monarch-initiative
- 16 skills
- 0 followers
- 23 hours ago last updated
- ▌ Compare Deep Research · monarch-initiative bundleRun one research prompt across multiple deep research providers (via the Deep Research Client) and compare the results side by side — length and structure, citation counts, whether cited sources actually resolve, and whether they are relevant to the question. Use when the user wants to benchmark, evaluate, bake off, or compare deep research tools/providers/agents, or asks which research provider is best for a question.
- ▌
- ▌ Curate Geneset · monarch-initiativeUse when curating or reviewing a GO-term interpretation of a non-GO gene set (MSigDB C8/C2/H, literature disease-activity, or GWAS/CRISPR genetics) for the curation/ gold standard in this repo. Covers grounding in the real membership, OLS term verification, the category / recovery_status / insight axes, evidence, series, the 4-gate validator, and folding the set into the eval.
- ▌ Evaluate Enrichment · monarch-initiativeUse when evaluating a GO enrichment method or a GOA evidence variant (all vs IBA vs IBA+IEA vs no-contributes_to) against the curated benchmark in this repo — the IBA/evidence-ablation eval. Covers building queries.gmt, prepare_go_eval, running genesets-rs, and scoring with the confirmatory/mechanistic split and the recovery_status diagnostics, plus the don't-refit-the-gold guardrail.
- ▌ Odk · monarch-initiativeUse when running any ODK-backed command in this repo — owltools, robot, make NORM, robot verify, or any other tool that lives inside the ODK docker image
- ▌ Merge Terms · monarch-initiativeUse when asked to merge two MONDO terms — obsoleting one and transferring its metadata to the surviving term
- ▌ Release Announcement · monarch-initiativeGenerate a formatted Mondo release announcement with statistics table from release diff reports
- ▌ Ontogpt Extract · monarch-initiative bundleRun OntoGPT to turn unstructured text (abstracts, papers, clinical or field notes, PDFs, PubMed results) into structured, ontology-grounded data. Use when asked to extract entities, relations, or structured records from text with OntoGPT or SPIRES, to run `ontogpt extract`, to set up models and API keys for it, to batch over documents, or to read and convert its YAML/JSON output.
- ▌ Ontogpt Troubleshoot · monarch-initiative bundleDiagnose and fix problems with OntoGPT runs and outputs, including empty or partial extracted objects, values left as AUTO instead of ontology ids, hallucinated or merged values, wrong identifiers, authentication and model errors, slow first runs, annotator download failures, and cache confusion. Use when an `ontogpt extract` result looks wrong, when the command errors or exits, or when asked why an entity did not ground.
- ▌ Ontogpt Author Template · monarch-initiative bundleWrite or modify an OntoGPT extraction template (a LinkML schema with SPIRES annotations), including choosing the ontologies and OAK annotators that ground each entity class, setting id_prefixes, writing field prompts, and validating the schema before use. Use when no bundled template fits, when a template must ground to a different ontology, when asked to add fields or entity classes to a template, or when asked which ontology to use for a kind of entity.
- ▌ Ontogpt Select Template · monarch-initiative bundleChoose the right OntoGPT extraction template (LinkML schema) for a text and a goal, or decide that none of the bundled templates fits and a new one is needed. Use when asked which template or schema to use with OntoGPT, what a template extracts or grounds to, whether OntoGPT can pull a given kind of information (diseases, phenotypes, drugs, genes, GO terms, environmental samples, recipes, etc.) from text, or before any `ontogpt extract` run where the template is not already given.
- ▌ Mic Terms · monarch-initiativeSkill for adding and validating ontology term annotations in the MIC knowledge base. Covers CHEBI, FOODON, HP, GO, MONDO, UBERON, HGNC lookups. Use when adding term bindings to nutrient YAML files.
- ▌ Mic Compliance · monarch-initiativeSkill for analyzing and improving compliance in the MIC knowledge base. Use this when checking nutrient file completeness, identifying missing fields (ontology terms, evidence, descriptions), understanding weighted priority scoring, and systematically improving knowledge base coverage.
- ▌ Mic References · monarch-initiativeSkill for validating and repairing evidence references in the MIC knowledge base. Use this when working with evidence items in nutrient YAML files, validating that snippet text matches PubMed abstracts, and repairing misquoted evidence. Critical for ensuring scientific accuracy and preventing AI hallucinations.
- ▌ Mic Nutrient Creation · monarch-initiativeSkill for creating new nutrient YAML files from MIC website content. Use this when extracting a nutrient from lpi.oregonstate.edu/mic. Also useful for enhancing existing nutrient entries.
- ▌