ai-gene-review: Skill for Claude Code

.claude/skills/aigr-pr-review/SKILL.md

aigr-pr-review is a skill for Claude Code from ai4curation/ai-gene-review. It costs 50 tokens per session (1,009 once invoked), scanned A, original, BSD-3-Clause.

A review guide for pull requests that change gene-function records using Gene Ontology (GO), a system for describing what genes do and where they act.

In plain words
What is it for?
Use it to review gene-review YAML files, write pull-request feedback, follow up on reviews, and check curation decisions.
Why use it?
It helps reviewers judge biological accuracy, evidence quality, GO term choice, and whether proposed annotation changes are justified.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; 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/aigr-pr-review/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 aigr-pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai4curation/ai-gene-review/aigr-pr-review/github.svg)](https://agentmods.dev/skills/ai4curation/ai-gene-review/aigr-pr-review)
Your own site
<a href="https://agentmods.dev/skills/ai4curation/ai-gene-review/aigr-pr-review"><img src="https://agentmods.dev/badge/skills/ai4curation/ai-gene-review/aigr-pr-review/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 aigr-pr-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai4curation/ai-gene-review/aigr-pr-review"><img src="https://agentmods.dev/badge/skills/ai4curation/ai-gene-review/aigr-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,009 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 $0.00050 $0.01009
Opus 5 $0.00025 $0.00504
Sonnet 5 $0.00010 $0.00202
Haiku 4.5 $0.00005 $0.00101

Measured 12d ago against content hash e3aeaeb1c3c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aigr-pr-review 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 12d 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/aigr-pr-review/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIGR PR Review Skill

Use this skill when reviewing AIGR pull requests or drafting review feedback about gene review YAML, GO annotation decisions, evidence support, or UniProt-backed summaries.

Use the repository's existing guidance and agents where appropriate, especially CLAUDE.md and .claude/agents/annotation-reviewer.md.

Trust Validation

Do not re-check what just validate already covers.

If validation passes, do not spend review effort on:

  • YAML formatting or whitespace
  • Empty or null optional keys
  • Required-vs-optional field presence
  • Enum spelling, structural schema shape, or other deterministic validation concerns

The reviewer's job is the non-deterministic part: biological judgment, GO ontology judgment, evidence quality, and whether the curation narrative is coherent.

Focus Areas

  1. GO term specificity and aspect correctness
  • Prefer the most accurate GO term supported by the evidence, not the nearest generic match.
  • Flag terms that are too broad, too narrow, or placed in the wrong GO aspect.
  • Be especially skeptical of vague terms like protein binding when a more informative MF term is available.
  • If recommending MODIFY, provide the concrete replacement term(s) with GO IDs.
  1. Evidence quality
  • Each annotation review should be supported by accessible evidence.
  • Check that cited PMIDs, GO references, file references, and supporting text actually justify the claimed action.
  • Do not accept unsupported NEW annotations.
  • If the relevant publication or evidence cannot be accessed, prefer UNDECIDED.
  1. Core function identification
  • core_functions should capture the gene's main conserved molecular/cellular role.
  • Do not treat every phenotype, developmental consequence, or systems-level effect as core.
  • Use the combination of review YAML, UniProt annotations, deep research, notes, and cited publications to infer what is core vs peripheral.
  1. Description quality
  • The top-level description should be a standalone biological summary for a biologist.
  • Flag project or workflow framing in description, including phrases such as Proteostasis Network, PN, this review, curation, GOA correctly captures, or should be annotated.
  • Project-specific observations, disagreements with a project source list, and annotation-propagation cautions belong in *-notes.md, review.reason, core_functions, or suggested_questions, not in description.

Read the full file on GitHub · 94 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. 12d ago First seen · 94 lines · 50 tokens per session scan A e3aeaeb1c3c2

Subscribe to this mod's changes

aigr-pr-review is a skill published in the GitHub repository ai4curation/ai-gene-review (24 stars, last pushed today), licensed BSD-3-Clause. It adds 50 tokens to every session and 1,009 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

pr-review-triage

Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.

cobusgreyling/loop-engineering · 35 tokens