CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-sequence-retrieval

Retrieve DNA/RNA/protein sequences from NCBI and ENA with disambiguation. Quality hierarchy: RefSeq (NM_/NP_) > RefSeq predicted (XM_/XP_) > GenBank submissions. Use for fetching specific sequences by accession, gene-symbol-to-sequence lookup, transcript-isoform retrieval, and curated-vs-raw-submission preference.

63

Quality

74%

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 ./plugins/tooluniverse/skills/tooluniverse-sequence-retrieval/SKILL.md

The canonical home for this skill is tooluniverse-sequence-retrieval in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

The content is well-structured and actionable, with executable tool-call examples and a clear phased workflow. Its main weaknesses are redundancy between the Domain Reasoning and Reasoning Framework sections and the absence of explicit post-retrieval validation checkpoints.

Suggestions

Consolidate the 'Domain Reasoning' and 'Reasoning Framework' sections, which restate the same RefSeq/GenBank hierarchy and version-number guidance, to remove duplication and improve conciseness.

Add an explicit validation checkpoint in Phase 2 — e.g., verify the retrieved accession's organism/strain matches the query before reporting — to strengthen workflow clarity for retrieval operations.

Validate the assumed response structure (result['data']['uids']) in the code example, or note the expected schema, so the guidance is fully copy-paste ready rather than relying on an assumed shape.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining concepts Claude already knows, but the 'Domain Reasoning' and 'Reasoning Framework' sections substantially overlap ('Prefer RefSeq over GenBank', 'Check version numbers' appear in both), which is unnecessary duplication that could be tightened.

3 / 5

Actionability

Provides concrete, mostly executable tool-call examples with parameters (NCBI_search_nucleotide, NCBI_get_sequence, ena_get_entry), decision trees, fallback chains, and an error-handling table, with only minor gaps such as assuming an unvalidated response structure (result['data']['uids']).

4 / 5

Workflow Clarity

A clear four-phase sequence (Phase 0–3) is present with a workflow diagram and error handling, but verification checkpoints are implicit rather than explicit — there is no step validating that a retrieved sequence matches the expected organism/strain, which fits the 'sequence present but checkpoints missing or implicit' anchor.

3 / 5

Progressive Disclosure

The single self-contained file is well-organized with clear section headers and no buried or nested references, and the absence of bundle files is appropriate; minor organization gaps (the overlapping Domain Reasoning/Reasoning Framework sections) keep it just below a 5.

4 / 5

Total

14

/

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.

The description is specific, distinctive, and complete, clearly stating both the capability and a concrete 'Use for ...' trigger list in third-person voice. Its only gaps are a few missing natural synonyms (e.g., fasta) that keep trigger-term quality and specificity just below the top anchor.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Retrieve DNA/RNA/protein sequences', 'fetching specific sequences by accession', 'gene-symbol-to-sequence lookup', 'transcript-isoform retrieval' — with strong but not fully exhaustive coverage, fitting the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.

4 / 5

Completeness

Explicitly answers both 'what' ('Retrieve DNA/RNA/protein sequences from NCBI and ENA with disambiguation') and 'when' via a concrete 'Use for ...' clause listing specific trigger tasks, matching the anchor for clearly and explicitly answering both what and when.

5 / 5

Trigger Term Quality

Includes natural terms users would say ('DNA/RNA/protein sequences', 'gene-symbol-to-sequence lookup', 'transcript-isoform retrieval') with good keyword coverage, but misses some common synonyms or file extensions (e.g., 'fasta', '.fasta') that a 5 would require.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — biological sequence retrieval from NCBI and ENA — with domain-specific trigger phrases and database names, giving it distinct triggers and minimal conflict risk with unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
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.