AlpacaLabsLLC/skills-for-architects

Claude Code skills for architecture, real estate, and workplace strategy. Type /skill-name and go.

What it solves

Architecture Studio is a local-first framework designed for architecture, engineering, and construction (AEC) firms to build, govern, and share AI-assisted workflows. It solves the problem of integrating AI into professional practice by providing a governance layer, persistent memory for studios and projects, and a structured way to create and manage custom skills and agents without compromising data privacy or professional boundaries.

How it works

The system operates as a plugin (as) for Codex and Claude Code. It separates maintained plugin capabilities from user-owned workspaces.

  • Governance and Memory: It uses a system of rules (e.g., for units, code citations, and professional disclaimers) and linked plain files to preserve studio and project context.
  • Extension Points: Firms can create their own "skills" (procedures) at three levels: bundled reference skills (upstream), studio skills (firm-wide), and project skills (client- or project-specific).
  • Orchestration: On Claude Code, it provides native agents (like the site-planner or sustainability-specialist) that orchestrate multiple skills to complete complex tasks.
  • Local-First: All studio and project records remain as local files in the user's workspace, ensuring that plugin updates do not overwrite firm-specific data.

Who it’s for

It is built for architecture firms and AEC professionals who want to leverage AI for tasks such as site planning, zoning analysis, sustainability research, and project management while maintaining professional standards and data control.

Highlights

  • Cross-Platform Support: Works with both Codex and Claude Code.
  • AEC-Specific Tooling: Includes bundled skills for NYC zoning, environmental analysis, EPD parsing, and CSI outline specifications.
  • ** uma own custom skills via /as:skill-maker.
  • Professional Governance: Enforces professional disclaimers and CSI formatting through hooks and rules.
  • Local-First Memory: Maintains persistent project and studio context through a structured local file system.

Related

  • Project
    steipete/agent-scripts

    A centralized management system for shared AI agent instructions, reusable skills, and portable helper scripts across multiple local workspaces.

  • Project
    ZhixiangLuo/10xProductivity

    A local-first stack that turns coding agents into personal AI assistants for work by leveraging existing user permissions and tool access to bypass corporate IT constraints.

  • Project
    AVIDS2/memorix

    Memorix is a Node.js library that adds a local‑first, searchable memory store to any AI coding assistant. It persists facts, design rationales, and Git‑derived insights in a SQLite database, exposing them via MCP, a CLI, and an optional web UI. By installing a single `memorix setup --agent <name>` command, dozens of agents (Claude Code, Codex, Copilot CLI, Cursor, Gemini CLI, etc.) can share the same project‑scoped memory, enabling smoother handoffs, better context retention, and multi‑agent orchestration.

  • Project
    openclaw/agent-skills

    A centralized library of shared workflows and helper scripts for AI coding agents to ensure consistent behavior across multiple repositories.

  • Project
    awslabs/aidlc-workflows

    A harness-neutral implementation of the AI-Driven Development Life Cycle (AI-DLC) that turns AI agents into a structured, gated, and verifiable software engineering workflow across multiple AI IDEs and CLIs.