CtrlK
BlogDocsLog inGet started
Tessl Logo

bioservices

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

69

Quality

86%

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

72%

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 executable code and good progressive disclosure, but loses points on conciseness due to minor redundancy and on workflow clarity because batch operations lack explicit validation/verification feedback loops.

Suggestions

Remove redundant content: the Overview restates the description and the Resources section re-lists scripts already documented above — consolidate to tighten token use.

Add explicit validation/verification checkpoints to batch and file-exporting workflows (batch_id_converter.py, pathway_analysis.py), e.g., verify output file exists and validate converted IDs before declaring success.

Trim the 'Additional Information' section, which largely duplicates links already present in Installation and the Resources references.

DimensionReasoningScore

Conciseness

The body is mostly efficient with tight, executable code and no basic-concept padding, but the Overview repeats the description and the Resources section re-lists scripts already shown, so it could be tightened.

2 / 3

Actionability

Every section provides fully executable code with real arguments, real organism codes, and concrete compound IDs (e.g., cpd:C11222 -> CHEMBL278315), plus copy-paste bash commands for the scripts.

3 / 3

Workflow Clarity

Multi-step workflows are sequenced and BLAST async status-checking is noted, but batch/file-exporting operations (batch_id_converter.py, pathway_analysis.py) lack explicit validation or verification checkpoints, which caps the score at 2 per the rubric.

2 / 3

Progressive Disclosure

SKILL.md is a clear overview with one-level-deep, well-signaled references (services_reference.md, workflow_patterns.md, identifier_mapping.md) that all exist as real files, and the four scripts are organized in a dedicated directory.

3 / 3

Total

10

/

12

Passed

Description

100%

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 concise yet complete: it states concrete capabilities, explicit trigger terms, clear when-to-use guidance, and explicit disambiguation against adjacent skills. No verbosity or over-claims present.

DimensionReasoningScore

Specificity

Names multiple concrete actions (querying databases, cross-database analysis, ID mapping) alongside specific services (UniProt, KEGG, ChEMBL, Reactome), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly states what it does ('Unified Python interface to 40+ bioinformatics services') and when to use it ('Use when querying multiple databases... in a single workflow'), with explicit trigger guidance.

3 / 3

Trigger Term Quality

Uses natural user-facing terms like 'querying multiple databases', 'ID mapping', 'cross-database analysis', and 'single-database lookups' that a user would naturally say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

Explicitly carves out a niche from gget ('quick single-database lookups') and biopython ('sequence/file manipulation'), giving clear distinct triggers unlikely to conflict.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
K-Dense-AI/scientific-agent-skills
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.