Skills geniml

📦

geniml

Content revision r1 High Risk ⚡ Contains scripts📁 Filesystem access⚙️ External commands🌐 Network access

Analyze Genomic Intervals With Geniml

Genomic interval machine learning requires careful preprocessing, model selection, and validation. This skill guides Geniml workflows for BED embeddings, scATAC-seq analysis, and consensus peaks.

Supports: Claude Codex Code(CC)

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "geniml" from https://skillstore.io/skills/k-dense-ai-geniml.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-geniml/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/k-dense-ai-geniml.md Signed manifest GET /api/skills/k-dense-ai-geniml/manifest Signed lockfile GET /api/skills/k-dense-ai-geniml/lockfile

Test it

Using "geniml". Plan a Region2Vec workflow for 40 ATAC-seq BED files and a project universe.

Expected outcome:

Recommended hard tokenization against the project universe before training.
Suggested starting values for embedding dimension, context length, shuffling count, and learning rate.
Listed validation checks for token coverage, silhouette score, and downstream clustering review.

Using "geniml". Help me decide how to build a consensus peak universe from mixed ATAC-seq samples.

Expected outcome:

Recommended starting with coverage cutoff for fast inspection.
Explained when to move to CCF or ML for noisy boundaries or publication-quality analysis.
Provided checks for merge distance, minimum peak size, and genome assembly consistency.

Using "geniml". Prepare an scEmbed workflow for an AnnData scATAC-seq dataset.

Expected outcome:

Outlined required peak coordinate fields and tokenization output.
Suggested training settings based on dataset scale.
Explained how to store embeddings for scanpy neighbors, clustering, and UMAP.

Security Audit

High Risk

v7 • 7/6/2026 Open versioned report

Static findings in SKILL.md and reference files are documentation examples, cache paths, or reference URLs rather than executable malicious behavior. The skill does include evaluation.json with self-declared safety status, which should be removed or clearly excluded from marketplace trust decisions.

7

Files scanned

1,559

Lines analyzed

0

Review items

0

False positives ignored

Confirmed security concerns (1)

High

evaluation.json:15-18

Prompt Injection Attempt Detected

evaluation.json declares "risk_level": "safe" and "safe_to_publish": true inside the skill package. This untrusted self-assessment can mislead marketplace or agent review if treated as authoritative.

The file contains explicit safe-publication claims in an audit-like structure. It does not issue direct override commands, so confidence is high rather than very high.

Risk Factors

⚡ Contains scripts (2)

evaluation.json:45 references/utilities.md:36

📁 Filesystem access (6)

evaluation.json:42 evaluation.json:42 references/utilities.md:23 references/utilities.md:39 references/utilities.md:23 references/utilities.md:39

⚙️ External commands (20)

🌐 Network access (4)

SKILL.md:32 SKILL.md:289 SKILL.md:290 SKILL.md:312

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Security Assessment

Copy report link

https://skillstore.io/skills/k-dense-ai-geniml/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-geniml/security.svg)](https://skillstore.io/skills/k-dense-ai-geniml?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-geniml?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-geniml/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-geniml.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

K-Dense-AI. (2026). geniml security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-geniml/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-geniml-2026,
  author = {K-Dense-AI},
  title = {geniml security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/k-dense-ai-geniml/audits/7},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "geniml security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
  - name: "K-Dense-AI"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/k-dense-ai-geniml/audits/7"
identifiers:
  - type: other
    value: "skillstore:k-dense-ai-geniml:audit:7"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

davila7 Recommended

davila7-geniml

Skillstore Score 76

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-geniml

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

45

Architecture

85

Maintainability

87

Content

70

Community

83

Spec Compliance

What You Can Build

Build BED Region Embeddings

Prepare BED files, tokenize regions against a universe, train Region2Vec, and review embedding quality metrics.

Cluster scATAC-seq Cells

Plan scEmbed preprocessing, train cell embeddings, and connect the output to scanpy clustering and visualization.

Create Consensus Peak Universes

Choose a universe-building method and tune cutoff, merge, and filter parameters for consistent downstream tokenization.

Try These Prompts

Choose a Workflow

I have BED files and metadata for genomic regions. Help me choose between Region2Vec, BEDspace, scEmbed, and universe building.

Train Region2Vec

Create a Region2Vec workflow for my BED files. Include tokenization, training parameters, output files, and validation checks.

Plan scEmbed Analysis

Help me prepare an scEmbed analysis for an AnnData scATAC-seq dataset with peak coordinates, tokenization, training, and scanpy integration.

Compare Universe Methods

Compare CC, CCF, ML, and HMM universe-building methods for my ATAC-seq peak collection, then recommend parameters and quality checks.

Best Practices

Validate BED coordinates, genome assembly, and universe coverage before training models.
Record parameters, random seeds, input file versions, and model outputs for reproducibility.
Use multiple evaluation metrics and biological labels before trusting embedding clusters.

Avoid

Training embeddings before checking tokenization coverage and genome assembly consistency.
Using BEDspace without verifying metadata file names match the BED input files.
Treating UMAP plots as proof of biological validity without quantitative and domain validation.

Frequently Asked Questions

What data does this skill focus on?

It focuses on genomic interval data, mainly BED files, scATAC-seq peak matrices, metadata tables, and consensus peak universes.

Does the skill run Geniml automatically?

No. It provides workflow guidance and command examples. The user or agent must run tools in a prepared environment.

When should I use Region2Vec?

Use Region2Vec when you need unsupervised embeddings for genomic regions or BED file collections without metadata-aware search.

When should I use BEDspace?

Use BEDspace when BED files have metadata labels and you need joint region-label search or similarity analysis.

What does scEmbed add?

scEmbed creates cell-level embeddings from single-cell ATAC-seq data and can store results for scanpy workflows.

What are the main setup requirements?

You need Geniml, scientific Python dependencies, valid BED or AnnData inputs, genome references, and StarSpace for BEDspace training.

Developer Details

Author

License

BSD-2-Clause license

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/geniml

Ref

b8ca75d2c0a7e7102978993058777d82b8ab2610

Maintenance freshness

7/20/2026

Usage

6 downloads · 190 views

File structure

📁 references/

📄 bedspace.md

📄 consensus_peaks.md

📄 region2vec.md

📄 scembed.md

📄 utilities.md

📄 evaluation.json

More from K-Dense-AI

venue-templates

Prepare Academic Venue Submissions

Academic submissions often fail because formatting rules vary by venue. This skill provides templates, requirements, and examples for faster preparation.

Research & Learning View

iso-13485-certification

Prepare ISO 13485 Certification Docs

Medical device teams must create complete QMS documentation before certification audits. This skill provides templates, checklists, and gap analysis guidance for ISO 13485 readiness.

Documentation View

pytdc

Analyze therapeutic ML datasets with PyTDC

Drug discovery teams need reliable datasets and fair evaluation protocols. This skill helps Claude use PyTDC for curated therapeutic ML data, benchmark splits, metrics, and molecular oracles.

Data & Analytics View

diffdock

Run DiffDock Molecular Docking

Protein-ligand docking requires careful setup, parameter choices, and result interpretation. This skill guides DiffDock workflows for poses, confidence scores, and screening.

Research & Learning View

statistical-analysis

Analyze Research Data with Statistical Guidance

Choosing tests and reporting results can be slow and error-prone. This skill guides test selection, assumptions, effect sizes, power analysis, Bayesian options, and APA reporting.

Data & Analytics View

scanpy

Analyze Single-Cell RNA-seq with Scanpy

Single-cell RNA-seq analysis requires many linked decisions across QC, normalization, clustering, and plotting. This skill gives Claude, Codex, and Claude Code structured Scanpy workflows, reference guidance, and reusable analysis scripts.

Data & Analytics View

bioservices

Connect Bioinformatics Databases with BioServices

by davila7

Bioinformatics research often requires separate interfaces for proteins, pathways, compounds, and identifiers. This skill guides unified BioServices workflows across major biological databases.

Research & Learning View

drugbank-database

Analyze DrugBank Data

by davila7

DrugBank data is rich but difficult to parse across XML, interactions, targets, and structures. This skill guides Claude, Codex, and Claude Code through repeatable DrugBank analysis workflows.

Research & Learning View

kegg-database

Explore KEGG Pathways and Molecular Data

by davila7

Finding connected biological records across KEGG can require several REST operations and careful identifier handling. This skill supplies focused helpers and references for reproducible academic queries.

Research & Learning View

ensembl-database

Query Ensembl Genomic Data

by davila7

Genomic researchers need reliable access to Ensembl data without memorizing every endpoint. This skill guides Claude, Codex, and Claude Code through gene, variant, sequence, and comparative genomics queries.

Data & Analytics View

exploratory-data-analysis

Analyze Scientific Data Files

by davila7

Scientific datasets often arrive in specialized formats that are hard to inspect quickly. This skill detects the format, summarizes contents, checks quality, and produces a clear EDA report.

Data & Analytics View

pytorch-lightning

Build Scalable PyTorch Lightning Training Workflows

by davila7

Deep learning projects become difficult to maintain when training, data, logging, and scaling logic are mixed. This skill provides structured PyTorch Lightning guidance and templates.

Coding & Development View