BIM Classification AI

Auto-suggests standard classification codes (UniFormat, MasterFormat) for BIM elements from their name, category and properties.

Data & AnalyticsIntermediate★ 306⑂ 79AI score 6/10Last updated: Aug 22, 2026

What it does

Takes BIM element data exported from Revit/IFC (id, name, category, properties) and suggests UniFormat II and CSI MasterFormat codes.
Scores each candidate with a keyword/category confidence value (0–1), returns the top 5 suggestions and picks the best one as the default.
Includes a built-in mapping table for common Revit categories (Walls, Ducts, Structural Columns, Windows, Sprinklers, ...).
Supports batch classification over a pandas DataFrame, Excel export, and a summary of classification rate and high-confidence rate.

Who it's for

BIM managers and coordinators auditing model data quality and missing classification codes.
Cost estimators and QTO specialists who need elements mapped to cost databases.
AEC data engineers automating what used to be manual code assignment across thousands of elements.

Examples

Single element — classify "Concrete Floor Slab Level 2" (category Floors, material Concrete) and get B1010 Floor Construction with a confidence score.
Batch run — read bim_elements.xlsx, append UniFormat/MasterFormat columns for every element, and write classified_elements.xlsx.
QA report — call get_summary() to report "classification rate 87%, high confidence 62%" in a model-quality deliverable.

Caveat: OmniClass, Uniclass and CWICR exist only as enum values with no code tables, and the CWICR mapping example references an undefined helper — you must supply those yourself.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/HEAD/1_DDC_Toolkit/BIM-Analysis/bim-classification-ai/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the 1_DDC_Toolkit/BIM-Analysis/bim-classification-ai folder from the GitHub repo datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction into my ~/.claude/skills/bim-classification-ai/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction.git /tmp/ddc && mkdir -p ~/.claude/skills && cp -r /tmp/ddc/1_DDC_Toolkit/BIM-Analysis/bim-classification-ai ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal (PowerShell or Git Bash on Windows).
Verify Python and install dependencies: python3 --version, then pip install pandas openpyxl.
Clone the repository: git clone https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction.git
Copy the skill into Claude's skills folder: mkdir -p ~/.claude/skills && cp -r DDC_Skills_for_AI_Agents_in_Construction/1_DDC_Toolkit/BIM-Analysis/bim-classification-ai ~/.claude/skills/
Restart Claude Code and prompt something like "Classify these BIM elements with UniFormat codes".
Prepare your input as an Excel/CSV file with element_id, name and category columns so batch classification works out of the box.

View source on GitHub ↗License: MIT