techygarg/lattice

README preview

# Lattice

<p align="center">
  <img src="docs/image/logo.png" alt="lattice" width="500" height="500">
</p>

Composable AI skills that teach assistants structured thinking — design-first, context-aware, and architecture-guided.

[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
[![Claude Code](https://img.shields.io/badge/Claude_Code-plugin-blue.svg)](https://claude.ai/marketplace)
[![Cursor](https://img.shields.io/badge/Cursor-compatible-blue.svg)](https://cursor.com)
[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](https://github.com/techygarg/lattice/blob/main/CONTRIBUTING.md)
[![martinfowler.com](https://img.shields.io/badge/martinfowler.com-article_series-red.svg)](https://martinfowler.com/articles/reduce-friction-ai/)
[![StarMapper](https://starmapper.bruniaux.com/api/badge/techygarg/lattice)](https://starmapper.bruniaux.com/techygarg/lattice?utm_source=badge&utm_medium=readme&utm_campaign=stargazer-map)

## What is Lattice?

AI coding assistants jump straight to code, silently make design decisions, forget constraints mid-conversation, and produce output nobody reviewed against real standards. Lattice fixes this with composable skills in three tiers — atoms, molecules, refiners — that embed battle-tested engineering disciplines plus a living context layer that accumulates your project's standards, decisions, and review insights across every feature cycle.

Three principles guided Lattice's design:

View full repository on GitHub →