bio-database-evidence

Unified biological database evidence owner. Use for gene annotation, variant clinical significance, cancer mutation evidence, GWAS trait associations, pathway mapping, target-disease evidence, protein structures, protein interaction networks, reference single-cell census queries, and cross-database biological ID mapping. Do not use for full single-cell analysis, bulk RNA-seq differential expression, BAM/VCF processing, protein embedding models, metabolic flux modeling, genomic interval ML, or flow-cytometry file parsing.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, well-structured, and uses progressive disclosure effectively with a real one-level-deep reference. Its main weakness is actionability: the body gives strategic workflow guidance and names sources, but the executable query specifics live entirely in the reference file.

Suggestions

Add one or two concrete executable patterns to the body (e.g., a representative API/ID-lookup snippet or the exact evidence-output table columns) so the SKILL.md is actionable without forcing a reference hop.

Tighten workflow step 2 ("Pick the narrowest source that answers the evidence question") with a brief decision heuristic or mapping of entity type to primary source.

Surface the reference's evidence-output table column pattern directly in the workflow so the expected result shape is visible in the overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized with bullet lists and a short workflow; it assumes Claude's competence and avoids explaining biological concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	The body names concrete sources (Ensembl, ClinVar, COSMIC, GWAS Catalog, KEGG, Reactome, Open Targets, AlphaFold DB, RCSB PDB, STRING, CELLxGENE) but the executable specifics (API endpoints, query syntax, exact output handling) are delegated to the reference rather than present in the body, leaving the main instructions somewhat strategic.	2 / 3
Workflow Clarity	Five clearly sequenced steps guide entity identification, source selection, provenance preservation, tabular output, and access/license caveats; the read-only evidence-gathering nature does not require destructive-operation validation loops, and step 5 acts as a caveat checkpoint.	3 / 3
Progressive Disclosure	SKILL.md is a clear overview that points to a single, well-signaled, one-level-deep reference (references/database-evidence-sources.md, which exists), with content appropriately split between overview and source-specific detail.	3 / 3
	Total	11 / 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 specific, trigger-rich, complete, and highly distinctive. It covers a broad but coherent evidence-gathering niche with strong positive and negative triggers that minimize conflict with neighboring skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities such as "gene annotation, variant clinical significance, cancer mutation evidence, GWAS trait associations, pathway mapping, target-disease evidence, protein structures, protein interaction networks" — a comprehensive set of specific actions rather than vague language.	3 / 3
Completeness	Explicitly answers what ("Unified biological database evidence owner" plus the capability list) and when via an equivalent "Use for..." trigger clause, with a "Do not use for..." clause further sharpening the when-guidance.	3 / 3
Trigger Term Quality	Includes natural terms a bioinformatics user would say ("gene annotation", "variant clinical significance", "GWAS trait associations", "protein structures", "single-cell census queries") with good coverage of the domain's common phrasings.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche (biological database evidence) and explicit "Do not use for" exclusions (full single-cell analysis, bulk RNA-seq, BAM/VCF processing, protein embedding models, metabolic flux modeling, genomic interval ML, flow-cytometry parsing) that distinguish it from adjacent skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/bio-database-evidence/SKILL.md
Commit: f627ab5

Reviewed: about 8 hours 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.