메뉴
Use whenever you need to access the GO-CAM store (Noctua). This is accomplished via an API called barista.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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.
| name | noctua |
| description | Use whenever you need to access the GO-CAM store (Noctua). This is accomplished via an API called barista. |
Use for listing and searching models, create/read/update on models.
This uses the noctua command line tool, which should have been installed when we ran uv sync
I recommend:
alias barista='uv run noctua barista'
You can get help at any time
barista --help
subcommands also have help
Ask your the user to get a barista token. This should be on the test server:
http://noctua-dev.berkeleybop.org/workbench/noctua-landing-page/
Click "login"
The token should be in the environment
export BARISTA_TOKEN=<token>
or in .env
To dump a model in minerva JSON:
barista export-model --model 646ff70100002557
This is the low-level triple representation used natively in Noctua
In gocam-yaml:
barista export-model --model 646ff70100002557 -f gocam-yaml
This is the structured version
Most recent 50:
barista list-models --limit 50
All that reference a gene product
barista list-models --gp UniProtKB:Q14457
Search by title
barista list-models --title "immune"
Please see the /gocam-best-practice skill
The barista command (alias for noctua barista) provides tools for model creation and editing.
# Export model in Minerva JSON format
barista export-model --model <model-id>
# Export in GO-CAM YAML format
barista export-model --model <model-id> -f gocam-yaml
# List recent models
barista list-models --limit 50
# Search models by gene product
barista list-models --gp UniProtKB:Q14457
# Search models by title
barista list-models --title "immune"
# Create a new empty model
barista create-model
# Add an individual (molecular activity, BP, or CC)
barista add-individual --model <model-id> --class <GO-term> --assign <variable-name>
# Create a relationship between individuals
barista add-fact --model <model-id> \
--subject <variable-or-id> \
--object <variable-or-id> \
--predicate <relation-id>
# Add evidence to support a relationship
barista add-fact-evidence --model <model-id> \
--subject <variable-or-id> \
--object <variable-or-id> \
--evidence <evidence-code> \
--reference <PMID>
--live flag--assign) for readability when building complex models