Architecture logo

Architecture

Community
techygarg
architecture

Enforce architectural rules when generating or modifying code, and validate proposed designs before approval (design mode). Defaults to clean architecture; supports any architecture style via the architecture-refiner. Validates layer responsibilities, dependency direction, and structural constraints using the loaded architecture rules. Use when generating code, reviewing architecture, creating new files, or when the user mentions 'architecture', 'layers', 'structure', 'dependency rules', 'hexagonal architecture', 'ports and adapters', 'modular monolith', or 'onion architecture'. Also use when reviewing generated code for structural compliance.

Overview

Publishertechygarg
Repositorylattice
Skill namearchitecture
Stars
208
Forks
16
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by techygarg on GitHub. Read the source before you install it.

Installation

Install the Architecture AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/techygarg/lattice/tree/main/skills/architecture
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/techygarg/lattice.git /tmp/lattice
mkdir -p .claude/skills
cp -r /tmp/lattice/skills/architecture .claude/skills/architecture
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Architecture in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Architecture on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Architecture is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Architecture

Config Resolution

Step 1 — Determine mode:

  1. Read .lattice/config.yaml in repo root
  2. Check architecture_mode key
    • If architecture_mode: custom → custom mode
    • If absent, or other value → clean architecture mode (default)

Step 2 — Load enforce rule:

  • Clean architecture mode → Read ./references/clean-architecture.md for enforce instruction (Self-Validation Checklist, Anti-Pattern Scan, Ambiguity Signals, structural principles)
  • Custom mode → Read ./references/custom-architecture.md for enforce instruction

Step 3 — Load architecture content:

  • Clean architecture mode:

    1. Check paths.architecture in .lattice/config.yaml for a custom document path.
    2. If a document exists at that path → read it and check its YAML frontmatter for mode:
      • mode: overlay (or no mode field): read ./references/clean-architecture-defaults.md first, then apply the custom document's sections on top. Sections match by exact heading — a custom section replaces the matching default; new sections append after the defaults.
      • mode: override: the custom document takes full precedence. It must be comprehensive.
    3. If the path is configured but no document exists at it → tell the user which configured path is missing, then read ./references/clean-architecture-defaults.md.
    4. If there is no configured path → read ./references/clean-architecture-defaults.md.
  • Custom mode:

    1. Check paths.architecture in .lattice/config.yaml for team architecture doc
    2. If found → read it. Sole reference — no default.
    3. If not found → surface: "No architecture document found. Run /architecture-refiner and select your architecture style to define your team's standards."

Step 4 — Language adaptation:

If paths.language_idioms is set in the config and the document exists, read its "Dependency Management" section and adapt dependency direction enforcement to language idioms (e.g., Go interface-at-consumer, Java DI containers, Rust trait bounds). Language idioms take precedence over pseudocode defaults.

Enforcement

STOP after generating each component. Read the Self-Validation Checklist and Anti-Pattern Scan from the loaded enforce rule (clean-architecture.md or custom-architecture.md) and apply them.

Project-specific checks: If architecture content doc (loaded in Step 3) contains a Validation Checklist section (§6), apply those checks as additional project-specific validation after the enforce rule checklist.

Design Mode

When invoked during design — no code is being written; a planning molecule is validating a proposed design artifact — apply the same enforce rule as a forward-looking check:

  1. Take the proposed artifact (component list, layer assignment, data flow, or contract set) as the unit of validation.
  2. Evaluate it against the Self-Validation Checklist and Anti-Pattern Scan from the loaded enforce rule, plus the project-specific Validation Checklist if present — before the artifact is presented for user approval.
  3. Report violations as concrete findings on the artifact ("Component X reaches from layer A to layer C, skipping B"), not generic advice. Resolve them through the design.
  4. STOP: do not skip checklist evaluation on the grounds that no code exists yet — the proposed structure is what gets validated.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Architecture AI skill do?

Enforce architectural rules when generating or modifying code, and validate proposed designs before approval (design mode). Defaults to clean architecture; supports any architecture style via the architecture-refiner. Validates layer responsibilities, dependency direction, and structural constraints using the loaded architecture rules. Use when generating code, reviewing architecture, creating new files, or when the user mentions 'architecture', 'layers', 'structure', 'dependency rules', 'hexagonal architecture', 'ports and adapters', 'modular monolith', or 'onion architecture'. Also use wh...

Why use Architecture on TypingMind?

Because you install it once and use it with any model. Architecture is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Architecture in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/techygarg/lattice/tree/main/skills/architecture. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Architecture?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Architecture?

As many as you like. As long as a model supports skills, you can use Architecture with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Architecture AI skill free?

Yes. It is published on GitHub by techygarg under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇