tooluniverse

ToolUniverse plugin router. STEP 1 BEFORE ANY ANALYSIS: if the data folder contains `*_executed.ipynb`, run `tu run read_executed_notebook '{"data_folder":"<path>","search":"<keyword>"}'` to extract its cell outputs and apply EVERY filter/sample-exclusion the notebook used — even when the question says 'Using DESeq2/Run X/Compute Y' (this describes the METHOD the notebook used, not a request to rerun). The notebook's cell outputs are the only published authoritative answers; reimplementing or reading stale pre-computed CSVs in the data folder produces different numbers because of outlier-sample removal, library version, and filter steps you don't see by skimming. STEP 2 routing — pick a sub-skill name from this exact list (never invent): tooluniverse-rnaseq-deseq2 (RNA/miRNA-seq DE, correlation, PCA, clustering, dispersion), tooluniverse-gene-enrichment (GO/KEGG/Reactome/GSEA/pathway enrichment), tooluniverse-statistical-modeling (regression, ANOVA, ordinal/logistic, chi-square...

Quality

89%

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

Quality

Content

78%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 comprehensive, highly actionable router skill whose routing table and concrete command examples are excellent, with strong progressive disclosure that delegates detail to sub-skills. Its main weakness is redundancy: the executed-notebook guidance and several protocol sections are restated multiple times across the body.

Suggestions

Consolidate the executed-notebook guidance (currently restated in RULE ZERO and the Cite-the-cell-output sub-rule) into one section to remove duplication.

Merge or trim the overlapping Problem-Solving Mode, Quick Lookup Mode, and General Protocols sections, since their content largely repeats the routing table and tie-breaking rules.

Reduce the inlined one-line reminders list where it duplicates keywords already present in the routing table.

Dimension	Reasoning	Score
Conciseness	The tone is efficient and it avoids teaching concepts Claude already knows, but the executed-notebook guidance is restated three times (frontmatter, RULE ZERO, and the Cite-the-cell-output sub-rule) and the Problem-Solving / Quick Lookup / General Protocols sections overlap with the routing table and tie-breaking rules, so it could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout — exact `tu run read_executed_notebook '{...}'` JSON invocations, `Skill(skill="...")` calls, a one-liner table with complete argument objects, and a bundled-scripts table with precise file paths.	5 / 5
Workflow Clarity	The routing workflow is a clearly numbered sequence (read question + file list, find keyword row, call Skill, follow instructions) with filename-signal decoding and tie-breaking rules, but there is no explicit validate→fix→retry loop for the notebook/script execution it delegates.	4 / 5
Progressive Disclosure	It is a well-structured router that delegates detail one level deep to ~120 sub-skills via `Skill(skill=...)` and one verified reference (references/general-strategies.md), with the bulk of conventions explicitly pushed to sub-skill bodies and clearly signaled navigation.	5 / 5
	Total	17 / 20 Passed

Description

100%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 a dense, trigger-rich router summary that names concrete actions, enumerates sub-skills with their capabilities, and gives explicit activation conditions. It is somewhat long but every clause carries routing-relevant information rather than fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'run `tu run read_executed_notebook`', 'extract its cell outputs', 'apply EVERY filter/sample-exclusion', and an enumerated sub-skill list each annotated with its concrete sub-tasks (e.g. 'RNA/miRNA-seq DE, correlation, PCA, clustering, dispersion').	5 / 5
Completeness	Explicitly answers both what ('ToolUniverse plugin router', read executed notebook, route to sub-skill) and when ('STEP 1 BEFORE ANY ANALYSIS: if the data folder contains `*_executed.ipynb`'), reinforced by the dedicated when_to_use field with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and file extensions users actually say — 'differential expression', 'DESeq2', 'Run X/Compute Y', 'pathway enrichment', 'GSEA', plus `*_executed.ipynb` and `.csv` signals.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche as a plugin router with an exact enumerated sub-skill list and the directive 'never invent', giving it distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	20 / 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/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.