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.

72

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable, well-structured body with concrete code and clear phases. Consolidating overlapping reasoning sections and moving reference tables into bundled files would improve both conciseness and progressive disclosure.

Suggestions

Merge 'Domain Reasoning' and 'Reasoning Framework' into a single concise section to remove overlapping content and save tokens.

Move the 'Tool Reference', 'Search Parameters Reference', and 'Curation Level Tiers' tables into separate bundle files (e.g., references/tools.md) referenced one level deep from the body.

Add an explicit validate→fix→retry checkpoint in Phase 2 (e.g., confirm retrieved accession/version before reporting) to strengthen the feedback loop for retrieval operations.

DimensionReasoningScore

Conciseness

Lean and table-driven with minimal conceptual padding, assuming Claude's competence; the 'Domain Reasoning' and 'Reasoning Framework' sections partially overlap and could be consolidated for tighter token efficiency.

4 / 5

Actionability

Provides copy-paste-ready Python snippets with real tool names and parameters, plus parameter references, fallback chains, and an error-handling table covering common cases.

5 / 5

Workflow Clarity

Clear four-phase sequence with decision trees, identity checklist, and report checklist, but recovery relies on fallback chains and an error table rather than an explicit validate→fix→retry feedback loop checkpoint.

4 / 5

Progressive Disclosure

Well-organized with clear section headers, but at ~140 lines it inlines reference material (tool reference, search parameters, curation tiers) that could be split into separate bundle files; no external references are used.

4 / 5

Total

17

/

20

Passed

Description

92%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 strong, specific description that clearly communicates both capability and trigger conditions with concrete domain terminology. Minor room to add everyday synonyms and file-format triggers for broader natural-language matching.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—'fetching specific sequences by accession', 'gene-symbol-to-sequence lookup', 'transcript-isoform retrieval', 'curated-vs-raw-submission preference'—plus disambiguation and the RefSeq/GenBank quality hierarchy, giving comprehensive coverage.

5 / 5

Completeness

Explicitly states both what the skill does ('Retrieve DNA/RNA/protein sequences from NCBI and ENA with disambiguation') and when to use it via a concrete 'Use for...' clause enumerating four trigger scenarios.

5 / 5

Trigger Term Quality

Good coverage of domain terms ('DNA/RNA/protein sequences', 'accession', 'gene-symbol', 'transcript-isoform'), but leans technical and omits common synonyms or file extensions a less expert user might say (e.g., 'FASTA', 'gene sequence').

4 / 5

Distinctiveness Conflict Risk

Narrow, well-defined niche anchored to specific databases (NCBI/ENA) and the RefSeq-vs-GenBank curation distinction, minimizing overlap with other skills.

5 / 5

Total

19

/

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.