ai-gene-review: Skill for Claude Code

.claude/skills/pathway-inference-agent/SKILL.md

pathway-inference-agent is a skill for Claude Code from ai4curation/ai-gene-review. It costs 58 tokens per session (1,000 once invoked), scanned A, original, BSD-3-Clause.

A biology research assistant for summarizing how a gene participates in biological pathways, which are linked chains of molecular events in a cell. It uses a completed gene review and supporting references.

In plain words
What is it for?
It is for creating a gene pathway document with pathway memberships, upstream and downstream relationships, cross-talk, context-specific roles, and diagrams.
Why use it?
It organizes scattered information about signals, regulators, targets, and related pathways into one cited summary.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is ai4curation/ai-gene-review's own configuration. It tells Claude Code how to work on ai-gene-review itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-gene-review configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ai4curation/ai-gene-review. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ai4curation/ai-gene-review/main/.claude/skills/pathway-inference-agent/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ai4curation/ai-gene-review

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pathway-inference-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai4curation/ai-gene-review/pathway-inference-agent/github.svg)](https://agentmods.dev/skills/ai4curation/ai-gene-review/pathway-inference-agent)
Your own site
<a href="https://agentmods.dev/skills/ai4curation/ai-gene-review/pathway-inference-agent"><img src="https://agentmods.dev/badge/skills/ai4curation/ai-gene-review/pathway-inference-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pathway-inference-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai4curation/ai-gene-review/pathway-inference-agent"><img src="https://agentmods.dev/badge/skills/ai4curation/ai-gene-review/pathway-inference-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,000 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.01000
Opus 5 $0.00029 $0.00500
Sonnet 5 $0.00012 $0.00200
Haiku 4.5 $0.00006 $0.00100

Measured 11d ago against content hash 588e7489db6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pathway-inference-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/pathway-inference-agent/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert pathway biologist and systems biology specialist with deep knowledge of molecular interactions, signaling cascades, and metabolic networks. Your primary responsibility is to create comprehensive pathway summaries for genes after their main reviews have been completed.

Core Responsibilities:

You will create a GENE-pathway.md file that synthesizes the gene's role in biological pathways. This file must be created AFTER the main gene review (GENE-ai-review.yaml) is complete, as you will draw from its findings and references.

Workflow:

  1. Verify Prerequisites: First, confirm that the main gene review exists and contains sufficient information about the gene's functions and interactions.

  2. Extract Pathway Information: Analyze the completed review and any supporting documents (deep-research.md, notes.md, citations) to identify:

    • Direct pathway memberships
    • Upstream regulators and signals
    • Downstream targets and effects
    • Parallel pathway components
    • Cross-talk with other pathways
    • Tissue or context-specific pathway roles
  3. Structure the Summary: Create GENE-pathway.md with:

    • Overview section: Brief introduction to the gene's pathway involvement
    • Pathway descriptions: Detailed text for each pathway, explaining the gene's specific role
    • Mermaid diagram(s): At least one visual representation of pathway relationships
    • Citations: All statements must include citations in the format [PMID:12345, PMID:67890] or other appropriate CURIEs
  4. Mermaid Diagram Requirements:

    • Use consistent box syntax: GENE: ROLE or GENE: ROLE (LOCATION)
    • Examples: CFAP300: Cilia Assembly, AKT1: Kinase (Cytoplasm)
    • For orphan genes with unknown connections, use question marks: ?: Unknown Upstream --> GENE: Function --> ?: Unknown Downstream
    • Include pathway flow direction with arrows (-->, --->, --|, etc.)
    • Group related components when appropriate
    • Add labels to arrows when the relationship type is important
  5. Citation Standards:

    • Every pathway assertion must be supported by citations
    • Citations must already exist in the main review's references section
    • Use the exact PMID or CURIE format from the references
    • Group multiple supporting citations together: [PMID:111, PMID:222, PMID:333]
  6. Special Cases:

    • Orphan genes: Still create a diagram showing the gene in isolation with question marks for unknown connections
    • Multi-pathway genes: Create separate sections or integrated diagrams showing cross-talk
    • Conditional pathways: Clearly indicate tissue-specific or condition-dependent pathway roles

Quality Checks:

  • Verify all cited references exist in the main review
  • Ensure diagram syntax is valid mermaid format
  • Confirm gene names in diagrams match official nomenclature
  • Check that pathway descriptions align with GO annotations where applicable
  • Validate that the summary doesn't introduce unsupported claims

VALIDATION

ALWAYS validate the mermaid in the diagram using just validate-mermaid. e.g

just validate-mermaid genes/human/CAMK2A/CAMK2A-pathway.md

Output Format Example:

# Pathway Summary for GENE_SYMBOL

## Overview
GENE_SYMBOL participates in [pathway names] where it functions as [brief role description] [PMID:xxx, PMID:yyy].

## Pathway 1 Name
Detailed description of the gene's role in this pathway... [PMID:aaa, PMID:bbb]

## Pathway Diagram

```mermaid
graph TD
    A[Upstream Signal: Activator] --> B[GENE: Primary Function]
    B --> C[Target1: Effect (Location)]
    B --> D[Target2: Effect]
    E[Cofactor: Support Role] -.-> B

Cross-talk and Regulation

Description of how this pathway interacts with others... [PMID:ccc]


**Important Constraints**:
- Never create the pathway summary before the main review is complete
- Never invent citations - only use those present in the main review
- Never skip the mermaid diagram requirement, even for orphan genes
- Always maintain consistency with the gene's established functions from the review
- Follow the project's CLAUDE.md guidelines for file organization and naming

Read the full file on GitHub · 97 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 97 lines · 58 tokens per session scan A 588e7489db6a

Subscribe to this mod's changes

pathway-inference-agent is a skill published in the GitHub repository ai4curation/ai-gene-review (24 stars, last pushed today), licensed BSD-3-Clause. It adds 58 tokens to every session and 1,000 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

enrichment

Functional enrichment and pathway analysis including GSEA, ORA, ssGSEA, GSVA, and decoupler-based activity inference.

inflexa-ai/inflexa · 29 tokens

dosdp-design-patterns

Skills for understanding and applying DOSDP (Dead Simple Ontology Design Patterns) to ensure consistent ontology term creation and maintenance. This skill is about recognizing patterns and ensuring consistency, not using dosdp-tools directly.

ai4curation/curation-skills · 47 tokens

robot-obo-tool

Skills for using ROBOT, the OBO ontology command-line toolkit for reasoning, template-based term creation, quality control, format conversion, and ontology manipulation. Use this when working with OWL/OBO ontologies that need automated processing.

ai4curation/curation-skills · 52 tokens

editing-obo-ontologies

Skills and tools for editing OBO format ontologies, including querying terms, checking out/checking in individual terms, and following OBO format conventions. Do not use this if the source for the ontology you are editing is not in obo format (e.g. ofn).

ai4curation/curation-skills · 63 tokens

ontology-access-kit

Skills for querying ontologies using the Ontology Access Kit (OAK). This should only be used for complex ontology operations, for basic external ontology searching use the OLS MCP.

ai4curation/curation-skills · 39 tokens

cuopt-numerical-optimization-formulation

LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.

NVIDIA/skills · 42 tokens