biopython

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with excellent progressive disclosure into verified reference files, but it is somewhat verbose for the main skill body and the batch-automation workflows lack explicit validation/feedback loops that the rubric requires for higher workflow-clarity scores.

Suggestions

Add explicit validation checkpoints to batch workflows—e.g., after Entrez batch fetch or BLAST runs, verify expected record counts and handle empty/failed results before proceeding.

Trim repeated or basic exposition (repeated Entrez email setup blocks, definitions of standard formats like FASTA/GenBank) to reduce token load in the main SKILL.md.

Consolidate the duplicated grep/search-pattern sections (two 'Quick Reference'/'Reading Documentation' blocks show near-identical rg examples) into a single navigation block.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient with executable examples per module, but it repeats concepts Claude already knows (e.g., what FASTA/GenBank formats are, generic file-handling advice) and reiterates the Entrez email setup multiple times; the 488-line body could be tightened.	3 / 5
Actionability	Every major capability section provides copy-paste-ready, executable Python examples covering common cases (SeqIO parsing, BLAST, Entrez search, PDB distance, tree building), and troubleshooting entries give concrete fixes.	5 / 5
Workflow Clarity	Batch/automated operations (BLAST, Entrez batch fetching) lack explicit validation checkpoints or feedback loops; the rubric caps workflow clarity at 3 for batch operations without validation steps.	3 / 5
Progressive Disclosure	The SKILL.md is a well-structured overview pointing to seven one-level-deep reference files, all verified to exist in references/ (sequence_io, alignment, databases, blast, structure, phylogenetics, advanced), with clear 'Reference:' signaling and search patterns.	5 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong across all dimensions: it states concrete capabilities, includes natural trigger terms and file formats, answers both what and when, and actively disambiguates from sibling skills (gget, bioservices).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—'sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access'—with batch processing and BLAST automation, giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly states what it does ('Comprehensive molecular biology toolkit...') and when to use it ('Use for...'), and further distinguishes with 'For quick lookups use gget; for multi-service integration use bioservices', clearly answering both what and when with concrete triggers.	5 / 5
Trigger Term Quality	Natural terms include 'sequence manipulation', 'file parsing', 'FASTA/GenBank/PDB', 'phylogenetics', 'BLAST', and file extensions, covering synonyms and concrete formats users would actually say.	5 / 5
Distinctiveness Conflict Risk	The skill carves a clear niche and explicitly disambiguates from adjacent tools ('For quick lookups use gget; for multi-service integration use bioservices'), minimizing conflict risk for wrong-skill triggering.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/biopython/SKILL.md
Commit: 9cf7d9a

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.