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.
64%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./plugins/nex-business-operations/skills/nex-datasheet-extractor/SKILL.mdThe canonical home for this skill is nex-datasheet-extractor in NexaiGuy/nex-ai-skills
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.
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.
Python, pdfminer.six, pytest.
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.
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.
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
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.
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.
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.
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.
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
NexaiGuy/nex-ai-skills
4034c84
Canonical home
since Nov 1, 2026
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.