datasheet-extractlisted

# Datasheets Skill ## Purpose 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-search`, `mouser-search`, `lcsc-search`, `element14-search`). ## Scope This skill owns: - **Extraction schema** — the canonical JSON structure for per-MPN specs. Versioned via `EXTRACTION_VERSION` in `scripts/datasheet_extract_cache.py`. - **PDF page selection** — heuristics to pick pages most likely to contain pinouts, e-chars, applications, SPICE models. - **Quality scoring** — weighted rubric (pin coverage, voltage ratings, application info, electrical chars, SPICE specs). - **Consumer API** — helpers in `scripts/datasheet_features.py` for other skills to query specific fields (e.g., `get_regulator_features(mpn)`, `get_mcu_features(mpn)`). - **Verification** — consistency checks between extracted data and schematic/PCB usage. ## Non-goals - **No PDF downloading.** That is owned by distributor skills (`digikey-search`, `mouser-search`, `lcsc-search`, `element14-search`). - **No global library.** Each project's extractions live in `<project>/datasheets/extracted/`. There is no shared cross-project cache. ## Cache location ``` <project>/ design.kicad_sch datasheets/ TPS61023DRLR.pdf # downloaded by distributor skills extracted/ manifest.json # extraction manif