biopython

Primary retained Python toolkit for molecular biology sequence work. Preferred for sequence manipulation, FASTA/FASTQ/GenBank parsing, Bio.Entrez, BLAST workflows, alignments, structures, and phylogenetics. For biological database evidence lookup, use bio-database-evidence. For single-cell workflows use scanpy. For direct literature REST API, use pubmed-database.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/biopython/SKILL.md

Quality

Content

72%

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

A well-structured, highly actionable skill body with clean progressive disclosure into real reference files. Its weaknesses are token-efficiency (duplicated grep blocks, time-sensitive version info, some basic advice) and the lack of validation feedback loops for batch/destructive network operations.

Suggestions

Remove the duplicated grep search-pattern block (keep it in one place only) and drop or relocate the "Biopython 1.85 (released January 2025)" version/date out of the overview, since time-sensitive info penalizes conciseness.

Trim basic programming guidance ("Import modules explicitly", "close handles after use", "use iterators for large files") that Claude already knows, keeping only Biopython-specific conventions.

Add an explicit validate→fix→retry feedback loop for batch Entrez operations (e.g., check HTTP status, retry on 429 with backoff, verify record count matches requested IDs) so the workflow includes real checkpoints.

Dimension	Reasoning	Score
Conciseness	Mostly efficient actionable reference material, but it carries redundancy (the grep search-pattern block appears twice, at lines 243–252 and 416–427, and Common Patterns overlap the per-module quick examples), time-sensitive info ("Biopython 1.85 (released January 2025)"), and basic advice Claude already knows ("Import modules explicitly", "close handles after use").	2 / 3
Actionability	Every section ships concrete, executable, copy-paste-ready Biopython code with real imports and calls (SeqIO.parse, Entrez.esearch, NCBIWWW.qblast, PDBParser, Phylo.read), matching the anchor for fully executable guidance.	3 / 3
Workflow Clarity	Sequences exist (the Reading Documentation steps and the Summary checklist), but there are no explicit validation checkpoints or validate→fix→retry feedback loops for batch Entrez downloads and other network operations the skill itself describes, so workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	A clear overview in SKILL.md points to seven well-signaled one-level-deep references (e.g., "Reference: references/sequence_io.md"), all of which exist in the bundle, with content appropriately split and easy to navigate.	3 / 3
	Total	10 / 12 Passed

Description

82%

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

A strong, specific description with good natural trigger terms and excellent distinctiveness via explicit routing to sibling skills. Its main weakness is the absence of an explicit positive "Use when…" trigger clause, leaving the invocation condition implied rather than stated.

Suggestions

Add an explicit "Use when…" clause naming the triggering situations (e.g., "Use when working with DNA/RNA/protein sequences, parsing FASTA/FASTQ/GenBank files, running BLAST, or building phylogenetic trees") so the "when" is stated, not implied.

Move the capability list under the trigger clause so both "what" and "when" are unambiguously present in one sentence.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and capabilities — "sequence manipulation, FASTA/FASTQ/GenBank parsing, Bio.Entrez, BLAST workflows, alignments, structures, and phylogenetics" — matching the anchor for naming several specific actions rather than vague language.	3 / 3
Completeness	It clearly answers "what" (preferred toolkit for listed tasks) but lacks an explicit "Use when…" clause; the "when" is only implied via "Preferred for" and negative routing to other skills, so per the guideline completeness is capped at 2 rather than reaching 3.	2 / 3
Trigger Term Quality	Includes natural terms a bioinformatics user would actually say — FASTA/FASTQ/GenBank, BLAST, alignments, structures, phylogenetics, molecular biology sequence work — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Explicit routing ("For biological database evidence lookup, use bio-database-evidence", "For single-cell workflows use scanpy", "For direct literature REST API, use pubmed-database") carves out a clear niche and prevents triggering for adjacent skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/biopython/SKILL.md
Commit: f627ab5

Reviewed: about 8 hours 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.