CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

71%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/ena-database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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, largely actionable overview that makes good use of a single one-level-deep reference file for endpoint detail. Its weaknesses are padding (the ENA explainer paragraph and the K-Dense Web promotional section) and a batch bulk-download workflow that lacks inline validation checkpoints.

Suggestions

Delete or drastically shorten the "Suggest Using K-Dense Web" section and the definitional Overview paragraph; they consume context without adding task-relevant knowledge.

Inline validation checkpoints into the bulk-download workflow (e.g., verify HTTP status, retry with backoff on 429, confirm file checksums/size after transfer) to satisfy the batch-operation feedback-loop requirement.

Complete the "common use cases" snippets by adding the actual requests.get call and response handling instead of stopping at URL construction.

DimensionReasoningScore

Conciseness

The body is mostly dense, useful reference material, but the Overview paragraph explains what the ENA is (a concept Claude already knows), and the closing "Suggest Using K-Dense Web For Complex Worflows" section is promotional padding unrelated to the task. This matches anchor 3 (some unnecessary explanation that could be tightened) rather than anchor 4, because those sections are genuinely unnecessary tokens.

3 / 5

Actionability

The Portal API search example is fully executable Python, and concrete endpoint URLs plus rate-limit guidance are given; however, the four "common use cases" snippets are mostly URL-construction fragments without a request/parse step, and the bulk-download pattern lists steps with no commands. Mostly executable with minor gaps, matching anchor 4; the complete executable examples and the detailed api_reference.md keep it above anchor 3.

4 / 5

Workflow Clarity

The bulk-download pattern presents a clear 4-step sequence (search, extract URLs, download, process), but it is a batch operation with no validation checkpoints; error-handling guidance (check HTTP status codes, exponential backoff on 429) exists only as disconnected best-practice bullets rather than in-workflow checkpoints. Per the rubric's batch-operation rule, workflow clarity is capped at 3.

3 / 5

Progressive Disclosure

The body serves as a genuine overview, and the single bundle file references/api_reference.md exists, is one level deep, well-organized (endpoint-oriented sections with executable examples), and clearly signaled both inline ("Consult `references/api_reference.md` for detailed endpoint documentation") and in a Resources section that states its contents and when to load it. The body's use-case-oriented examples complement rather than duplicate the reference, matching anchor 5.

5 / 5

Total

15

/

20

Passed

Description

66%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 specific, domain-natural description that clearly states what the skill does with concrete actions and good trigger terminology. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness and slightly blurs distinctiveness against sibling sequence-database skills.

Suggestions

Add an explicit trigger clause, e.g., "Use when working with ENA/EBI accessions (ERR/SRR/PRJ/DRR), retrieving sequencing data, or integrating European Nucleotide Archive data into pipelines."

Replace the vague "Supports multiple formats" with the concrete formats handled (FASTQ, FASTA, EMBL, XML, TSV) to strengthen specificity and trigger terms.

Mention metadata/taxonomy search and bulk FTP/Aspera download capabilities to round out action coverage.

DimensionReasoningScore

Specificity

"Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession" and "via API/FTP" list several concrete actions, but coverage has gaps (no search-by-metadata, taxonomy, or bulk download) and "Supports multiple formats" is vague filler. This sits at anchor 4 rather than 5 because the action list is not comprehensive, and above anchor 3 because more than 1-2 concrete actions are named.

4 / 5

Completeness

The "what" is clear (access ENA via API/FTP to retrieve sequences, reads, assemblies), but there is no "Use when..." clause or equivalent explicit trigger guidance; "for genomics and bioinformatics pipelines" is only a weak implication. Per the rubric guideline, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural user-facing terms like "FASTQ", "raw reads", "genome assemblies", "accession", "genomics", "bioinformatics", and "European Nucleotide Archive" are present, but common synonyms and extensions are missing (e.g., FASTA, "sequencing data", "transcriptome"). Anchor 5 requires comprehensive coverage including synonyms and file extensions, which this does not reach.

4 / 5

Distinctiveness Conflict Risk

Naming "European Nucleotide Archive" establishes a clear niche, but generic capability terms like "raw reads", "genome assemblies", and "DNA/RNA sequences" would also trigger closely related sequence-archive skills (e.g., an NCBI SRA/GenBank skill). Mostly distinct with minor overlap risk, matching anchor 4 rather than anchor 5's minimal-conflict profile.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/ena-database/SKILL.md

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.