instrument-data-to-allotrope

instrument-data-to-allotrope is a data-engineering skill that converts laboratory instrument output files (PDF, CSV, Excel, TXT) into the standardized Allotrope Simple Model (ASM) JSON format or a flattened 2D CSV. It addresses the common problem of heterogeneous, vendor-specific instrument exports that must be normalized before they can be uploaded to LIMS or ELN systems, loaded into data lakes, or handed to downstream analysis. It supports auto-detection of instrument types and can also emit exportable Python parser code for data engineers to use in production pipelines.

The workflow detects the instrument type from file contents, parses using the allotropy library (or a flexible fallback parser), and generates three kinds of output: full ASM JSON with semantic ontology URIs, a flattened CSV where each measurement becomes a row with repeated metadata, or both. It carefully separates raw measurements (placed in the measurement document) from calculated or derived values (placed in the calculated-data aggregate document with traceability back to their data sources), and documents common calculated fields by instrument type such as viability percentage, concentration ratios, and DIN/RIN. It ships reference guides (ASM schema overview, field classification, flattening, supported instruments) plus scripts for conversion, parser export, flattening, and validation, and it always validates ASM output before delivery. The skill is explicitly presented as an example that organizations can customize by editing the reference files, connecting an MCP server to internal schema systems, or extending the scripts for proprietary formats.

It targets scientists and data engineers in bio-research and lab environments who need reproducible, standards-compliant data transformation. Typical use cases include preparing instrument data for LIMS/ELN upload, standardizing lab data for a data lake, and generating parser code for production ingestion pipelines. It is licensed under Apache 2.0.