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.

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/ena-database/SKILL.md

Quality

Content

68%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 well-structured, mostly executable skill body with appropriate offloading of API detail to a real reference file. The main weakness is workflow validation: error handling and rate-limit backoff are documented as best practices rather than embedded as checkpoints in the multi-step bulk download workflow.

Suggestions

Embed validation checkpoints in the Bulk Download Pattern (e.g., "check response.status_code and retry with exponential backoff on 429" after each API call step).

Complete the code examples: show the actual GET request for the Browser API case and a concrete enaBrowserTools download command.

Link the reference as a markdown path (references/api_reference.md) where it is first mentioned in section 2, and move the per-API endpoint enumeration into the reference file.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational with compact code blocks and a well-placed pointer to references/api_reference.md, with only minor over-explanation (the two-sentence ENA overview and an 8-bullet When-to-Use list that duplicates the description). It is trimmable but not noticeably padded, matching anchor 4 rather than 5.	4 / 5
Actionability	The Portal API example is fully executable requests code, and the use-case section gives concrete URL patterns. Minor gaps: the Browser API example assigns a URL but never issues the request, and enaBrowserTools is named without an install or usage command — anchor 4, not 5.	4 / 5
Workflow Clarity	The Bulk Download Pattern gives a clear 4-step sequence (search, extract URLs, download, process), but validation guidance (check HTTP status codes, 429 backoff) sits in Best Practices instead of being integrated as checkpoints in the sequence. Since bulk download is a batch operation, the implicit-checkpoint gap caps this at 3 rather than 4.	3 / 5
Progressive Disclosure	A single one-level reference (references/api_reference.md, verified to exist) is well signaled with a content summary and an explicit load condition. Minor gaps keep it from 5: the reference is described but not linked as a markdown path, and some API enumeration in the body could move into the reference file.	4 / 5
	Total	15 / 20 Passed

Description

70%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 distinct, domain-specific description with several concrete retrieval actions and good natural keywords. Its main weakness is the missing explicit 'Use when...' trigger clause, leaving the invocation conditions only weakly implied.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions ENA, accessions like ERR/PRJ/DRA, or needs to download sequencing data or assemblies."

Include common synonyms and accessions users actually type: "ENA", "nucleotide", "sequencing data", "SRA-style accessions".

Drop the filler phrase "Supports multiple formats" or replace it by naming the formats (FASTQ, FASTA, BAM/CRAM, XML, TSV).

Dimension	Reasoning	Score
Specificity	"Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession" lists several concrete actions with concrete formats, matching the 'several specific actions; minor gaps' anchor. Not 5 because search, taxonomy, and cross-reference capabilities are omitted; not 3 because more than 1-2 concrete actions are named.	4 / 5
Completeness	The "what" is clear and concrete, but there is no explicit "Use when..." clause or equivalent trigger guidance — "for genomics and bioinformatics pipelines" describes a context, not when to invoke the skill, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Natural user terms like "FASTQ", "raw reads", "genome assemblies", "accession", and "genomics and bioinformatics" give good keyword coverage including a file format. A few natural terms are missing (e.g., the "ENA" abbreviation itself, "sequencing data", "nucleotide"), so it does not reach the comprehensive-synonym anchor 5.	4 / 5
Distinctiveness Conflict Risk	It names a specific database (European Nucleotide Archive) with domain-specific triggers (FASTQ, assemblies, accessions), giving it a clear niche with minimal overlap risk against generic data-access skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/ena-database/SKILL.md
Commit: 4082a2e

Reviewed: 1 day 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.