CommunityProductivity & Collaborationgithub.com

ArchSightLabs/archsight-aios

Building-industry AI agent skills for BIM, IFC, RAG, GraphRAG, project evidence work, code review, and runtime governance.

What is archsight-aios?

ArchSightLabs/archsight-aios is a comprehensive suite of AI agent skills, workflows, and multi-agent toolkits specifically designed for building industry knowledge workers and AI development teams. The skill focuses on key domains including Building Information Modeling (BIM), Industry Foundation Classes (IFC), Retrieval-Augmented Generation (RAG), GraphRAG, project evidence management, code review, and runtime governance. It provides a structured framework for integrating AI agents into construction and architecture workflows, enabling tasks such as intelligent document processing, automated compliance checks, and collaborative design review. The toolkit is platform-agnostic and compatible with major AI agent systems like Claude Code, Cursor, and Codex, leveraging markdown-based skill definitions to encapsulate domain-specific prompts, tools, and evaluation metrics. By combining domain expertise with agent orchestration, archsight-aios helps reduce manual overhead in building projects, improve accuracy in data retrieval and analysis, and maintain governance over AI-assisted processes.

Works with~Claude Code~Codex CLI~Cursor
npx skills add ArchSightLabs/archsight-aios

Installed? Explore more Productivity & Collaboration skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

What does archsight-aios do?

Building-industry AI agent skills for BIM, IFC, RAG, GraphRAG, project evidence work, code review, and runtime governance.

This skill provides a comprehensive set of AI-powered capabilities for building industry professionals and AI research teams. It supports:

  • BIM (Building Information Modeling): Automate model checking, clash detection, and data extraction from BIM models.
  • IFC (Industry Foundation Classes): Parse and manipulate IFC files for interoperability and analysis.
  • RAG (Retrieval-Augmented Generation): Enhance AI answers with domain-specific building and construction knowledge.
  • GraphRAG: Leverage knowledge graphs for more structured and context-aware retrieval.
  • Project Evidence Work: Collect, organize, and verify project documentation and compliance evidence.
  • Code Review: Automate review of code and configuration files for building software and agent workflows.
  • Runtime Governance: Monitor and enforce policies on AI agent actions during execution.

Each component is designed as a modular, self-contained skill that can be integrated into your existing AI agent pipelines. The toolkit is compatible with popular agent platforms including Claude Code, Cursor, and Codex.

Getting Started

  1. Clone this repository or copy the skill definition into your agent's skill directory.
  2. Configure environment variables as needed (see individual component docs).
  3. Invoke skills via agent instructions or tool calls.

Example Usage

# Example: Query a BIM model using the BIM skill
agent run --skill bim-check --model project.ifc --output report.md

Contributing

Contributions are welcome! Please see the CONTRIBUTING.md file for guidelines.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Related Skills