microbiomedata

Use this skill to assemble an evidence bundle (context texts) from a parsed submission or ETL study context, including DOI abstracts and PDF content.

Use this skill to retrieve supplementary materials for a manuscript DOI, prioritizing the file types useful for characterizing NMDC submissions and samples (tabular metadata and supplementary documents). Performance-first, single attempt, no repeated retries.

Use this skill to fetch abstract or description text for a DOI using a source waterfall (datacite, crossref, openalex, pubmed, and repository-specific sources like osti, ess-dive, jgi).

Use this skill to suggest metadata field values for a full NMDC submission object by parsing submission data, fetching DOI/PDF context, loading schema, and returning cited LLMOutput JSON.

Use this skill to orchestrate NMDC metadata suggestions — detects input shape, routes to env-triad and/or metadata-suggestion-pipeline, and returns a merged LLMOutput JSON. Entry point for all metadata suggestion requests.

Use this skill to suggest env_broad_scale, env_local_scale, and env_medium values for NMDC biosample records using study context, DOI abstracts, and schema enumerations.

Use this skill to extract structured fields (DOIs, study name, description, protocol info, MIxS extensions) from a raw NMDC submission portal object. Called at the start of metadata-suggestion-pipeline and env-triad when a submission_object is present.

Use this skill to retrieve PDF content for publications via web_fetch (agentic path).

Use this skill to decide whether a source vocabulary warrants a reusable mapping artifact and, when it does, author a validated SSSOM mapping set (subject/predicate/object with provenance) from a source controlled vocabulary (land-cover classes, habitat…

Use this skill to translate an NCBI BioProject (BioSamples plus SRA runs) into an NMDC-schema Database JSON, then hand curation to the nmdc-env-triad, nmdc-taxon-resolution, nmdc-target-gene and nmdc-schema-reference skills, validate, and emit run notes via…

Use this skill to resolve MIxS env_broad_scale, env_local_scale, and env_medium to ENVO CURIEs via runoak, constrained to the correct anchor classes and the MIxS soil-package valueset. Trigger when an ingest leaves ENVO:00000000 sentinels on biosample…

Use this skill to curate amplicon LibraryPreparation records an NCBI ingest left unfinished: write a description (target plus primers) from the SRA DESIGN_DESCRIPTION on every amplicon library, and select a TargetGeneEnum target_gene for single-gene amplicons…

Use this skill at the end of an ingest or curation run to write a short human-readable RUN_NOTES.md a curator can review and act on: record counts, what resolved deterministically vs by LLM judgment, what was deferred and why, ambiguous cases needing a human…

Use this skill to look up NMDC LinkML slot ranges, value-type wrappers (QuantityValue, ControlledIdentifiedTermValue vs ControlledTermValue) and enum allowed-values via SchemaView before shaping any non-trivial NMDC slot value or diagnosing a validation…

Use this skill before committing ANY predicted or resolved value to an NMDC record: cite a per-sample labeled source, never fabricate a CURIE from memory, omit rather than guess, keep each reason under 12 words, and validate before commit. Read whenever…

Use this skill to resolve organism names to NCBITaxon CURIEs via runoak for samp_taxon, host_taxid, and host_name, applying NMDC's unambiguous-intent rule for host assignment. Trigger when a host or taxon slot is unset or holds free-text needing lifting to a…

Annotate the MIxS checklist/extension slot report with grounded priority and comment columns judging how important it is for NMDC to add each missing MIxS slot. Use when asked to assess MIxS slot gaps, prioritize slots to add to nmdc-schema, or produce the…