// Skills for rare disease case support: ontology-first normalization/retrieval and the clinical genetics consult report format contract (structure + theme). Load the relevant skill file when performing the matching task.
| id | rare_disease_skills_index |
| name | Rare Disease Skills Index |
| description | Skills for rare disease case support: ontology-first normalization/retrieval and the clinical genetics consult report format contract (structure + theme). Load the relevant skill file when performing the matching task. |
| tags | ["rare_disease","ontology","orphanet","omim","hpo","clinical_report"] |
Curated playbooks for the rare disease MDT workflow. Each agent loads the skill file that matches its current task — do not inline these contracts into prompts.
Deterministic normalization against the local Orphanet/OMIM/HPO layer before any online evidence retrieval. Disease alias normalization, phenotype alignment, xref resolution, and the SQLite query scripts live here.
Skill file: rd_ontology_first.md
When to use:
ontology mode)ontology mode)The authoritative format contract for the final clinical genetics consult report: cover page, 4-level numbering, 9 sections, sign-off block, machine-readable JSON, and the standalone HTML theme (embedded CSS, weasyprint PDF path).
Skill file: clinical_report_format.md
When to use:
IMPORTANT: This file is the single source of truth for report layout and styling. The leader must follow it exactly rather than improvising structure or CSS.
Scenario router for paper-writing tasks. Use after root triage to select paper submission, journal article, conference paper, grant proposal, lab report, group report, talk/workshop, or revision-response behavior.
Routing and workflow skill family for paper-writing tasks. Covers manuscript drafting, journal and conference papers, grant proposals, lab reports, group-meeting reports, talks, workshop notes, reviewer rebuttals, academic HTML/PDF/LaTeX output with editable-block contracts, citation grounding, evidence checking, and pre-submission quality gates.
Workflow phases for paper-writing tasks: triage, material inventory, research question, literature review, paper outline, data analysis summary, figure storyline, reader testing, and finalize packet. Each phase is a short contract — read the relevant rows for the current task only.
Section-level writing skill for evidence-bound academic prose: IMRaD papers, grants, reports, talks, and response letters. Indexes section-specific templates (abstract, introduction, method, results, discussion) and pre-submission quality protocols (claim-evidence, reviewer rubric, response letter).
Skills for opening and driving agent-controllable visualization components in the Pantheon UI sidebar — interactive viewers the agent can open, control, and read back. Viewers: Vitessce (spatial / single- cell omics), Viv (bioimage / microscopy), plus agent-generated apps.
Skills for querying and downloading data from genomic, transcriptomic, 3D-genome, and cancer-genomics databases. Covers programmatic access to public repositories, gene annotation, sequence retrieval, processed functional-genomics tracks, Hi-C / Micro-C contact matrices, TCGA-style cohorts, and large-scale single-cell data.