geniml
Lets your agent work with genomic data locally. It validates information and prepares models for genetic sequence analysis.
What it does
Geniml helps prepare and check genomic data for use in machine learning models. It ensures your data is in the correct format and everything is set up for the next steps.
When to use it
- ✓When you have genomic interval data (like DNA regions) and want to use it for analysis.
- ✓Before running machine learning models on genomic data to ensure quality.
- ✓To check if your genomic data files follow the expected rules.
Example of what to ask your AI
“Check if my genomic data file 'my_data.bed' is compatible with the GRCh38 genome.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
It works by checking the structure of your genomic data files and comparing them against format rules and reference genomes. It also helps plan how the data will be used in models.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add K-Dense-AI/scientific-agent-skills --skill genimlOr download just the file:
curl -L https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/main/skills/geniml/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Geniml
Use Geniml for machine learning and statistical workflows over genomic interval sets. Treat coordinates, assemblies, token vocabularies, model artifacts, and sample grouping as explicit contracts. The bundled scripts validate or plan; they do not import Geniml, contact services, deserialize models, or execute training.
Bash is declared only for explicit, user-approved uv, Python, Geniml,
Gtars, Git, and native CLI commands shown in this guide; bundled Python helpers
do not spawn subprocesses. Example paths under data/, refs/, work/, and
models/ are user-provided project placeholders, not missing bundled files.
Verified release snapshot
- Latest stable PyPI release on 2026-10-01:
geniml==0.8.4(2026-01-14). - PyPI does not declare
Requires-Python; its classifiers list Python 3.10-3.14. The current recipes below were tested on Python 3.12. geniml==0.8.4acceptsgtars>=0.2.5; the verified base smoke used currentgtars==0.10.0(2026-09-05, Python >=3.10).- Extras are
mlandtest. The base install omits Torch, Gensim, Scanpy, Hugging Face Hub, pyBigWig, and HMM dependencies. - Upstream documentation contains stale examples. Release source and installed
--helpoutput take precedence where they conflict.
Install reproducibly
Use a separate project environment. The tested CPU stack uses Python 3.12:
uv venv --python 3.12
uv pip install "geniml==0.8.4" "gtars==0.10.0"
For the Region2Vec/scEmbed recipes tested here, add only their required libraries:
uv pip install "torch==2.14.1" "gensim==4.4.0" "huggingface-hub==2.0.0" \
"scanpy==1.12.4" "anndata==0.12.19" "zarr==2.18.7"
For the consensus recipes, also install pyBigWig==0.3.26 and
hmmlearn==0.3.3. For a durable project, use the same requirements with
uv add and retain uv.lock.
Geniml requires Zarr <3. AnnData 0.13 requires Zarr >=3, so current AnnData
cannot share this environment. Keep AnnData 0.12.19 here; transfer H5AD files
between separate environments when newer AnnData features are needed. Never
force an incompatible installation with --no-deps.
The full geniml[ml]==0.8.4 extra includes additional, older pinned components.
Its resolution was checked with anndata==0.12.19 and gtars==0.10.0, but
that full stack was not executed; it selected Scanpy 1.11.5 and Transformers
4.57.6. It is unnecessary for the workflows above.
Do not install an unpinned Git branch. Record Python, OS/architecture, the
resolved lockfile, and the PyPI artifact digest. Geniml itself is BSD-2-Clause;
the MIT frontmatter value licenses this skill's content.
Start with the safety gate
Before importing Geniml or running an external binary:
- Work only with explicit local regular files. Reject URLs, FIFOs, devices, and symlinks unless the user deliberately changes that policy.
- Validate BED structure and the declared assembly against a trusted local chromosome-sizes file.
- Bound file count, bytes, rows, workers, epochs, and output size.
- Separate train/validation/test by patient, donor, biological replicate, or other independent unit—not by BED row or cell alone.
- Inventory and checksum the universe, tokenizer, model, config, inputs, metadata manifest, and native binaries.
- Obtain explicit approval before any BEDbase or Hugging Face download. Never infer approval from a model ID or BEDbase identifier.
- Keep logs aggregate and bounded. BED filenames, sample IDs, phenotypes, labels, barcodes, and genomic intervals may be sensitive.
Coordinate and assembly contract
BED intervals are normally 0-based, half-open [start, end): start is
included, end is excluded, and length is end - start. Do not mix them with
1-based closed coordinates from VCF/GFF or user-facing genome browsers.
For every corpus and artifact, record:
- assembly and patch/accession where possible (for example GRCh38 versus GRCh38.p14), plus the chromosome-sizes checksum;
- contig naming convention (
chr1versus1), alt/random/decoy policy, and mitochondrial naming; - coordinate convention, sorting order, duplicate/overlap policy, and whether BED strand is meaningful;
- liftover tool, chain digest, source/target assemblies, unmapped fraction, and post-liftover validation.
Reject negative coordinates, end <= start, integer overflow, unknown
contigs, ends beyond contig length, malformed columns, mixed assemblies, and
…
FAQ
What are 'genomic intervals'?
They are like addresses that mark specific positions in DNA, such as regions of interest.
What does 'validate contracts' mean?
It means checking if your data follows a set of expected rules and formats so it can be used correctly.
Does Geniml train machine learning models?
No, Geniml helps prepare and check data before training, but it doesn't perform the training itself.
Details
Original description by the author
Supports audited local Geniml genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess consensus universes.
Popularity
- GitHub stars
- 51k
- Ranking position
- #1874
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
13c-metabolic-flux
Estimates metabolic fluxes using carbon-13 isotope tracing data. It is useful for analyzing cellular metabolism and biochemical pathways.
K-Dense-AI/scientific-agent-skills
adaptyv
Designs protein characterization experiments using the Adaptyv API. It helps estimate costs, submit sequences, and monitor lab results.
K-Dense-AI/scientific-agent-skills
aeon
Performs machine learning tasks on time series data. It is useful for classifying, forecasting, detecting anomalies, and finding patterns in sequential data.
K-Dense-AI/scientific-agent-skills
alphagenome
Looks up precomputed genomic effects for genetic variants. It provides scores and explanations to understand the impact of variants on the genome.
K-Dense-AI/scientific-agent-skills
Similar skills
pytorch-patterns
Helps your agent use PyTorch for machine learning models. It applies best practices for efficient model training and ensures reproducible results.
affaan-m/ECC
evm-token-decimals
Helps your agent avoid errors with decimal numbers across different blockchain networks. It ensures token values are accurate in transactions and calculations.
affaan-m/ECC
knowledge-agent
Creates and queries knowledge bases using AI. It allows asking questions about past work or compiling expertise on a topic.
thedotmack/claude-mem