agentleFS
NexaiGuyNexaiGuy/nex-ai-skills/skills/nex-datasheet-extractor/SKILL.md

nex-datasheet-extractor

Skill1 starsChanged 15 days agoMITView on GitHub

Extracts structured electrical specs, package data, and compliance status from component datasheet PDFs. Use when: Convert PDF datasheets into structured JSON or CSV rows; Identify electrical constraints like voltage and temperature ranges; Extract package and pin count data for footprint assignment.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Only works on PDFs with a text layer.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Nex Datasheet Extractor

Free skill by Nex AI. This file is the public guide from Agensi. Scripts, extension source, and templates from the original package are not in this folder.

The problem

Manually transcribing electrical specifications from PDF datasheets into component libraries is slow and prone to human error. Developers and hardware engineers often waste hours hunting for supply voltages, temperature ranges, and package types across multi-page documents.

What it does

  • Parses PDF text layers to extract primary part numbers and manufacturer names.
  • Identifies key electrical parameters including min/max supply voltages and operating temperatures.
  • Extracts mechanical data like package strings and pin counts for footprint mapping.
  • Checks for RoHS and REACH compliance status within the document text.
  • Outputs structured data in JSON or CSV format for direct library ingestion.

Frameworks & tools

Python, pdfminer.six, pytest.

Why this beats prompting it yourself

General LLM prompting for PDF extraction often suffers from hallucination of numerical values or inconsistent formatting. This skill uses a specialized script to target specific datasheet patterns, providing a structured output with an extraction confidence score to flag entries needing manual review.

Use cases

  • Populating an ECAD component library (Altium, KiCad) from a batch of PDFs.
  • Automating compliance checks for large BOMs by extracting RoHS/REACH status.
  • Building a searchable internal database of component electrical characteristics.

Known limitations

Only works on PDFs with a text layer. Scanned images or tables formatted as images will not be captured. Requires manual verification of electrical parameters before library commitment.

Example

Request

Extract the specs from components/stm32f4.pdf and save it as a CSV row for my library.

Result

Extraction complete. Created stm32f4.csv: part_number: STM32F405RG manufacturer: STMicroelectronics package: LQFP64 supply_voltage_min: 1.8 supply_voltage_max: 3.6 operating_temp_min: -40 operating_temp_max: 85 rohs_status: Compliant confidence: high

Questions

How does the nex-datasheet-extractor improve my hardware engineering workflow?

This skill automates the tedious task of transcribing electrical specs, package data, and compliance status from PDF datasheets into structured formats like JSON or CSV, significantly reducing human error and manual labor.

Can this skill extract data from scanned datasheets or images?

It is designed to work with PDFs that have a text layer; however, it cannot extract data from scanned images or tables rendered as images.

How does the tool handle potential inaccuracies in the extracted data?

The skill provides a structured output accompanied by a confidence score, allowing you to quickly identify and manually verify entries that may require a second look before final library ingestion.

What exactly is included in the purchase of this skill?

You will receive the specialized Python-based extraction scripts, a suite of pytest files for validation, and documentation on how to integrate the output into ECAD tools like Altium or KiCad.

Which AI agents or environments are compatible with this extractor?

The skill is highly compatible with any Python-based environment and can be integrated as a custom tool for AI agents that support script execution and file processing.


Built by Nex AI. More skills, including the paid catalog: https://www.agensi.io/creators/ch1n4-g3nd4x

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.