From cherryhardware
Use to extract structured specifications from component datasheet PDFs—pinouts, electrical characteristics, peripherals—for schematic and PCB analyzers.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cherryhardware:datasheetsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Extract structured, machine-readable specifications from component datasheet PDFs and make them available to analyzer skills. Works on whatever PDFs are downloaded under `<project>/datasheets/` (downloads are owned by distributor skills like `digikey`, `mouser`, `lcsc`, `element14`).
Extract structured, machine-readable specifications from component datasheet PDFs and make them available to analyzer skills. Works on whatever PDFs are downloaded under <project>/datasheets/ (downloads are owned by distributor skills like digikey, mouser, lcsc, element14).
This skill owns:
EXTRACTION_VERSION in scripts/datasheet_extract_cache.py.scripts/datasheet_features.py for other skills to query specific fields (e.g., get_regulator_features(mpn), get_mcu_features(mpn)).digikey, mouser, lcsc, element14).<project>/datasheets/extracted/. There is no shared cross-project cache.<project>/
design.kicad_sch
datasheets/
TPS61023DRLR.pdf # downloaded by distributor skills
extracted/
manifest.json # extraction manifest (legacy name: index.json)
TPS61023DRLR.json # structured extraction (this skill's output)
references/extraction-schema.md — canonical schema, every field definedreferences/field-extraction-guide.md — how to find each field in datasheets from common vendors (TI, ST, NXP, Espressif, Microchip)references/quality-scoring.md — rubric details, score thresholdsreferences/consumer-api.md — how kicad/emc/spice/thermal consume extractionsscripts/datasheet_extract_cache.py — cache manager, resolver, indexerscripts/datasheet_page_selector.py — page selection heuristicsscripts/datasheet_score.py — extraction quality scoringscripts/datasheet_verify.py — cross-check extraction vs schematic usagescripts/datasheet_features.py — consumer helper API (new in v1.3)<project>/datasheets/extracted/<MPN>.json).datasheet_features.py.sync_datasheets_digikey.py, sync_datasheets_lcsc.py, or equivalent. Without extraction, IC-aware checks (VM-001 rail voltage, PS-001 power-good, PR-004 USB, DP-002 USB speed classification) fall back to heuristics on unknown ICs.datasheets/extracted/ is empty — the analyzers won't produce the extractions themselves.trust_level: low → mixed or high.npx claudepluginhub dropio12/cherry-hardware-agent --plugin cherryhardwareUse to extract structured specifications from component datasheet PDFs—pinouts, electrical characteristics, peripherals—for schematic and PCB analyzers.
Extracts structured FF&E product specs from PDFs like price books, fact sheets, and spec sheets using PyMuPDF, structuring into standardized Google Sheets, CSV, or markdown schedules.
Parses complex documents with PaddleOCR to extract text, tables, formulas, charts, and layout structure. Use for invoices, academic papers, multi-column layouts, or any document needing structured understanding.