bioservices

Unified Python access to 40+ bioinformatics web services; use when you need to query multiple databases (e.g., UniProt/KEGG/ChEMBL/Reactome) with one consistent API in a single workflow, especially for cross-database analysis and identifier mapping.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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 highly actionable, well-sequenced skill body built around a runnable cross-service script, with only minor conciseness slack. Its main weakness is progressive disclosure: the rich references/ and scripts/ bundle is never linked from SKILL.md.

Suggestions

Link the existing bundle from the body, e.g. under 'Implementation Details' add '**Full service reference**: See [references/services_reference.md](references/services_reference.md)' and similar pointers for workflow_patterns.md and identifier_mapping.md.

Move the per-method signature catalog in 'Common parameters' into references/services_reference.md, keeping only the most-used signatures inline in SKILL.md.

Trim restating comments in the example script (e.g. '# show header + first rows') to tighten token usage without losing clarity.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and stays mostly lean, but the ~80-line example script carries restating comments and the Implementation Details section re-lists API signatures that could be trimmed; matches 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	A fully copy-paste-ready script covers six common cross-service cases (UniProt search/retrieve, ID mapping, KEGG pathway/KGML/SIF, QuickGO, PSICQUIC, compound→ChEMBL) and Implementation Details gives concrete method signatures, matching 'fully executable; copy-paste ready'.	5 / 5
Workflow Clarity	The example is framed as an explicit numbered 1–6 sequence with code for each step; operations are read-only retrievals so the destructive/batch validation cap does not apply, but no explicit validation checkpoints are shown, matching 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	Section structure is clear, but bundle files exist (references/services_reference.md, workflow_patterns.md, identifier_mapping.md and four scripts) and are never referenced or signaled from the body, while the long example and API reference are inlined; matches 'some structure; references present but not clearly signaled; content that should be separate is inline'.	3 / 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, third-person description that pairs a concrete capability statement with an explicit 'use when' trigger and specific database names. It is comprehensive on completeness and distinctiveness with only minor specificity gaps.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("query multiple databases", "identifier mapping", "cross-database analysis") plus named databases, matching the 'several specific actions; minor gaps' anchor; not a 5 because the lead phrase "Unified Python access" is somewhat generic rather than a fully enumerated action set.	4 / 5
Completeness	Explicitly answers both what ("Unified Python access to 40+ bioinformatics web services ... one consistent API") and when ("use when you need to query multiple databases ... especially for cross-database analysis and identifier mapping") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases a bioinformatics user would say ("query multiple databases", "cross-database analysis", "identifier mapping") appear alongside provider synonyms (UniProt/KEGG/ChEMBL/Reactome), giving good coverage; not a 5 because there are no file extensions or layperson synonyms.	4 / 5
Distinctiveness Conflict Risk	The multi-database bioinformatics plus identifier-mapping niche with named providers is a clear, distinct trigger surface with minimal overlap risk against generic data or single-database skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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/bioservices/SKILL.md
Commit: f5ef65b

Reviewed: 20 minutes 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.