~/agent-config

Agent setup, without the guesswork

Skills, rules, MCP configs, hooks, and starter kits you can copy into Cursor, Claude Code, Codex, Windsurf, Cline, or Copilot. Pick what you need, grab the command, move on.

42 resources · 6 kits · 6 agents

Browse by type

Starter kits

View all
Kit5 resources

Backend API Kit

Everything an agent needs to design and ship a typed backend API — contract-first design, a sound database schema, a Postgres MCP for live schema access, a strict TypeScript rule, and a security pass before you merge.

Cursor, Claude Code · 5 steps

Open →
Kit5 resources

Claude Code Power User

A power setup for Claude Code — design-first brainstorming and planning, a persistent memory graph, structured sequential reasoning, and clean conventional commits for a tidy history.

Claude Code · 5 steps

Open →
Kit4 resources

Essential Cursor Setup

Minimum viable agent configuration for Cursor — brainstorming and writing-plans for design-first work, UI/UX Pro Max for visual quality, and a base rule for consistent behavior.

Cursor · 4 steps

Open →
Kit4 resources

MCP Developer Stack

Common MCP servers for day-to-day development — GitHub for repo context, filesystem for local files, and Playwright for browser verification.

Cursor, Claude Code, Windsurf, Cline · 4 steps

Open →
Kit6 resources

Next.js Full-Stack Agent

A complete agent stack for Next.js development — planning skills, framework expertise, UI components, and design guidelines.

Cursor, Claude Code, Windsurf, Cline, Codex, GitHub Copilot · 6 steps

Open →
Kit5 resources

Quality & Testing Kit

Turn your agent into a disciplined engineer — test-driven development, a systematic debugging loop, safe refactoring, a built-in code reviewer, and a format-on-save hook so every change lands clean.

Cursor, Claude Code · 5 steps

Open →

Popular resources

View all
Skill

API Design

Designs consistent REST and RPC APIs — resource naming, status codes, pagination, versioning, and error shapes. Produces an OpenAPI-friendly contract.…

#api #rest #design +1

Cursor, Claude Code, Windsurf +3

Skill

Brainstorming

Explores user intent, requirements, and design before implementation. Required before any creative work — features, components, or behavior changes.

#planning #design #spec +1

Cursor, Claude Code, Windsurf +3

Skill

Code Review

Reviews diffs for correctness, security, and style before you open a PR. Flags risky changes, missing tests, and edge cases the author may have missed…

#review #quality #pr +1

Cursor, Claude Code, Windsurf +3

MCP

Filesystem MCP

Official MCP server for controlled local file access. Set allowed directories in the args — only paths listed here can be read or written by the agent…

#mcp #filesystem #local +1

Cursor, Claude Code, Windsurf +2

Details
Skill

Frontend Design

Comprehensive frontend design patterns and visual polish guidance for building distinctive, production-grade interfaces.

#design #frontend #ui +1

Cursor, Claude Code, Windsurf +3

MCP

GitHub MCP

Lets your agent read issues, PRs, and repo metadata from GitHub. Add a personal access token with repo scope to .cursor/mcp.json (or your agent's MCP…

#mcp #github #git +2

Cursor, Claude Code, Windsurf +2

Details

~/learn-ai

Learn how AI works

Plain-English guides on language models, tokens, and agents — so the tools in the catalog actually make sense.

All posts
Fundamentals1 min read

Tokens, Context Windows, and Why Prompts Matter

Every model has a finite short-term memory measured in tokens. Understanding it explains why prompts get "forgotten," why long chats drift, and how to keep answers sharp.

Jul 13, 2026

Read →
Fundamentals2 min read

How Large Language Models Actually Work

A plain-English tour of what happens between your prompt and the model's answer — prediction, training, and why LLMs sometimes get things confidently wrong.

Jul 10, 2026

Read →