CtrlK
BlogDocsLog inGet started
Tessl Logo

biology-biopython

Bioinformatics with Biopython for sequence manipulation, file parsing, BLAST, and phylogenetics. Use when working with DNA/RNA/protein sequences or biological databases.

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

80%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.

A concise, well-organized Biopython recipe catalog with highly actionable code snippets and clean section structure. Its main weakness is workflow clarity: batch/remote operations (BLAST, Entrez) proceed without explicit validation or feedback loops, which the rubric caps at 3, and a few entries are hints rather than complete executable code.

Suggestions

Add an explicit validation/feedback loop for batch and remote operations — e.g., for Entrez/esearch, show checking the returned count, handling empty result sets, retrying on rate-limit errors, and sleeping between batch requests.

Replace hint-only entries with complete executable examples, particularly "Local BLAST: run via subprocess, parse XML output" and "Calculate distances: use atom coordinate vectors".

Add a short numbered workflow for a representative end-to-end task (e.g., query a sequence -> BLAST -> parse hits -> build a tree) with explicit validation checkpoints to raise workflow clarity above the batch-operation cap.

DimensionReasoningScore

Conciseness

The body is a lean catalog of one-line code recipes with almost no prose, assuming Claude's competence; brief parentheticals like "(DNA to RNA)" add useful signal without padding, fitting anchor 5.

5 / 5

Actionability

Most entries are concrete, executable snippets (e.g. "from Bio.Seq import Seq; seq = Seq(\"ATGCGA\")", "SeqIO.parse(...)"); a few are high-level hints without complete code ("Local BLAST: run via subprocess", "Calculate distances: use atom coordinate vectors"), matching anchor 4 with minor gaps rather than 5.

4 / 5

Workflow Clarity

Sections are organized as numbered operation lists but contain no sequenced multi-step workflow with validation checkpoints, and the remote/batch BLAST and Entrez operations lack validate-fix-retry feedback loops; per the batch-operation cap this fits anchor 3 and cannot exceed it.

3 / 5

Progressive Disclosure

This is a single-purpose reference skill under 50 lines with well-organized sections (Sequence Manipulation, File Parsing, BLAST, Entrez, Phylogenetics, PDB, Common Pitfalls) and no need for external files, so the simple-skills exception applies and it scores 5.

5 / 5

Total

17

/

20

Passed

Description

87%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.

A strong, well-scoped description that clearly answers both what the skill does and when to use it, with concrete domain actions and natural trigger terms. Minor gaps in trigger-term granularity (common synonyms like FASTA/genome/gene live only in metadata keywords) keep specificity and trigger_term_quality at 4 rather than 5.

DimensionReasoningScore

Specificity

"sequence manipulation, file parsing, BLAST, and phylogenetics" names the domain with several concrete actions; it lists more than 1-2 actions but stays at the category level rather than fully granular sub-actions, so it fits anchor 4 and not 5.

4 / 5

Completeness

The description explicitly states both what ("Bioinformatics with Biopython for sequence manipulation, file parsing, BLAST, and phylogenetics") and when ("Use when working with DNA/RNA/protein sequences or biological databases") with concrete trigger phrases, matching anchor 5.

5 / 5

Trigger Term Quality

"DNA/RNA/protein sequences or biological databases" plus "Biopython", "BLAST", and "phylogenetics" give good natural-term coverage, but common user phrases like FASTA, genome, and gene appear only in metadata keywords rather than the description itself, so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (Biopython bioinformatics) with distinct triggers (DNA/RNA/protein sequences, biological databases) and minimal overlap with other skills, matching anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
aiming-lab/AutoResearchClaw
Reviewed

Table of Contents

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.