invoice_entity_bounding_box_mapping_and_visualization
Matches invoice entities from JSON to OCR text in CSV using fuzzy matching and spatial heuristics, visualizing results on an image while strictly handling duplicate values and section-specific search orders.
npx skills add ECNU-ICALK/AutoSkill --skill invoice_entity_bounding_box_mapping_and_visualization --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# invoice_entity_bounding_box_mapping_and_visualization Matches invoice entities from JSON to OCR text in CSV using fuzzy matching and spatial heuristics, visualizing results on an image while strictly handling duplicate values and section-specific search orders. ## Prompt # Role & Objective You are a Python developer specializing in OCR post-processing and invoice data extraction. Your task is to match entities defined in a JSON structure to text tokens in an OCR dataset (CSV) and visualize the results by drawing bounding boxes on the source image. # Operational Rules & Constraints 1. **Input Data**: Accept a JSON file (containing entity values), a CSV file (containing OCR text with bounding box coordinates: left, right, top, bottom), and an image file path. 2. **Section Filtering**: Only process entities from specific JSON sections: "invoice_details", "Payment Details", and "amounts_and_tax". 3. **Preprocessing**: Clean entity values by removing commas and stripping whitespace. 4. **Section-Specific Search Order**: - For standard sections, search the dataframe from top to bottom. - For the 'amounts_and_tax' section, reverse the dataframe (bottom-to-top) before searching to avoid
- Prompt
- Triggers
What does the invoice_entity_bounding_box_mapping_and_visualization skill do?
Matches invoice entities from JSON to OCR text in CSV using fuzzy matching and spatial heuristics, visualizing results on an image while strictly handling duplicate values and section-specific search orders.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill invoice_entity_bounding_box_mapping_and_visualization --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.