An automated utility to sort supply chain document packages, extract images, run OCR, verify dimension tolerance consistency, and generate comprehensive quality review reports.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install auto-dimension-report-skill-en
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install auto-dimension-report-skill-en using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is AutoDimensionReport?
The AutoDimensionReport skill is a comprehensive automation pipeline designed to streamline supply chain document verification, quality assurance, and APQP inspection package reviews. By converting incoming PDFs to editable formats, sorting files, and extracting embedded images, this utility eliminates the tedious manual labor of parsing unstructured supplier records. It integrates deeply with AI pipelines to establish complete traceability and reduce human errors in high-stakes manufacturing and engineering audits.
At its core, the tool features automated dimension inspection verification, comparing measured sheet values against standard tolerances to catch false pass claims in measurement reports. When running within the Openclaw Skills ecosystem, AutoDimensionReport acts as an intelligent assistant that automatically extracts text clues like stamps, official seals, and signatures, providing human operators with a pre-analyzed, reliable, and secure document verification environment.
AutoDimensionReport Use Cases
- Supplier and Quality Document Review: Instantly organize scattered PDF, Word, and Excel files into a structured three-layer workspace for simplified auditing.
- Dimension Inspection Verification: Validate consistency between actual measurements and standard tolerances to catch false OK or Pass claims in measurement reports.
- Image and Seal Extraction: Batch extract images, stamp pages, or scanned documents to inspect signature validity and legal indicators.
- Traceable Conversions: Transform unformatted PDFs into clean DOCX files while embedding direct image references for manual audit pathways.
How AutoDimensionReport Works
- Confirm Scope: Identify the input directory and determine processing requirements (OCR, table validation, or full reporting).
- Convert & Sort: Run the extraction script to convert PDFs to DOCX, copy relevant Excel files, and organize assets into output and image folders.
- OCR Recognition: Process extracted images to perform OCR and output structured text files inside the imagetomd workspace.
- Tolerance Verification: Analyze data tables to check if the recorded measurements align mathematically with target tolerance ranges and detect non-standard terminology.
- Report Generation: Compile findings into a unified ReviewReport.md detailing anomalies, missing metadata fields, and detected stamps or signatures.
AutoDimensionReport Setup
Install dependencies using uv or pip, then run the sequential pipelines. Configure the OCR engine inside the scripts/config.json file prior to execution.
# Step 1: Execute Document Sorting & Image Extraction
uv run python "scripts/task_convert_extract.py" --dir "/path/to/task-folder"
# Step 2: (Optional) Execute Image OCR Recognition
python "scripts/image_to_markdown.py" --dir "/path/to/task-folder" --model "paddleocr-ppocrv5-server"
# Step 3: (Optional) Run Tolerance & Judgement Verification
python "scripts/extract_verify_data.py" --dir "/path/to/task-folder"
# Step 4: Generate the Final Review Report
python "scripts/generate_report.py" --dir "/path/to/task-folder" --format md
AutoDimensionReport Data Schema & Taxonomy
This skill generates a clear, three-layer trace workspace under the provided task folder:
| Directory / File | Description |
|---|---|
output/ |
Contains converted .pdf.docx, copied source sheets (.xlsx, .xlsm), and _ImageIndex.xlsx. |
image/ |
Subdirectories grouped by source file containing all extracted media/drawings. |
imagetomd/ |
Structured Markdown files holding OCR-recognized text per image asset. |
ReviewReport.md |
The final aggregated analysis, flagging tight-limits, precision gaps, and seal locations. |
AutoDimensionReport Advanced Features
- Advanced Column Override Parameters: Customize Excel scanning layouts via CLI arguments (e.g., specifying custom sequence, item, tolerance, and judgment rows/columns).
- Dual-Image Indexing: Automatically maintains embedded visual assets alongside clean markdown reference points to prevent traceability breaks.
- Dynamic Fallbacks: Gracefully falls back to local Python OCR scripts if primary Herdsman HTTP APIs encounter timeouts or network limits.
- Deep Data Audits: Uncovers hidden quality risks including precision inconsistencies, bias anomalies, and OK-only filling patterns in supplier sheets.
- Environment Integrations: Configure environment variables such as
HERDSMAN_BASE_URLorHERDSMAN_OCR_TRANSPORTfor flexible cloud or local hosting setups.
SKILL.md
Loading
Related Openclaw Skills
Herdsman Skill
Herdsman Skill is an integration package that exposes local LLMs, TTS, ASR, OCR, and image generation capabilities to external agent platforms.
RAGFlow Workbench
An end-to-end RAG platform workbench for Windows to automate Docker verification, admin bootstrapping, knowledge base CRUD, and parsing lifecycles.
CET Preparation Skill
An advanced, interactive AI agent skill for CET-4 and CET-6 preparation featuring adaptive simulations, instant diagnostic feedback, and structured study planning.
Tech News Brief AI Agent
An automated AI agent skill designed to discover, fetch, clean, summarize, and deliver daily tech and semiconductor news directly to your inbox.
License Audit
An automated multi-language license compliance scanner powered by Trivy that identifies high-risk dependencies and exports reports in various formats.
Agnes Image and Video Generation Skill
An advanced AI generation skill that leverages Agnes AI's models to create, edit, and synthesize high-resolution images and videos seamlessly.
Featured*
