18 subagents designed to enable AI to autonomously judge, execute tasks, and self-evolve from experience.

Provides workflows, prompts, and a LaTeX template for Claude Code, Cursor, and Codex to review and format Tianjin University undergraduate theses.