AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Geniml Genomic-Interval ML Auditor

A Geniml-focused skill that validates BED/universe contracts and plans Region2Vec, scEmbed, and consensus-universe runs with safety and compatibility checks.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Validates BED structure, 0-based half-open coordinates, contig naming, assembly and chrom.sizes checksums, reporting a normalization plan without rewriting your files.
  • Plans Region2Vec and scEmbed runs: Parquet tokens corpora, gtars Tokenizer from a universe BED, embedding_dim, and the seven special tokens that make len(tokenizer) ≠ universe rows.
  • Inspects model bundles (checkpoint.pt, config.yaml, universe.bed) for vocab_size/embedding_dim and universe-byte mismatches before any inference.
  • Documents the real 0.8.4 CLI spellings (build-universe, assess-universe, eval) versus stale upstream docs, plus migration notes for moved module paths.
  • Requires explicit approval before BEDbase or Hugging Face downloads and prefers local cache inspection commands.

Who it's for

  • Genomics data scientists building embeddings or clustering over ATAC-seq/ChIP-seq peak sets.
  • Teams merging BED files across cohorts who worry about assembly mixing and patient/donor-level leakage.
  • Anyone who must vet third-party Region2Vec/scEmbed checkpoints before loading them.

Example uses

  1. "Check data/peaks.bed against GRCh38" → bed_validator.py reports coordinate, contig, and length violations.
  2. "Audit manifest.tsv for train/test leakage by patient_id" → corpus_auditor.py returns checksums, assemblies, and leakage risk.
  3. "Is models/r2v compatible with refs/universe.bed?" → model_artifact_inspector.py plus tokenizer_compatibility.py surface vocab and special-token mismatches.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/geniml/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/geniml folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/geniml/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/geniml ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Make sure Claude Code is installed and you can open a terminal.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/geniml ~/.claude/skills/
  5. For real analysis work, install Python 3.11–3.12 and uv, then run uv venv --python 3.12 and uv pip install "geniml[ml]==0.8.4" "gtars==0.9.2".
  6. Restart Claude Code and ask something like "use the geniml skill to validate my BED file".
  7. Note: the bundled scripts are standard-library only and make no network calls; BEDbase/Hugging Face downloads always need your explicit approval.
View source on GitHub ↗License: MIT