CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

biopython

A comprehensive toolbox for computational molecular biology; use it when you need programmatic sequence/structure parsing, batch bioinformatics pipelines, or automated NCBI/BLAST workflows.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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, anchored by a fully executable example pipeline with install and run instructions, and it makes genuine use of a well-structured one-level-deep reference bundle. Its weaknesses are repetition of Entrez configuration and rate-limit guidance across three places, generic reproducibility advice, and an unlabeled reference list that could be tied to the topics they cover.

Suggestions

Consolidate Entrez email/API-key and rate-limit guidance into one place (e.g., Implementation Details) and drop the duplicated explanation from the code comments and Run block, keeping only the env-var names.

Replace the bare reference filename list with labeled pointers per topic (e.g., "**Sequence I/O**: `references/sequence_io.md`; **BLAST**: `references/blast.md`") and move the per-module API detail from Key Features into those references.

Either show a concrete retry pattern for transient HTTP failures (e.g., a short retry loop around Entrez.efetch) or remove the unimplemented "implement retries" instruction so the workflow's error-recovery story is complete.

DimensionReasoningScore

Conciseness

The body is mostly efficient — it assumes familiarity with bioinformatics formats and leads with runnable code — but Entrez email/rate-limit guidance is repeated across the code comments ("NCBI requires an email. An API key increases rate limits"), the Run block, and Implementation Details ("Always set Entrez.email... Optionally set Entrez.api_key... add delays"), streaming I/O is stated in both When to Use ("without loading everything into memory") and Implementation Details, and the Reproducibility section is generic advice. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' at 3 rather than the 'minor instances' anchor at 4.

3 / 5

Actionability

The Example Usage section is a complete, copy-paste-ready pipeline (install command, env-var configuration, FASTA parsing, GC fraction, remote BLAST, NCBI efetch) with run commands and a sample input.fasta, covering the common case exactly as the top anchor requires.

5 / 5

Workflow Clarity

The workflow is clearly sequenced (1) parse FASTA → 2) compute GC → 3) BLAST → 4) fetch top hit → 5) print) with some checkpoints present (RuntimeError if NCBI_EMAIL is unset, `if not blast_record.alignments: return None`, `Optional[str]` no-hits handling), but error recovery is mentioned without being implemented ("implement retries for transient HTTP failures" gives no code or pattern), matching 'clear sequence with most checkpoints present; minor validation gaps' at 4 rather than the explicit feedback-loop anchor at 5.

4 / 5

Progressive Disclosure

The bundle's seven reference files (sequence_io.md, alignment.md, databases.md, blast.md, structure.md, phylogenetics.md, advanced.md) all exist and are listed one level deep in the body, and the overview content is appropriately split. However the references are presented as a bare filename list under "Reference guides (if present in this repository) can be consulted" rather than per-topic labeled pointers (e.g., "**BLAST**: See references/blast.md"), and the Key Features section inlines module-level API detail that belongs in the references — 'references mostly clear; minor organization gaps' at 4.

4 / 5

Total

16

/

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 description with an explicit trigger clause, concrete capability statements, and a well-defined niche. Its only weaknesses are the slightly padded opener "A comprehensive toolbox" and missing common file-format trigger terms (FASTA/FASTQ/PDB) that would push specificity and trigger coverage to full marks.

DimensionReasoningScore

Specificity

The description names several concrete capability areas — "programmatic sequence/structure parsing", "batch bioinformatics pipelines", "automated NCBI/BLAST workflows" — but opens with the broad phrase "A comprehensive toolbox for computational molecular biology" and omits finer-grained actions (e.g., translation, tree building, PDB parsing), matching the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor at 5.

4 / 5

Completeness

The description explicitly answers both questions: what it does ("programmatic sequence/structure parsing, batch bioinformatics pipelines, or automated NCBI/BLAST workflows") and when to use it ("use it when you need..."), with concrete trigger phrases, matching the anchor at 5 exactly.

5 / 5

Trigger Term Quality

Natural user terms like "sequence", "bioinformatics pipelines", "NCBI", "BLAST", and "structure" are present, giving good keyword coverage, but common synonyms and file extensions users would say (FASTA, FASTQ, PDB, .fasta) are missing, which falls just short of the comprehensive anchor at 5.

4 / 5

Distinctiveness Conflict Risk

"computational molecular biology" combined with named services "NCBI/BLAST" carves out a clear niche with distinct triggers and minimal overlap risk with unrelated skills, matching the 'clear niche with distinct triggers' anchor.

5 / 5

Total

18

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Data Analysis/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.