Skills biopython

🧬

biopython

Name: biopython
Author: K-Dense-AI

Safe 🔑 Env variables⚙️ External commands📁 Filesystem access🌐 Network access

Analyze biological sequences with Biopython

Also available from: davila7

Process DNA, RNA, and protein sequences efficiently using Biopython. Access NCBI databases programmatically, perform sequence alignments, and automate complex bioinformatics pipelines for research applications.

Supports: Claude Codex Code(CC)

📊 71 Adequate

Download the skill ZIP

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

Toggle on and start using

Test it

Using "biopython". Read a GenBank file and print information about each record

Expected outcome:

Record ID: NC_001416
Description: Escherichia coli bacteriophage lambda, complete genome
Sequence length: 48502 bp
GC content: 49.23%
Features: 73 total (genes, promoters, operators)

Using "biopython". Search PubMed for CRISPR and get the first 5 results

Expected outcome:

Found 15432 results for 'CRISPR'
PMIDs: 37253479, 37253478, 37253477, 37253476, 37253475
First result: Title, Authors, Journal info

Security Audit

Safe

v4 • 1/17/2026

All 546 static findings are FALSE POSITIVES. This skill contains only markdown documentation files with Python code examples for Biopython. The scanner misidentified markdown code block delimiters as shell commands, Biopython module names (Bio.Align, Bio.Phylo) as cryptographic algorithms, and documentation placeholders as real secrets. No executable code exists. This is a legitimate scientific documentation skill.

Files scanned

3,743

Lines analyzed

findings

Total audits

Risk Factors

🔑 Env variables (7)

evaluation_output.json:48 evaluation_output.json:188 references/databases.md:26 references/databases.md:26 skill-report.json:219 SKILL.md:59 SKILL.md:59

⚙️ External commands (415)

📁 Filesystem access (6)

references/advanced.md:71 references/advanced.md:465 references/advanced.md:85 references/blast.md:28 references/blast.md:403 SKILL.md:343

🌐 Network access (8)

references/databases.md:35 references/databases.md:25 skill-report.json:219 skill-report.json:6 SKILL.md:409 SKILL.md:410 SKILL.md:411 SKILL.md:412

Audited by: claude View Audit History →

Quality Score

Architecture

Maintainability

Content

Community

100

Security

100

Spec Compliance

What You Can Build

Batch sequence processing

Process large FASTA files, calculate GC content, translate sequences, and prepare data for downstream analysis.

Build analysis pipelines

Create automated workflows for sequence retrieval, alignment, phylogenetics, and results parsing.

Learn bioinformatics

Explore sequence operations, database access, and structural bioinformatics through practical examples.

Try These Prompts

Read sequence files

Show me how to read a FASTA file and extract sequence records using Bio.SeqIO.

NCBI database access

Write code to search PubMed using Bio.Entrez and fetch the top 10 results for a query about protein kinase.

Sequence alignment

Perform a pairwise global alignment between two DNA sequences using Bio.Align and show me the alignment score.

Protein structure

Load a PDB file and calculate the distance between two alpha carbon atoms in a protein chain.

Best Practices

Always set Entrez.email when accessing NCBI databases to comply with their usage policy
Use iterators like SeqIO.parse() for large files to avoid loading everything into memory
Cache downloaded sequences to avoid redundant network requests and respect rate limits

Avoid

Do not hardcode API keys in scripts; use environment variables instead
Do not skip error handling for network operations which can fail due to connectivity issues
Do not process large alignments without checking memory requirements first

Frequently Asked Questions

What file formats does Biopython support?

FASTA, GenBank, FASTQ, EMBL, SwissProt, PDB, mmCIF, and many more alignment formats.

How do I access NCBI databases?

Use Bio.Entrez with your email set. Search with esearch, fetch with efetch, and parse results with Entrez.read.

Can Biopython run local BLAST searches?

Yes, but requires NCBI BLAST+ installed separately. Use Bio.Blast.Applications for command-line execution.

How do I calculate sequence properties?

Use Bio.SeqUtils for GC content, molecular weight, melting temperature, and protein analysis.

What is the difference between parse and read?

parse() returns an iterator for multiple records; read() expects exactly one record in the file.

How do I handle rate limits with NCBI?

Set Entrez.api_key for 10 requests per second, or use 3 per second without a key. Add delays between requests.

Developer Details

Author

K-Dense-AI

License

BSD-3-Clause

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/biopython

Ref

main

File structure

📁 references/

📄 advanced.md

📄 alignment.md

📄 blast.md

📄 databases.md

📄 phylogenetics.md

📄 sequence_io.md

📄 structure.md

📄 evaluation_output.json

📄 SKILL.md