CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

biopython

Provides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Supports batch processing, custom molecular-biology pipelines, BLAST automation, structure analysis, and motif analysis.

60

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/biopython/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 well-structured overview with excellent progressive disclosure and highly actionable, executable examples for every major Biopython domain. The weaknesses are redundancy (duplicated rg-pattern and Entrez-setup blocks) and workflows — particularly batch Entrez downloads — lacking explicit validation checkpoints.

Suggestions

Deduplicate: remove one of the two rg search-pattern blocks (General Workflow Guidelines vs Quick Reference) and consolidate the thrice-repeated Entrez email/tool setup snippet into a single location referenced elsewhere.

Add explicit validation checkpoints to the batch workflows, e.g. verify downloaded record counts match requested IDs, and retry with backoff on HTTP 400/429 or Entrez rate-limit warnings.

Fix the minor executable gaps in Pattern 3 and the error-handling snippet by defining 'sequence'/'accession' or loading them from a prior step.

DimensionReasoningScore

Conciseness

The body is mostly task-focused, but contains avoidable duplication: the rg search-pattern block appears twice (General Workflow Guidelines and Quick Reference), the Entrez email setup snippet is repeated three times, and the 'When to Use'/'Core Capabilities' lists mirror the description. It fits the 3 anchor ('mostly efficient but could be tightened'); not 2 since it never explains concepts Claude already knows.

3 / 5

Actionability

Concrete, near copy-paste-ready examples cover the common cases (SeqIO parsing/conversion, PairwiseAligner, Entrez esearch, NCBIWWW.qblast, PDBParser distances, Phylo tree building, SeqUtils stats). Not 5: Pattern 3 passes an undefined 'sequence' variable to qblast and the error-handling snippet references an undefined 'accession', leaving minor gaps.

4 / 5

Workflow Clarity

A coherent 4-step workflow exists (identify module → read reference → extract patterns → combine) with a solid troubleshooting section, but the workflow steps embed no explicit validation checkpoints, and batch operations (Entrez batch downloading, Pattern 3's fetch loop) lack verification steps — the rubric's batch-operation cap applies. Not 2: the sequence is clear and substantial error-recovery guidance is present.

3 / 5

Progressive Disclosure

The body is a clean overview: each of the seven domain sections signals exactly one real one-level-deep reference file (all present in references/) with a 'Use for' list and a quick example, references/review.md records verification status, and rg search patterns aid discovery. Matches the 5 anchor; no references are buried or nested.

5 / 5

Total

15

/

20

Passed

Description

75%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, specific description in third person that names concrete actions, formats, and modules, giving it low conflict risk. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness, and some natural synonym terms (bioinformatics, multiple sequence alignment, protein structure) are missing.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with DNA/RNA/protein sequences, FASTA/GenBank/FASTQ files, BLAST results, NCBI/PubMed lookups, or phylogenetic trees.'

Include missing natural synonyms users would say, such as 'bioinformatics', 'multiple sequence alignment', 'protein structure', and 'GC content'.

Mention 'Python' explicitly so users asking for Python-based bioinformatics tooling surface this skill.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions with named formats and modules — 'sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez)' plus 'batch processing, custom molecular-biology pipelines, BLAST automation, structure analysis, and motif analysis' — comprehensive coverage in third-person voice. It is not 4 because action coverage is comprehensive rather than having minor gaps.

5 / 5

Completeness

The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline. It is not 2 because the 'what' is concrete and specific rather than vague.

3 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would say (FASTA, GenBank, PDB, BLAST, PubMed, NCBI, phylogenetics, motif analysis), but misses common variations such as 'bioinformatics', 'multiple sequence alignment', 'protein structure', 'GC content', or 'restriction sites'. It fits the 4 anchor (good coverage, a few natural terms missing) rather than 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

'Provides Biopython workflows...' with distinct triggers (FASTA/GenBank/PDB, BLAST, PubMed, Bio.Entrez) carves a clear niche with minimal conflict risk against other skills. Not 4: the named library, formats, and databases make it highly distinguishable, not just mostly distinct.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.