ena-database

Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats.

1.15x

Quality

70%

Does it follow best practices?

Impact

96%

1.15x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/ena-database/SKILL.md

Quality

Discovery

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong, technically specific description that clearly identifies the ENA database and lists concrete data types and retrieval methods. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The domain-specific terminology is appropriate for the target audience.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when user needs to fetch sequence data from ENA, references ENA accession numbers (ERR/SRR/PRJ prefixes), or requests raw sequencing reads.'

Consider adding common abbreviation 'ENA' as a trigger term since users may reference it by acronym rather than full name.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession' and specifies access methods 'API/FTP'. Clear domain (ENA) with specific data types.	3 / 3
Completeness	Clearly answers 'what' (retrieve sequences, reads, assemblies from ENA) but lacks explicit 'Use when...' clause. The 'for genomics and bioinformatics pipelines' implies use cases but doesn't provide explicit trigger guidance.	2 / 3
Trigger Term Quality	Excellent coverage of natural terms: 'DNA/RNA sequences', 'FASTQ', 'genome assemblies', 'accession', 'genomics', 'bioinformatics pipelines', 'European Nucleotide Archive', 'ENA'. These are terms bioinformaticians would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche: specifically targets European Nucleotide Archive, mentions specific data types (FASTQ, genome assemblies), and accession-based retrieval. Unlikely to conflict with general file or document skills.	3 / 3
	Total	11 / 12 Passed

Implementation

57%

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

This skill provides a solid structural overview of ENA with reasonable organization and appropriate progressive disclosure to reference documentation. However, it suffers from verbosity in explaining concepts Claude already knows, incomplete code examples that aren't fully executable, and missing validation/error handling workflows for data retrieval operations.

Suggestions

Remove the 'When to Use This Skill' section and trim explanatory text about what ENA is and basic data type definitions - Claude knows these concepts

Make code examples fully executable with complete request handling, response parsing, and error checking (e.g., show how to actually download and save a FASTQ file)

Add explicit validation steps to the bulk download workflow: verify checksums, handle partial downloads, implement retry logic with exponential backoff

Replace the illustrative URL construction examples with complete working functions that handle the full request-response cycle

Dimension	Reasoning	Score
Conciseness	The content includes some unnecessary explanations (e.g., explaining what ENA is, what studies/samples are) that Claude would already know. The 'When to Use This Skill' section is largely redundant. However, the technical content is reasonably efficient.	2 / 3
Actionability	Code examples are provided but are incomplete - they show URL construction but not full request handling, error checking, or actual data extraction. The examples are more illustrative than copy-paste executable.	2 / 3
Workflow Clarity	The 'Bulk Download Pattern' provides a sequence but lacks validation checkpoints. There's no error handling workflow or verification steps for downloaded data integrity. Rate limiting guidance exists but no retry logic is shown.	2 / 3
Progressive Disclosure	Good structure with clear sections and a single-level reference to 'references/api_reference.md' for detailed API documentation. The main skill provides overview while pointing to detailed reference appropriately.	3 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	10 / 11 Passed

Repository: K-Dense-AI/claude-scientific-skills
Commit: 71add64

Reviewed: 7 days 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.