// 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.
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.
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.
| name | drawio |
| description | 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. |
Generate .drawio files for GO-CAM pathway network diagrams from a claims document.
After completing the annotation pipeline (Phase 7), generate a network sketch as Output 5.
Input: the claims document (expert_validation_claims.docx or .md).
Output: agent-output/pathway_sketch.drawio.
This skill requires workflow/network_template_draw.drawio. It copies page 1 (Shape Palette) verbatim into the output file. The template is confirmed to exist at that path — read it before generating the diagram.
A .drawio file is XML. The root element is <mxfile> containing <diagram> pages.
Each diagram contains an <mxGraphModel> with a <root> holding <mxCell> elements for nodes and edges.
The file must have exactly 3 pages (diagrams):
id="palette") — copy of the template shapes, arrows, badges, and annotation notes. Copy this verbatim from the template file at workflow/network_template_draw.drawio, page 1.id="canvas") — the actual network diagram. You build this.id="canvas2") — overflow page. Leave empty unless the network is very large.From the claims document, identify:
Each node type has a specific style string. Copy exactly from the template.
Protein / enzyme node:
<mxCell id="[gene_symbol]" parent="1"
style="rounded=1;whiteSpace=wrap;html=0;fillColor=#D6EAF8;strokeColor=#2980B9;strokeWidth=2;arcSize=10;verticalAlign=middle;fontSize=11;fontFamily=Arial;"
value="[GENE_SYMBOL]
[brief role]" vertex="1">
<mxGeometry height="68" width="168" x="[X]" y="[Y]" as="geometry" />
</mxCell>
Small molecule node:
<mxCell id="[molecule_id]" parent="1"
style="ellipse;whiteSpace=wrap;html=0;fillColor=#FCF3CF;strokeColor=#F39C12;strokeWidth=2;verticalAlign=middle;fontSize=12;fontFamily=Arial;fontStyle=1;"
value="[Name]" vertex="1">
<mxGeometry height="62" width="118" x="[X]" y="[Y]" as="geometry" />
</mxCell>
Complex node:
<mxCell id="[complex_id]" parent="1"
style="rounded=1;whiteSpace=wrap;html=0;fillColor=#D5F5E3;strokeColor=#27AE60;strokeWidth=2;dashed=1;dashPattern=8 4;arcSize=10;verticalAlign=middle;fontSize=11;fontFamily=Arial;"
value="[Complex Name]
[subunits]" vertex="1">
<mxGeometry height="82" width="215" x="[X]" y="[Y]" as="geometry" />
</mxCell>
Linked process (cloud):
<mxCell id="[process_id]" parent="1"
style="ellipse;shape=cloud;whiteSpace=wrap;html=0;fillColor=#F2D7D5;strokeColor=#C0392B;strokeWidth=1.5;verticalAlign=middle;fontSize=11;fontFamily=Arial;fontStyle=1;"
value="[Process name]" vertex="1">
<mxGeometry height="75" width="168" x="[X]" y="[Y]" as="geometry" />
</mxCell>
Positive regulation (green arrow):
<mxCell id="e_[source]_[target]" edge="1" parent="1" source="[source_id]" target="[target_id]"
style="edgeStyle=orthogonalEdgeStyle;rounded=0;strokeColor=#27AE60;strokeWidth=2.5;endArrow=block;endFill=1;"
value="">
<mxGeometry relative="1" as="geometry" />
</mxCell>
Negative regulation (red arrow):
<mxCell id="e_[source]_[target]" edge="1" parent="1" source="[source_id]" target="[target_id]"
style="edgeStyle=orthogonalEdgeStyle;rounded=0;strokeColor=#E74C3C;strokeWidth=2.5;endArrow=block;endFill=1;"
value="">
<mxGeometry relative="1" as="geometry" />
</mxCell>
Upstream context (grey dashed arrow):
<mxCell id="e_[source]_[target]" edge="1" parent="1" source="[source_id]" target="[target_id]"
style="edgeStyle=orthogonalEdgeStyle;rounded=0;strokeColor=#95A5A6;strokeWidth=1.5;endArrow=block;endFill=0;dashed=1;dashPattern=6 4;"
value="">
<mxGeometry relative="1" as="geometry" />
</mxCell>
For edges that need waypoints (routing around other nodes), add an <Array> inside geometry:
<mxGeometry relative="1" as="geometry">
<Array as="points">
<mxPoint x="[X]" y="[Y]" />
</Array>
</mxGeometry>
Each edge gets a numbered badge corresponding to its claim number in the claims document.
HIGH confidence badge (blue):
<mxCell id="badge_[N]" parent="1"
style="ellipse;whiteSpace=wrap;html=0;fillColor=#2980B9;strokeColor=none;fontColor=#FFFFFF;fontStyle=1;fontSize=10;fontFamily=Arial;verticalAlign=middle;"
value="[N]" vertex="1">
<mxGeometry height="22" width="28" x="[X]" y="[Y]" as="geometry" />
</mxCell>
MEDIUM confidence badge (dark grey):
<mxCell id="badge_[N]" parent="1"
style="ellipse;whiteSpace=wrap;html=0;fillColor=#7F8C8D;strokeColor=none;fontColor=#FFFFFF;fontStyle=1;fontSize=10;fontFamily=Arial;verticalAlign=middle;"
value="[N]" vertex="1">
<mxGeometry height="22" width="28" x="[X]" y="[Y]" as="geometry" />
</mxCell>
LOW / upstream context badge (light grey):
<mxCell id="badge_[N]" parent="1"
style="ellipse;whiteSpace=wrap;html=0;fillColor=#95A5A6;strokeColor=none;fontColor=#FFFFFF;fontStyle=1;fontSize=10;fontFamily=Arial;verticalAlign=middle;"
value="[N]" vertex="1">
<mxGeometry height="22" width="28" x="[X]" y="[Y]" as="geometry" />
</mxCell>
Place badges near the midpoint of their corresponding edge.
<mxCell id="title" parent="1"
style="text;html=0;fontSize=16;fontFamily=Arial;fontStyle=1;fontColor=#2C3E50;align=left;"
value="[Pathway Name] — [Species] | GO-CAM [model ID]" vertex="1">
<mxGeometry height="30" width="1400" x="15" y="10" as="geometry" />
</mxCell>
camk2a, pick1, ca2, ampar).e_[source]_[target] (e.g., e_camk2a_cacng2).badge_[N] matching claim numbers.# Pseudocode for assembling the .drawio file
palette_xml = read_page_1_from("workflow/network_template_draw.drawio")
canvas_xml = build_canvas(nodes, edges, badges, title)
canvas2_xml = empty_canvas()
output = f'''<mxfile host="app.diagrams.net" pages="3">
{palette_xml}
{canvas_xml}
{canvas2_xml}
</mxfile>'''
write("agent-output/pathway_sketch.drawio", output)
After generating the file:
& as &, < as <)