Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/fmschulz/omics-skills/exploratory-data-analysisnpx skills add fmschulz/omics-skills --skill exploratory-data-analysisgit clone --depth 1 https://github.com/fmschulz/omics-skillsWrote 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.
[](https://agentmods.dev/skills/fmschulz/omics-skills/exploratory-data-analysis)<a href="https://agentmods.dev/skills/fmschulz/omics-skills/exploratory-data-analysis"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/exploratory-data-analysis.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00042 | $0.02760 |
| Opus 5 | $0.00021 | $0.01380 |
| Sonnet 5 | $0.00008 | $0.00552 |
| Haiku 4.5 | $0.00004 | $0.00276 |
Grade A, and why
exploratory-data-analysis 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploratory Data Analysis
Overview
Inspect scientific files before downstream analysis. The bundled script recognizes more than 100 simple and compound suffixes and writes a bounded Markdown report. It performs content-level analysis only for the common formats listed below; other recognized formats receive file metadata and a reference-catalog entry.
The six reference files contain 239 format entries. Some entries describe the same suffix in different domain contexts, so this is not a count of unique formats or implemented parsers.
Bundled content parsers:
- NumPy arrays (
.npy,.npz), CSV/TSV samples, JSON, and HDF5 - FASTA and FASTQ, including common gzip-compressed suffixes
- TIFF/OME-TIFF, PNG, and JPEG raster images
- Reference-only metadata for every other recognized suffix
- Representative streaming analyzers for PDB/SDF/SMILES, MGF/mzML/mzXML, and mzTab families; proprietary binary formats remain reference-only unless their project environment supplies a reader.
When to Use This Skill
Use this skill when:
- User provides a path to a scientific data file for analysis
- User asks to "explore", "analyze", or "summarize" a data file
- User wants to understand the structure and content of scientific data
- User needs a structure-and-quality report before analysis
- User wants to assess data quality or completeness
- User asks what type of analysis is appropriate for a file
Quick Reference
| Task | Action |
|---|---|
| Unknown file | Detect extension and load the matching reference file before analyzing content. |
| Tabular data | Summarize dimensions, types, missingness, ranges, outliers, duplicates, and candidate keys. |
| Sequence data | Count records, length distribution, GC content, quality scores when available, and format issues. |
| Imaging or arrays | Report shape, channels/axes, dtype, value range, metadata, and scale/calibration when present. |
| Final report | Write a concise Markdown EDA report with findings, caveats, and next analysis options. |
What ships with it
11 files 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.
- assets/report_template.md 3.3 KB
- fixtures/results.mztab 61 B
- fixtures/spectra.mgf 58 B
- fixtures/structure.pdb 259 B
- references/bioinformatics_genomics_formats.md 21 KB
- references/chemistry_molecular_formats.md 22 KB
- references/general_scientific_formats.md 15 KB
- references/microscopy_imaging_formats.md 18 KB
- references/proteomics_metabolomics_formats.md 15 KB
- references/spectroscopy_analytical_formats.md 18 KB
- scripts/eda_analyzer.py 28 KB runs code
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.
- 4d ago First seen · 298 lines · 42 tokens per session scan A d3d693129817
exploratory-data-analysis is a skill published in the GitHub repository fmschulz/omics-skills (7 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 2,760 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
annotate-variants
Annotate variants with deterministic tools such as VEP and preserve exact tool versions and command provenance. Use after normalization and before prioritization.
detect-build-normalize
Detect the reference build and create a normalized derived copy without touching the raw input. Use before annotation or cross-tool comparison.
ingest-vcf
Validate and inventory VCF or BCF input files before downstream analysis. Use when a user provides a genome variant file or asks what data is inside it.
query-variants
Answer targeted questions about genes, rsIDs, coordinates, or variant panels from local genome files. Use for focused exploration before full reporting.
setup-workstation
Prepare or validate a local genome-analysis workstation. Use before the first run on a machine or when toolchain drift is suspected.
nextflow-runner
Run or prepare reproducible Nextflow workflows for heavy genomics jobs. Use only for explicit workflow execution, not routine question answering.