Agent skill

Omics Tools

by DrugClaw in DrugClaw/DrugClaw

Omics and single-cell workflow guide for AnnData, Scanpy-style dataset profiling, PyDESeq2-oriented count checks, pysam alignment inspection, and pyOpenMS mass-spectrometry summaries.

Apache-2.0Auto-check passedResearch & Science

Install Omics Tools

skills CLI
$ npx skills add DrugClaw/DrugClaw --skill omics-tools -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install DrugClaw/DrugClaw omics-tools --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/DrugClaw/DrugClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/science/omics-tools .claude/skills/omics-tools && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
omics-tools
GitHub stars
125
Token cost
~1.1k tokens
SKILL.md length
367 words
Files
4
Skills in repo
25
Repo updated
First seen
Licence
Apache-2.0

At a glance

Omics and single-cell workflow guide for AnnData, Scanpy-style dataset profiling, PyDESeq2-oriented count checks, pysam alignment inspection, and pyOpenMS mass-spectrometry summaries.

  • Works in 5 steps: Start with structural profiling before… → For single-cell data, inspect… → For BAM or CRAM data, report mapped… → …
  • The user asks to inspect h5ad files
  • SKILL.md covers Environment Check, Bundled Assets, Preferred Workflow and Single-Cell And AnnData…, plus 5 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Omics Tools is an agent skill from DrugClaw/DrugClaw. Omics and single-cell workflow guide for AnnData, Scanpy-style dataset profiling, PyDESeq2-oriented count checks, pysam alignment inspection, and pyOpenMS mass-spectrometry summaries. Use when the user asks to inspect h5ad files, summarize BAM regions, profile omics count tables, or inventory mzML experiments before deeper modeling.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `templates/mzml_summary.py`, `templates/pysam_region_profile.py` and `templates/single_cell_profile.py`).

It sits in Research & Science, covering Bioinformatics. It works with AnnData, pysam and Scanpy. The repository describes itself as: 💊 AI Research Assistant for Accelerated Drug Discovery. 🦞. The licence is Apache-2.0.

When your agent uses it

  • The user asks to inspect h5ad files
  • Summarize BAM regions
  • Profile omics count tables
  • Inventory mzML experiments before deeper modeling

Example prompts

  • “Use the omics-tools skill to omic and single-cell workflow guide for AnnData, Scanpy-style dataset profiling, PyDESeq2-oriented count checks, pysam…”
  • “/omics-tools”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Start with structural profiling before statistical interpretation.
  2. For single-cell data, inspect dimensions, metadata coverage, and top group counts before clustering or marker analysis.
  3. For BAM or CRAM data, report mapped reads, index presence, and region counts before variant or expression conclusions.
  4. For mzML data, summarize spectra and acquisition structure before quantification.
  5. Save both a tabular output and a compact summary JSON.

What it can do on your machine

Read from SKILL.md and the folder at commit 960a6e0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Omics Tools loads about 1.1k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 367 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from DrugClaw/DrugClaw at commit 960a6e0, republished under its Apache-2.0 licence (© DrugClaw). 367 words, ~1,074 tokens.

Download SKILL.mdSave it as .claude/skills/omics-tools/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
omics-tools
description
Omics and single-cell workflow guide for AnnData, Scanpy-style dataset profiling, PyDESeq2-oriented count checks, pysam alignment inspection, and pyOpenMS mass-spectrometry summaries. Use when the user asks to inspect h5ad files, summarize BAM regions, profile omics count tables, or inventory mzML experiments before deeper modeling.
source
drugclaw
updated_at
2026-03-11

Omics Tools

Use this skill when the user asks to inspect or triage omics datasets before deeper modeling.

Typical triggers:

  • inspect h5ad or annotated single-cell matrices
  • summarize cell types, batches, and QC columns from AnnData
  • check alignment coverage or region counts from BAM or CRAM files
  • profile a mass-spectrometry mzML experiment before proteomics or metabolomics analysis
  • verify whether a dataset is ready for Scanpy, PyDESeq2, or downstream modeling

Environment Check

bash
which python3 || true
python3 - <<'PY'
mods = ["pandas", "numpy", "anndata", "pysam"]
extra = ["scanpy", "pydeseq2", "pyopenms", "skbio"]
for name in mods + extra:
    try:
        __import__(name)
        print(f"{name}: ok")
    except Exception as exc:
        print(f"{name}: missing ({exc})")
PY

Do not claim single-cell, alignment, or mass-spec analysis ran if the required module is absent.

Bundled Assets

  • templates/single_cell_profile.py
  • templates/pysam_region_profile.py
  • templates/mzml_summary.py

Preferred Workflow

  1. Start with structural profiling before statistical interpretation.
  2. For single-cell data, inspect dimensions, metadata coverage, and top group counts before clustering or marker analysis.
  3. For BAM or CRAM data, report mapped reads, index presence, and region counts before variant or expression conclusions.
  4. For mzML data, summarize spectra and acquisition structure before quantification.
  5. Save both a tabular output and a compact summary JSON.

Single-Cell And AnnData Profiling

bash
python3 templates/single_cell_profile.py \
  --input data/pbmc.h5ad \
  --cell-type-column cell_type \
  --group-column batch \
  --group-column donor \
  --output omics/pbmc_profile.csv \
  --summary omics/pbmc_profile.json

Use this first for:

  • cell and gene counts
  • observation and variable column inventory
  • top cell-type or batch distributions
  • quick readiness checks before Scanpy or scvi-style modeling

Alignment Profiling With Pysam

bash
python3 templates/pysam_region_profile.py \
  --bam alignments/sample.bam \
  --region chr7:55019017-55211628 \
  --region chr12:25205246-25250928 \
  --output omics/sample_region_profile.csv \
  --summary omics/sample_region_profile.json

Use this for:

  • mapped versus unmapped read counts
  • region-specific read totals
  • quick QA before variant or coverage workflows

Mass-Spectrometry Inventory

bash
python3 templates/mzml_summary.py \
  --input proteomics/run01.mzML \
  --output omics/run01_mzml_profile.csv \
  --summary omics/run01_mzml_profile.json

Use this for:

  • spectra and chromatogram counts
  • MS level inventory
  • retention-time range inspection before full pyOpenMS workflows
Show full SKILL.md (138 more words)Show less

Working Boundary

This skill is for data profiling and workflow triage. It does not replace full differential-expression analysis, trajectory inference, peptide identification, or validated clinical interpretation.

Output Expectations

Good answers should mention:

  • exact file paths and any regions or columns used
  • which template ran
  • core dataset dimensions or counts
  • what output files were written
  • whether the result is only profiling or a deeper analytical conclusion
  • any missing modules, index files, or malformed records

For general sequence analysis or command-line bioinformatics, activate bio-tools. For remote biology APIs such as GEO, Ensembl, UniProt, PDB, or Reactome, activate bio-db-tools. For transcription-factor network inference from processed expression matrices, activate grn-tools. For statistical modeling or survival analysis on omics-derived tables, activate stat-modeling-tools or survival-analysis-tools. For static or interactive omics figures, activate scientific-visualization-tools. For chemistry, ADMET, QSAR, or structure-aware affinity, activate chem-tools.

© DrugClaw, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files in skills/science/omics-tools of DrugClaw/DrugClaw.

  • SKILL.md
  • templates/mzml_summary.py
  • templates/pysam_region_profile.py
  • templates/single_cell_profile.py

Open the folder on GitHubat commit 960a6e0

Compare with similar skills

Omics Tools next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Omics Tools compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Omics Tools this skillDrugClaw/DrugClaw125—~1.1kAutomated safety check: PassApache-2.0
Scanpy Single-Cell Analysisdavila7/claude-code-templates32k15 repos~2.8kAutomated safety check: PassMIT
Anndatadavila7/claude-code-templates32k11 repos~2.5kAutomated safety check: PassMIT
ScanpyK-Dense-AI/scientific-agent-skills48k1 repos~5.1kAutomated safety check: PassBSD-3-Clause
Cellxgene CensusK-Dense-AI/scientific-agent-skills48k1 repos~3.4kAutomated safety check: NotesMIT
AnndataK-Dense-AI/scientific-agent-skills48k1 repos~3.9kAutomated safety check: NotesBSD-3-Clause

Similar skills

  • Scanpy Single-Cell Analysis

    davila7/claude-code-templates

    Walks through single-cell RNA-seq analysis with Scanpy: loading .h5ad and 10X data, QC, normalization, PCA and UMAP, Leiden clustering, marker genes and cell type annotation.

    32k GitHub starsUsed in 15 repos~2.8k tokens
    Research & ScienceAuto-check passed
  • Anndata

    davila7/claude-code-templates

    This skill should be used when working with annotated data matrices in Python, particularly for single-cell genomics analysis, managing experimental measurements with metadata, or handling…

    32k GitHub starsUsed in 11 repos~2.5k tokens
    Research & ScienceAuto-check passed
  • Scanpy

    K-Dense-AI/scientific-agent-skills

    Performs Scanpy single-cell RNA-seq QC, normalization, HVG selection, PCA/UMAP/t-SNE, clustering, exploratory marker ranking, pseudobulk preparation, visualization, and Seurat or…

    48k GitHub starsUsed in 1 repo~5.1k tokens
    Research & ScienceAuto-check passed
  • Cellxgene Census

    K-Dense-AI/scientific-agent-skills

    Queries the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data.

    48k GitHub starsUsed in 1 repo~3.4k tokens
    Research & ScienceAuto-check: notes
  • Anndata

    K-Dense-AI/scientific-agent-skills

    Handles annotated matrices in single-cell analysis, .h5ad and Zarr files, and integration with the scverse ecosystem.

    48k GitHub starsUsed in 1 repo~3.9k tokens
    Research & ScienceAuto-check: notes
  • Anndata Data Structure

    jaechang-hits/SciAgent-Skills

    Annotated matrices for single-cell genomics. An agent skill from jaechang-hits/SciAgent-Skills.

    371 GitHub starsUsed in 2 repos~5.8k tokens
    Research & ScienceAuto-check passed

More from DrugClaw/DrugClaw

All 25 skills in this repo
  • Bio DB Tools

    DrugClaw/DrugClaw

    Query public biology databases and APIs including UniProt, RCSB PDB, AlphaFold DB, ClinVar, dbSNP, gnomAD, Ensembl, GEO, InterPro, KEGG, OpenTargets, Reactome, and STRING.

    125 GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed
  • Grn Tools

    DrugClaw/DrugClaw

    Gene regulatory network workflow guide for transcriptomics and single-cell expression matrices using Arboreto, GRNBoost2, and GENIE3.

    125 GitHub stars~692 tokensUpdated 6 mo ago
    Auto-check passed
  • Knowledge Graph Tools

    DrugClaw/DrugClaw

    Drug-discovery knowledge-graph workflow guide for assembling drug-target-disease-pathway relationship graphs from OpenTargets GraphQL, ChEMBL REST, STRING PPI, and Reactome pathway APIs, then…

    125 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Literature Review Tools

    DrugClaw/DrugClaw

    Research-literature workflow guide for evidence-matrix assembly, citation-table normalization, structured review synthesis, and research-gap mapping.

    125 GitHub stars~923 tokensUpdated 6 mo ago
    Auto-check passed
  • Medical Data Tools

    DrugClaw/DrugClaw

    Medical data workflow guide for DICOM metadata inspection and basic de-identification, physiological signal analysis with NeuroKit2, and cohort-table profiling for clinical research datasets.

    125 GitHub stars~1.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Patent Landscape Tools

    DrugClaw/DrugClaw

    Drug-patent landscape workflow guide for searching US patents via the PatentsView API, classifying pharmaceutical claim types (NCE, formulation, method-of-use, polymorph, combination, biologic…

    125 GitHub stars~1.9k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Omics Tools

What does Omics Tools do?

Omics and single-cell workflow guide for AnnData, Scanpy-style dataset profiling, PyDESeq2-oriented count checks, pysam alignment inspection, and pyOpenMS mass-spectrometry summaries. Omics Tools is an agent skill from DrugClaw/DrugClaw. Omics and single-cell workflow guide for AnnData, Scanpy-style dataset profiling, PyDESeq2-oriented count checks, pysam alignment inspection, and pyOpenMS mass-spectrometry summaries.

When should I use Omics Tools?

Omics Tools fits situations like: the user asks to inspect h5ad files; summarize BAM regions; profile omics count tables; inventory mzML experiments before deeper modeling.

How do I install Omics Tools in Claude Code?

Run `npx skills add DrugClaw/DrugClaw --skill omics-tools -a claude-code`. Or copy the skill folder (skills/science/omics-tools in DrugClaw/DrugClaw) into .claude/skills/omics-tools in your project. Claude Code loads it when a task matches its description.

How do I install Omics Tools in Codex?

Run `npx skills add DrugClaw/DrugClaw --skill omics-tools -a codex`. Or copy the skill folder (skills/science/omics-tools in DrugClaw/DrugClaw) into .agents/skills/omics-tools in your project. Codex loads it when a task matches its description.

Can I use Omics Tools in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DrugClaw/DrugClaw --skill omics-tools -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/omics-tools, .gemini/skills/omics-tools, .github/skills/omics-tools and .opencode/skills/omics-tools in your project.

What does Omics Tools need to run?

Going by SKILL.md and its folder, Omics Tools needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Omics Tools access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Omics Tools safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Omics Tools use?

Omics Tools is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Omics Tools use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Omics Tools?

Skills that share tags, products or a category with Omics Tools: Scanpy Single-Cell Analysis (davila7/claude-code-templates, 32k stars), Anndata (davila7/claude-code-templates, 32k stars), Scanpy (K-Dense-AI/scientific-agent-skills, 48k stars) and Cellxgene Census (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Omics Tools?

DrugClaw (a GitHub organization) maintains it in DrugClaw/DrugClaw, which has 125 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on March 23, 2026.

Source: DrugClaw/DrugClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.