tooluniverse-noncoding-rna

Non-coding RNA analysis — miRNAs (miRBase, miRDB targets), lncRNAs (LNCipedia, RNAcentral), circRNAs, snoRNAs, and other ncRNA classes. Distinct mechanisms per class — miRNAs repress mRNA; lncRNAs scaffold/decoy/enhance. Use for ncRNA function prediction, miRNA-target prediction, lncRNA functional annotation, and ncRNA-disease association queries.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-noncoding-rna/SKILL.md

Quality

Content

71%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 body is highly actionable with a clear multi-phase workflow and executable examples, but it is over-long for a SKILL.md overview and inlines substantial background/reference material that would be better externalized into bundle files.

Suggestions

Move the TargetScan and miRTarBase download-and-process procedures plus the target/disease reference tables into separate reference files (e.g., references/target-prediction.md) and link to them one level deep.

Trim the hardcoded target and disease-association catalogs, which largely restate domain knowledge Claude already has, in favor of pointing to the live tools.

Add an explicit verification checkpoint in Phase 1 (e.g., 'Confirm at least one T1/T2 target before proceeding to enrichment') to strengthen workflow validation.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich, but inlines sizable background knowledge (ncRNA class definitions, hardcoded miR-21/miR-155 target lists, and a long disease-association catalog) that Claude largely knows and that could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance with real tool calls and parameters (ENCORI_get_miRNA_targets, ReactomeAnalysis_pathway_enrichment, STRING_get_network) and complete TargetScan/miRTarBase download-and-process Python covering common cases.	5 / 5
Workflow Clarity	A clear 5-phase sequence (Identity → Targets → Expression → Disease → Functional Interpretation) with an ASCII diagram and per-phase tool choices, though validation is interpretive (T1-T4 evidence grading) rather than explicit checkpoint/error-recovery feedback loops.	4 / 5
Progressive Disclosure	Well-organized into sections, but at ~250 lines it inlines content that belongs in separate reference files (the TargetScan and miRTarBase download procedures, large reference tables) and references no external bundle files at all.	3 / 5
	Total	15 / 20 Passed

Description

78%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, distinct, and answers both what and when with concrete use-case triggers, though the 'Use for' phrasing is marginally less explicit about user utterances than the ideal 'Use when the user mentions...' form.

Suggestions

Replace 'Use for ...' with an explicit 'Use when the user asks about ...' trigger clause listing natural query phrasings (e.g., 'Use when the user asks for miRNA targets, lncRNA function, or ncRNA-disease associations').

Add natural synonyms such as 'noncoding RNA', 'ncRNA targets', and '.gff/.gtf annotation' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('ncRNA function prediction, miRNA-target prediction, lncRNA functional annotation, and ncRNA-disease association queries') and names specific databases/classes, with only minor coverage gaps versus the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both 'what' (ncRNA analysis with class-specific mechanisms) and 'when' ('Use for ... prediction/annotation/association queries'); the 'Use for' clause gives concrete trigger use-cases but is slightly less explicit about user utterances than the score-5 'Use when the user mentions...' form.	4 / 5
Trigger Term Quality	Includes natural domain keywords users would say (miRNAs, lncRNAs, circRNAs, snoRNAs, miRNA-target prediction, ncRNA-disease association) with good coverage, though a few natural synonyms/query phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (non-coding RNA) with distinct named databases (miRBase, LNCipedia, RNAcentral) and class-specific mechanisms, giving minimal conflict risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-noncoding-rna/SKILL.md
Commit: 1b02920

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.