monarch-initiative

Skill for collecting recent clinical Practice Guideline citations from PubMed for dismech disorder entries. Use this skill when building or refreshing a care-guideline citation set — searching PubMed by disorder for Publication Type "Practice Guideline" within a recent time window, prioritizing disorders by guideline availability, and exporting a tab-delimited citation table for downstream phenotype/content gap mining (as was done for Fanconi anemia).

Skill for populating the `classifications` top-level block of a dismech Disease entry. Covers Harrison's Part assignment, mechanistic nosology, lysosomal storage, IUIS immunodeficiency, channelopathy, and ICD-O morphology fields, with a lookup table from common clinical phrasing to controlled-vocabulary keys.

Skill for initiating new disorder YAML files in the dismech knowledge base. Use this skill when the user asks to create a new disorder entry. Also useful for enhancing existing entries.

Instructions for reviewing a dismech PR, in particular PRs relating to disorder curation, either creating new dismech entries or updating existing ones.

Skill for analyzing and improving compliance in the dismech knowledge base. Use this skill when checking disorder file completeness, identifying missing fields (ontology terms, evidence, descriptions), understanding weighted priority scoring, and systematically improving knowledge base coverage.

Skill for validating and repairing evidence references in the dismech knowledge base. Use this skill when working with evidence items in disorder YAML files, validating that snippet text matches PubMed abstracts, and repairing misquoted or fabricated evidence. Critical for ensuring scientific accuracy and preventing AI hallucinations.

Skill for adding and validating ontology term references in the dismech knowledge base. This skill should be used when working with disorder YAML files that need ontology term annotations (HPO for phenotypes, CL for cell types, GO for biological processes, MONDO for diseases, UBERON for anatomical entities). Use this skill when adding phenotype_term, cell_types term, biological_processes term, or other ontology-bound fields to disorder files.

Use ONLY when the user explicitly asks to orchestrate parallel external agents (Codex or Claude Code) in tmux sessions via tp (tmux-pilot). Or when a user tells you that you're the boss or orchestrator. You can also use this if you are an operclaw agent. NEVER auto-invoke for a generic "do this in parallel" request. For in-process subagents, use superpowers:dispatching-parallel-agents instead.

Use when asked to merge two MONDO terms — obsoleting one and transferring its metadata to the surviving term

Use 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

Generate a formatted Mondo release announcement with statistics table from release diff reports

Analyze MONDO GitHub issues for validity, suggest improvements, and generate structured reports with duplication checks and identifier validation

Skill 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.

Skill 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.

Skill 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.

Skill 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.

Perform gene set enrichment analysis using AI research providers. Analyzes lists of genes to identify biological themes, pathways, and functional associations.

Toolkit for performing deep research on complex topics using multiple AI research providers (OpenAI, Falcon, Perplexity, Consensus). Emphasizes explicit speed vs depth trade-offs.

Use 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.

Use 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.

Updates the Monarch Initiative publications page with latest data from Google Scholar. Use this when the user asks to update publications, refresh citation metrics, or add new papers to the publications page.

Extract and cross-reference foundation stock (ancestor breed) relations from kennel club registry websites for a given species. Use when the user wants to build or update foundation stock data from breed registry sources.