gocam-agent

This skill should be used when creating, editing, or validating GO-CAM (Gene Ontology Causal Activity Model) models. It provides comprehensive annotation guidelines for molecular functions, biological processes, cellular components, and causal relationships following GO Consortium standards.

Search GO bioentities (genes, gene products, complexes) and their GO annotations directly from the GO database. Use to resolve MGI/MOD/ComplexPortal IDs, cross-check GO annotations independently of gocam search, or find MOD-specific gene product IDs needed in Noctua models.

Independent blind evaluation of GO-CAM claims documents using Claude Explore subagents to read the PDFs. Reads expert_validation_claims.md and verifies every claim against primary PDFs from scratch, producing a structured evaluation report. Use after gocam-claims-pipeline has generated its output. Always run in a fresh session — never in the same session as the pipeline. For a Gemini-powered alternative, see /blind-review-gemini.

Independent blind evaluation of GO-CAM claims documents using Gemini. One Gemini instance per primary PDF reads the paper directly and returns PASS/FLAG/FAIL verdicts on every claim citing it. Use after gocam-claims-pipeline has generated its output. Always run in a fresh session — never in the same session as the pipeline. For a Claude-engine alternative, see /blind-review-claude.

Generate a .drawio pathway diagram from a GO-CAM claims document. Use after completing the annotation pipeline (Phase 7) to produce agent-output/pathway_sketch.drawio. Reads shape styles and the Shape Palette page from workflow/network_template_draw.drawio.

Launches two parallel Gemini instances per paper to review GO-CAM claims from two complementary perspectives — a peer reviewer (scientific accuracy) and a GO-CAM curator (annotation correctness). Each receives the full claim in claims_template format and responds as an expert with OK/WRONG/UNCERTAIN plus a corrected claim where needed. Collects both outputs into peer_review_claims.md alongside the original claim.

Run the full GO-CAM literature-backed annotation pipeline. Reads GO-CAM models (OWL/TTL), verifies all claims against primary research PDFs, and produces expert validation documents. Use when starting or continuing a GO-CAM curation project folder.

Fetch full-text articles and metadata from PubMed/PMC. Use when a PDF is missing from literature/ and you need the article text or abstract to verify a claim. Full text is only available for open-access PMC articles (~6 million).

Forensic claim-by-claim and comment-by-comment validation of GO-CAM annotation outputs against primary PDFs. Applies 5 strict peer-reviewer rules. Produces OK/WRONG/UNCERTAIN verdicts with corrections. Use after gocam-claims-pipeline has produced its outputs; can run in the same session. Distinct from /blind-review-claude and /blind-review-gemini (which are blind and independent).

Independent blind evaluation of GO-CAM claims documents. Reads an expert_validation_claims.docx (or .md) and verifies every claim against primary PDFs, producing a structured evaluation report. Use after gocam-claims-pipeline has generated its output.

Use whenever you need to look up gene/protein annotations (UniProt ID, GO MF/BP/CC terms, SynGO annotations, ECO evidence codes) or run the gocam-curator extraction pipeline. Provides the search command and pipeline commands for the gocam-curator CLI tool.

Use when starting a completely new GO-CAM model from scratch, deciding whether a GO-CAM is needed vs standard annotations, or following the official GO Consortium workflow for model creation. Covers the conceptual structure of GO-CAMs, when to use them, and the step-by-step creation workflow.

Use whenever you need to access the GO-CAM store (Noctua). This is accomplished via an API called barista.