by datadrivenconstruction · Agent Tool · ★ 538
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Flagged: spawns subprocesses. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 538 |
| Forks | 113 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 71/100 |
| Open Issues | 3 |
| Last Updated | 2026-11-03 |
| Created | 2025-06-19 |
| Platforms | claude-code, cli, python |
| Est. Tokens | ~18k |
English • Deutsch • Español • Français • Русский • 中文 • العربية cad2data — DDC converters for RVT, IFC and DWG files Turn CAD/BIM files into open, structured data — locally, offline, without CAD licences. .rvt / .rfa → GLB · glTF · OBJ · IFC4 · JSONL/CSV .dwg → Excel · CSV · JSONL · DXF · SVG <img src
These tools work well together with cad2data-Revit-IFC-DWG for enhanced workflows:
Looking for a cad2data-Revit-IFC-DWG alternative? If you're comparing cad2data-Revit-IFC-DWG with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
AutoCAD MCP server for AI agents (Claude, Cursor, any MCP client): 240+ tools to draw, edit and read DWG/DXF d
Exact B-Rep CAD in TypeScript, with a Claude Code plugin that lets agents write parts and check them on OpenCa
Open-source Revit MCP server: let Claude and other AI assistants read and edit BIM models, with human approval
BIMwright — AI-native Revit MCP server (Revit 2022–2027)
Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: