원클릭으로 Manus에서 모든 스킬 실행

ifc-extract

스타3

포크0

업데이트2026년 3월 22일 06:36

Extract data from IFC building models. Accepts element types (door, wall, window, slab, roof, etc.) and optional property filters. Translates natural language queries into CLI commands. Results saved to output/ for cross-validation.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

thebrownproject

thebrownproject/buildbrain

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

/ifc-extract — IFC Data Extraction

Extract building element data from IFC models. For full CLI command syntax, flags, type shorthands, and natural language translation tables, see /cli-tools.

Step 1: Find the IFC file

If no file path provided:

ls data/*.ifc 2>/dev/null

Multiple files → ask user. No files → tell user to place IFC file in data/.

Step 2: Run the extraction

Scripts are at skills/cli-tools/scripts/ifc_extract.py. Always include --save.

python skills/cli-tools/scripts/ifc_extract.py <file.ifc> <command> [args] --save

Use /cli-tools to look up the correct command for the user's request. Common patterns:

User says	Command
"show me all doors"	`list door --save`
"fire-rated doors"	`query door --property Pset_DoorCommon.FireRating --not-null --save`
"external walls"	`query wall --property Pset_WallCommon.IsExternal --value true --save`
"how many windows per level"	`quantities window --group-by storey --save`
"what's in this model"	`summary --save`
"data quality check"	`validate --save`

Step 3: Present results

Summarize key findings in plain language ("Found 47 doors, 12 fire-rated, 35 without")
Show a formatted table for first 10-20 elements
Highlight notable items: missing properties, null fire ratings, proxy elements
Never compute totals yourself — use quantities command
Confirm save location

Step 4: Offer follow-ups

After list door: "Filter for fire-rated doors? Check quantities per level?"
After summary: "Which element type to explore?"
After any extraction: "Run /pdf-extract to find the matching PDF schedule?"

Rules

LLMs never do arithmetic. Use quantities for counts, areas, volumes.
Null properties are normal. Export settings issue, not data error.
Always use --save for downstream use by /cross-validate and /report.

이 저장소의 다른 Skills

같은 저장소

cli-tools

thebrownproject/buildbrain

Reference manual for BuildBrain CLI tools (ifc_extract.py and pdf_extract.py). Shows all commands, flags, output formats, and type shorthands. Use this as a reference when working with IFC or PDF data.

2026-03-223

cross-validate

thebrownproject/buildbrain

Compare IFC model data against PDF drawing schedules. Reads saved extraction data from output/, identifies count mismatches, missing properties, and conflicting values. Generates Markdown discrepancy report with PASS/WARN/INFO flags.

2026-03-223

pdf-extract

thebrownproject/buildbrain

Extract schedules, text, and tables from PDF construction drawings. Can search for specific terms to find relevant pages. Results saved to output/ for cross-validation.

2026-03-223

report

thebrownproject/buildbrain

Generate formatted construction deliverables — QTO tables, element schedules, material takeoffs, compliance checklists. Reads extracted data from output/, uses quantities command for aggregates. Formats per Australian construction conventions.

2026-03-223

scan

thebrownproject/buildbrain

Scan IFC and PDF files to create a project inventory. Shows element counts, schedule locations, and data quality issues. Use when starting work on a new project or wanting an overview.

2026-03-223

name	ifc-extract
description	Extract data from IFC building models. Accepts element types (door, wall, window, slab, roof, etc.) and optional property filters. Translates natural language queries into CLI commands. Results saved to output/ for cross-validation.
allowed-tools	Bash, Read, Write, Grep
argument-hint	[file.ifc] [element-type] [--property NAME] [--value VALUE]

/ifc-extract — IFC Data Extraction

Extract building element data from IFC models. For full CLI command syntax, flags, type shorthands, and natural language translation tables, see /cli-tools.

Step 1: Find the IFC file

If no file path provided:

ls data/*.ifc 2>/dev/null

Multiple files → ask user. No files → tell user to place IFC file in data/.

Step 2: Run the extraction

Scripts are at skills/cli-tools/scripts/ifc_extract.py. Always include --save.

python skills/cli-tools/scripts/ifc_extract.py <file.ifc> <command> [args] --save

Use /cli-tools to look up the correct command for the user's request. Common patterns:

User says	Command
"show me all doors"	`list door --save`
"fire-rated doors"	`query door --property Pset_DoorCommon.FireRating --not-null --save`
"external walls"	`query wall --property Pset_WallCommon.IsExternal --value true --save`
"how many windows per level"	`quantities window --group-by storey --save`
"what's in this model"	`summary --save`
"data quality check"	`validate --save`

Step 3: Present results

Summarize key findings in plain language ("Found 47 doors, 12 fire-rated, 35 without")
Show a formatted table for first 10-20 elements
Highlight notable items: missing properties, null fire ratings, proxy elements
Never compute totals yourself — use quantities command
Confirm save location

Step 4: Offer follow-ups

After list door: "Filter for fire-rated doors? Check quantities per level?"
After summary: "Which element type to explore?"
After any extraction: "Run /pdf-extract to find the matching PDF schedule?"

Rules

LLMs never do arithmetic. Use quantities for counts, areas, volumes.
Null properties are normal. Export settings issue, not data error.
Always use --save for downstream use by /cross-validate and /report.