What makes engineering-drawing-parser notable?

1.2K downloads. Trust evidence available

How should engineering-drawing-parser be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

engineering-drawing-parser

EN: Extract structured information from engineering drawings — mechanical 2D drafts, P&IDs, electrical schematics, construction architectural/structural draw... Skill: engineering-drawing-parser Owner: boboy-j Summary: EN: Extract structured information from engineering drawings — mechanical 2D drafts, P&IDs, electrical schematics, construction architectural/structural draw... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-05-26T17:42:23.327Z | user Initial release of Engineering Drawing Parser. - Extracts structured data (BOM, dimensions, tolerances, title block, symbol

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 10, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.0release · observed May 26, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17ckg9br2p4k5kx6cr8fc4jz5852pah:engineering-drawing-parser

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-boboy-j-engineering-drawing-parser/snapshot"

Documentation

CLAWHUB

15,750 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: engineering-drawing-parser
description: |
  EN: Extract structured information from engineering drawings — mechanical 2D drafts, P&IDs, electrical schematics, construction architectural/structural drawings — into machine-readable BOM, dimension lists, tolerance tables, title-block metadata and symbol inventories. Supports DWG/DXF/PDF/image input. Use when the user provides a drawing and asks "解析图纸 / 抽 BOM / 读尺寸 / 出明细表 / parse drawing / extract BOM".
  中文：从工程图纸（机械二维图、P&ID 工艺管道仪表流程图、电气原理图、建筑结构施工图）中抽取结构化信息，输出 BOM 物料清单、尺寸表、公差表、标题栏元数据、符号清单。支持 DWG/DXF/PDF/图片输入。当用户提供图纸并要求"解析/抽 BOM/读尺寸/出明细"时触发。
version: 1.0.0
metadata:
  openclaw:
    emoji: "📐"
    homepage: https://github.com/openclaw-skills/engineering-drawing-parser
    requires:
      bins:
        - python3
    envVars:
      - name: DRAWING_DOMAIN
        required: false
        description: Drawing domain hint, one of `mechanical|piping|electrical|civil`. Auto-detected if unset.
      - name: DRAWING_STANDARD
        required: false
        description: Standard hint, one of `GB|ISO|ANSI|JIS|DIN`. Defaults to GB for Chinese drawings.
      - name: DRAWING_OCR_LANG
        required: false
        description: OCR language hint, e.g. `chi_sim+eng`. Defaults to auto.
---

# Engineering Drawing Parser · 工程图纸智能解析

> Turn a 1:50 scale engineering drawing into a clean structured dataset in under 2 minutes — BOM, dimensions, tolerances, title block, and every visible symbol — all linked back to coordinates on the source page.
>
> 2 分钟把工程图纸变成结构化数据：BOM、尺寸、公差、标题栏、符号清单，每一项都能定位回原图坐标。

---

## 🎯 When to Use · 何时使用

**Trigger keywords (中文):** 解析图纸、读图纸、抽 BOM、出明细表、尺寸清单、公差清单、标题栏、装配图、零件图、施工图、P&ID、电气原理图

**Trigger keywords (EN):** parse drawing, extract BOM, read dimensions, tolerance list, title block, drawing OCR, P&ID parsing, schematic extraction

**Supported drawing types:**

| 类别 / Type | 子类 / Subtype | 支持元素 |
|---|---|---|
| 机械 Mechanical | 零件图、装配图、爆炸图 | 尺寸、公差、表面粗糙度、几何公差、BOM、标题栏 |
| 管道工艺 P&ID | 工艺流程、PFD/PID | 设备、管线、阀门、仪表、tag 号、介质 |
| 电气 Electrical | 原理图、接线图、系统图 | 元器件、网络标号、回路、参数 |
| 建筑结构 Civil | 平面、立面、剖面、节点 | 轴网、构件、标高、配筋、说明 |

**Supported formats:** DWG, DXF, PDF (vector or scanned), PNG/JPG/TIFF (scanned)

**Do NOT use when:**
- Drawing is a freehand sketch with no standardized notation
- File is a 3D model (STEP/STL/IGES) — use a CAD-native tool instead
- User wants the parser to redesign or modify the drawing

---

## 📋 Parsing Pipeline · 解析流程

### Step 1: Format dispatch · 格式分发

```bash
python3 scripts/dispatch.py --input <file> --out /tmp/raw_geom.json
```

- DWG/DXF → vector geometry via `ezdxf` (bundled)
- Vector PDF → vector geometry via `pdfminer`
- Scanned PDF / image → raster pipeline (OCR + symbol detector)

### Step 2: Region segmentation · 区域分割

`scripts/segment_regions.py` partitions every drawing into 5 zones:
- Title block (右下角标题栏)
- BOM / parts list (明细栏)
- Main view region (主视区)
- Notes & legends (技术要求、图例)
- Border & frame (图框)

This dramatically improves downstream extraction p

examples/README.md

# Examples · 示例

`sample_drawing.txt` is a text-layer dump of a mechanical drawing's title block + BOM + dimensions, the format produced by `pdfplumber` or `ezdxf` for vector PDFs/DWGs.

```bash
python3 ../scripts/run_pipeline.py --input sample_drawing.txt --domain mechanical --standard GB
```

Expected: title block 6 fields, BOM 3 rows, dimensions list with H7/g6 fit and φ120±0.05.

knowledge/README.md

# Knowledge Bundle

This directory ships domain reference data used by the skill scripts.

For the initial public release we keep only the schema / placeholder files
here so the bundle stays small and reviewable. Full reference tables (ICD-10
master, drug aliases, LOINC mapping, industry medians, curriculum codes,
symbol libraries, etc.) can be added incrementally via subsequent releases
without breaking the published API.

Add your own data by dropping CSV/JSON files into this directory and
pointing the relevant environment variable in `SKILL.md` to override the
bundled defaults.

README.md

# Engineering Drawing Parser · 工程图纸智能解析

[English](#english) | [中文](#chinese)

---

## English

Extract structured info from engineering drawings (mechanical, P&ID, electrical, civil) into BOM, dimensions, tolerances, title block, symbol inventory.

### Quick Start

```bash
python3 scripts/run_pipeline.py \
  --input part.dwg --domain mechanical --standard GB \
  --output part_parsed.json
python3 scripts/render_preview.py --input part_parsed.json --pdf annotated.pdf
```

### Features

- 📐 4 domains: mechanical, piping (P&ID), electrical, civil
- 📁 Formats: DWG, DXF, PDF (vector or scanned), PNG/JPG
- 📋 BOM extraction with merged-cell support
- 🔢 Dimension + tolerance (ISO 1101 geometric tolerance)
- 🔍 Symbol recognition (ISA-5.1, IEC 60617, GB)
- 📍 Every output linked back to drawing coordinates

### License

MIT-0

---

## Chinese

从工程图纸（机械/管道/电气/建筑）抽取 BOM、尺寸、公差、标题栏、符号清单。

### 快速开始

```bash
python3 scripts/run_pipeline.py \
  --input 零件.dwg --domain mechanical --standard GB \
  --output 零件_解析.json
python3 scripts/render_preview.py --input 零件_解析.json --pdf 标注图.pdf
```

### 功能

- 📐 4 大类：机械、管道、电气、建筑
- 📁 格式：DWG / DXF / PDF / 图片
- 📋 BOM 抽取，支持合并单元格
- 🔢 尺寸 + 公差（ISO 1101 几何公差）
- 🔍 符号识别（ISA-5.1、IEC 60617、GB 标准）
- 📍 每项输出可定位回原图坐标

### 协议

MIT-0

_meta.json

{
  "ownerId": "kn7ae6m5fzwqs7fmdmh97gr1yh82m2py",
  "slug": "engineering-drawing-parser",
  "version": "1.0.0",
  "publishedAt": 1779817343327
}

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.