Sdrf:techrefine
Use when the user wants to refine or verify SDRF technical metadata (instrument, tolerances, modifications, DDA/DIA) using raw MS file analysis via techsdrf.
Sdrf:autoresearch
Use when the user wants SDRF annotation to run as an autonomous retained-improvement loop over one dataset, a manifest, or a dataset class such as all PRIDE cell line or crosslinking datasets.
Sdrf:contribute
Use when the user has a completed SDRF annotation for a ProteomeXchange dataset and wants to contribute it back to the community via a PR to sdrf-annotated-datasets.
Sdrf:terms
Use when the user needs to find, verify, or compare ontology terms for SDRF columns. Triggers on questions about ontology terms, accessions, or which term to use.
Sdrf:brainstorm
Use when the user wants to plan what metadata to capture for a new experiment, or discuss experimental design and SDRF strategy before creating the file.
Sdrf:review
Use when the user wants a comprehensive quality review of an SDRF file, a PR review of an SDRF submission, or a quality score assessment.
Sdrf:cellline
Use when the user needs to look up cell line metadata or enrich an SDRF with cell-line-derived characteristics (organism, disease, sex, sampling site, ancestry, age). Triggers on cell line names (HeLa, MCF-7, A549, …), Cellosaurus accessions (CVCL_XXXX), or "annotate cell line" requests.
Sdrf:templates
Use when the user asks about SDRF templates, wants to select templates for an experiment, or needs to understand template layers, inheritance, mutual exclusivity, and selection rules.
Sdrf:explain
Use when the user asks about SDRF concepts, columns, errors, format rules, or wants to understand why something is done a certain way.
Sdrf:convert
Use when the user wants to choose an analysis pipeline, check SDRF compatibility with a pipeline, or understand how to go from SDRF to analysis.
Sdrf:metascreen
Use before sdrf:autoresearch when the user needs to screen or shortlist proteomics studies from PRIDE, MassIVE, ProteomeXchange accessions, or a manifest using detailed user-defined inclusion/exclusion criteria; extract study-level metadata from repository records and publications; and write an evidence-backed TSV for downstream annotation, review, or meta-analysis.
Sdrf:annotate
Use when the user wants to create or annotate an SDRF file for a proteomics dataset. Triggers on PXD accessions, requests to create SDRF, or annotation tasks.
Sdrf:knowledge
Use when the user asks about the SDRF format, column naming rules, ontology mappings, modification format, reserved words, label types, or any SDRF specification question. Also serves as background knowledge for all other SDRF skills.
Sdrf:fix
Use when the user has an SDRF file with known errors and wants them fixed automatically. Triggers on requests to fix, correct, or repair SDRF errors.
Sdrf:setup
Use when the user wants to set up SDRF skills dependencies, install parse_sdrf and techsdrf, or configure the environment for the first time.
Sdrf:design
Use when the user wants to analyze the experimental design encoded in an SDRF file, check for batch effects, confounders, or replication issues.
Sdrf:improve
Use when the user wants to improve an existing SDRF file strictly according to SDRF templates and specification rules (no speculative additions).
Sdrf:validate
Use when the user wants to validate an SDRF file, check for errors, or verify ontology terms. Triggers on requests to check, validate, or review SDRF content.