Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

scikit-bio Biological Data Toolkit

Equips Claude to run scikit-bio workflows — sequences, alignments, phylogenetic trees, diversity metrics, PCoA and PERMANOVA — with the current 0.7+ API.

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

What it does

Guides Claude through bioinformatics work with the scikit-bio (0.7+) Python library, using up-to-date function names and arguments:

  • Sequence handling for DNA/RNA/protein: reverse complement, transcription, translation, regex motif search
  • Alignment via pair_align, pair_align_nucl/prot (BLASTN/BLASTP-like), CIGAR paths, TabularMSA
  • Phylogenetics: NJ, UPGMA, GME/BME, NNI refinement, Robinson-Foulds comparisons, Newick I/O
  • Diversity: alpha (Shannon, Chao1, Faith's PD, Hill) and beta (Bray-Curtis, weighted/unweighted UniFrac)
  • Ordination and stats: PCoA, CA, CCA, RDA; PERMANOVA, ANOSIM, PERMDISP, Mantel; ANCOM/dirmult differential abundance
  • I/O for 19+ formats (FASTA, FASTQ, GenBank, Newick, BIOM) with generator patterns for big files
  • Protein language-model embeddings converted to distance matrices and ordinations

It explicitly flags removed or renamed APIs (local_pairwise_align_ssw, otu_ids → taxa, tip_tip_distances → cophenet), which cuts down on stale generated code.

Who it's for

  • Microbiome researchers and students working in the QIIME 2 ecosystem
  • Anyone doing phylogenetics, community ecology, or multivariate omics statistics
  • ML engineers linking protein embeddings back to classic bioinformatics pipelines

Example uses

  1. "From table.biom and tree.nwk, compute unweighted UniFrac, plot PCoA, then run PERMANOVA on the bodysite column."
  2. "Write a script that reads input.fastq, quality-filters, translates ORFs, and writes output.fasta."
  3. "Locally align these two FASTA sequences with BLASTN-like settings and print the score plus CIGAR string."

· · · Install guide · · ·

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 Claude Skill Mart.
Copy the skills/scikit-bio folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/scikit-bio/.
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 /tmp/sas && mkdir -p ~/.claude/skills && cp -r /tmp/sas/skills/scikit-bio ~/.claude/skills/

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

  1. Open a terminal and confirm Python 3.10+ is available: python3 --version.
  2. Install the library: uv pip install scikit-bio (or conda install -c conda-forge scikit-bio). NumPy 2.0+ is required.
  3. Optional extras for plots and tables: uv pip install matplotlib seaborn biom-format.
  4. Clone the skill repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  5. Copy the skill folder into place: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/scikit-bio ~/.claude/skills/
  6. Restart Claude Code and prompt something like "use scikit-bio to compute beta diversity for my BIOM table" to trigger the skill.
View source on GitHub ↗License: MIT