Lattice

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

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:

• Skills over prompts — versioned, team-owned skill files in the repository beat personal prompts on one developer's machine
• Composability over monoliths — small single-purpose skills that combine into workflows beat one instruction document that tries to cover everything
• Living context over static config — the .lattice/ folder grows smarter with every feature cycle rather than being configured once and forgotten

The Three Tiers

Tier	Purpose
Atoms	Single-principle guardrails — clean code, architecture, DDD, secure coding, test quality, design-first, and more
Molecules	Multi-step workflows that compose atoms — design, implement, refactor, fix, review
Refiners	Guided interviews that produce project-specific standards, customizing how atoms behave for your team

See How It Works for the full skill inventory and mechanics.

The Pipeline

Skills form a delivery lifecycle: lattice-init → design-blueprint → code-forge → review, with refactor-safely and bug-fix covering structural and defect-driven work. Each stage consumes and produces artifacts in .lattice/, growing the living context layer.

Getting Started

1. Install Lattice — choose the path that fits your setup:

   Option A — Claude Code plugin (also works in Cursor — reads Claude Code skills automatically)

   /plugins marketplace add techygarg/lattice
   /plugins install lattice
   /reload-plugins
   

   Option B — Clone and install locally (any AI tool)

   git clone https://github.com/techygarg/lattice.git
   cd lattice
   ./tools/install.sh /absolute/path/to/your/skills/folder

   Pass the skills directory for your tool: ~/.claude/skills/ for Claude Code, .cursor/skills/ for Cursor, or any tool's skills folder.

   Try it immediately. The repo includes sample/ — a realistic .NET 8 User Service spec with requirements, domain concepts, and constraints already written. Copy the sample/ folder contents into any empty directory and follow the steps below.

2. Run /lattice-init in your AI tool's chat — scans the project, suggests refiners in priority order, creates .lattice/config.yaml. All skill commands (/lattice-init, /design-blueprint, etc.) are typed in the AI chat, not the terminal.

3. Design — /design-blueprint walks through five progressive design levels before any code is written.

4. Implement — /code-forge generates implementation from the approved blueprint, applying all quality atoms.

5. Review — /review audits the change and persists insights into .lattice/ for the next cycle.

Learn More

• Origin Story — why Lattice exists, how five collaboration patterns became an installable framework, and the design philosophy behind it
• How It Works — full skill inventory, composability mechanics, atoms/molecules/refiners in depth, the pipeline
• Practical Guide — scenario-driven Q&A: getting started, customization, workflow, team usage, troubleshooting
• Configuration Reference — every .lattice/config.yaml key documented
• Framework Intelligence — verification passes, feedback loops, AI compliance techniques
• Collaborative Judgment — why AI should ask on genuine judgment calls and how it works at runtime
• The Article Series — the five collaboration patterns Lattice operationalizes (martinfowler.com)

License

MIT