ai-gene-review: Skill for Claude Code

.claude/skills/bioreason-predictions/SKILL.md

bioreason-predictions is a skill for Claude Code from ai4curation/ai-gene-review. It costs 83 tokens per session (1,782 once invoked), scanned A, original, BSD-3-Clause.

A workflow for reviewing BioReason-Pro-RL predictions about what genes do, including the model’s functional summaries and reasoning traces. Genes are DNA sequences that help produce biological functions, and BioReason-Pro-RL is a prediction system for studying them.

In plain words
What is it for?
Use it to review gene-function predictions, inspect reasoning traces, compare supervised and reinforcement-trained results, and run SFT/RL comparisons.
Why use it?
It provides a defined way to compare predictions with curated reviews, convert exported results into YAML, and assess the quality of the model’s reasoning.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/bioreason-predictions/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 bioreason-predictions

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai4curation/ai-gene-review/bioreason-predictions"><img src="https://agentmods.dev/badge/skills/ai4curation/ai-gene-review/bioreason-predictions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,782 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 $0.00083 $0.01782
Opus 5 $0.00042 $0.00891
Sonnet 5 $0.00017 $0.00356
Haiku 4.5 $0.00008 $0.00178

Measured 12d ago against content hash 1ac96a9fc5e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

bioreason-predictions 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/bioreason-predictions/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BioReason-Pro-RL Predictions

About

BioReason-Pro-RL is a pipeline for producing functional summaries of genes, along with reasoning traces, and other raw material (including high recall function predictions)

  • Web app: app.bioreason.net (model toggle top-left). Default: RL.
  • Paper: doi:10.64898/2026.03.19.712954

We store raw RL exports in:

{GENE}-bioreason-rl-predictions.md

We are primarily interested in the higher precision RL results rather than just Supervised Fine Tuning (SFT)

Structure of a bioreason report

A bioreason report is structured as a markdown doc in these parts:

  • Metadata (organism and sequence)
  • Thinking/Reasoning trace -- the models exposed internal trace of thoughts as to why it arrived at its conclusions
  • Functional summary -- a concise summary of what the function of the gene is
  • Other details
    • UniProt-style summary (model-generated; not imported from UniProt)
    • Interpro domains (from running it as part of pipeline)
    • GO Terms (upstream ESM autoregressive transformer predictions -- high recall, low precision)

We are generally NOT interested in the GO terms in this report. We know in advance these over-predict; they are there to show provenance of the reasoner.

File naming

File Content
{GENE}-bioreason-rl-predictions.md Raw RL web export (provenance)
{GENE}-deep-research-bioreason-sft.md Raw SFT web export when available (provenance)
{GENE}-gogpt-leaf-predictions.yaml GO-GPT leaf terms as PredictionReview YAML
{GENE}-bioreason-rl-review.md Evaluation of RL reasoning trace vs curated review

Reviewing a reasoning trace

Create {GENE}-bioreason-rl-review.md with:

# BioReason-Pro RL Review: {GENE} ({organism})

Source: {GENE}-bioreason-rl-predictions.md

- **Correctness**: X/5
- **Completeness**: X/5

## Functional Summary Review

{freeform analysis}

Comparison with interpro2go:

{comparison}

## Notes on thinking trace

{freeform analysis}

Read the full file on GitHub · 159 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 159 lines · 83 tokens per session scan A 1ac96a9fc5e7

Subscribe to this mod's changes

bioreason-predictions is a skill published in the GitHub repository ai4curation/ai-gene-review (24 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 83 tokens to every session and 1,782 once invoked, about $0.0004 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

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

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

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