CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a dense, actionable ncRNA pipeline with concrete code and a clear phase structure, but it suffers from internal redundancy (duplicate Limitations headers, repeated target lists) and lacks validation feedback loops for its fragile batch download procedures. The long computational procedures belong in a separate reference rather than inline.

Suggestions

Consolidate the two `## Limitations` sections into one and de-duplicate the miR-21 target lists (lines 113 and 166) and the mechanism descriptions repeated across Key principles, Type-based reasoning, and Phase 0/1.

Add explicit validation/verification checkpoints to the TargetScan and miRTarBase download-and-process procedures (e.g., verify the download succeeded and the expected columns exist before querying), with a fix-and-retry loop on failure.

Move the TargetScan and miRTarBase download-and-process scripts into a separate reference file (e.g., references/computational-procedures.md) and reference it one level deep from the main body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept filler, but contains real redundancy: two separate `## Limitations` headers (lines 186 and 251), repeated miR-21 target enumerations (lines 113 and 166), and mechanisms restated across the Key principles list, Type-based reasoning paragraph, and Phase 0/1 sections that could be tightened.

2 / 3

Actionability

Provides copy-paste-ready executable examples with exact arguments (`ENCORI_get_miRNA_targets(mirna="hsa-miR-21-5p", clip_min=1)`, full TargetScan and miRTarBase pandas download-and-process scripts) and a concrete tool-to-use table, satisfying the fully-executable anchor.

3 / 3

Workflow Clarity

A clear 5-phase sequence with an ASCII flow diagram and tool-selection rules is present, but the fragile batch download-and-process procedures (TargetScan, miRTarBase) lack explicit validate/verify checkpoints or error-recovery feedback loops, which caps workflow clarity at 2 per the batch-operations guideline.

2 / 3

Progressive Disclosure

Sections are reasonably labeled and navigable (When to Use, Core Tools, Workflow, Limitations) with no bundle files present, but the two substantial inline computational procedures (TargetScan/miRTarBase download-and-process) are advanced off-path content that should be split into a one-level-deep reference file rather than kept inline.

2 / 3

Total

9

/

12

Passed

Description

100%

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, trigger-rich, complete, and distinct: it names concrete ncRNA classes, databases, and tasks and provides an explicit 'Use for' clause covering four scenarios. It is among the strongest descriptions on the rubric.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions across ncRNA classes ("miRNAs (miRBase, miRDB targets)", "lncRNAs (LNCipedia, RNAcentral)", "circRNAs, snoRNAs") and four distinct tasks (function prediction, target prediction, functional annotation, disease associations), matching the anchor for multiple specific actions.

3 / 3

Completeness

Explicitly answers what ("Non-coding RNA analysis ... Distinct mechanisms per class") and when via an explicit "Use for ..." clause listing four trigger scenarios, satisfying the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Good coverage of natural domain terms a user would say ("miRNA-target prediction", "lncRNA functional annotation", "ncRNA-disease association", "miRNAs", "lncRNAs", "circRNAs", "snoRNAs") across both ncRNA classes and task types.

3 / 3

Distinctiveness Conflict Risk

A clear niche (specific ncRNA classes plus named databases miRBase/miRDB/LNCipedia/RNAcentral and specific tasks) with distinct triggers unlikely to overlap with adjacent skills.

3 / 3

Total

12

/

12

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.