tooluniverse-gene-regulatory-networks

Gene regulatory network analysis — TF-target inference (JASPAR motifs, ChIP-seq), motif scanning, eQTL integration, perturbation evidence (knockout/overexpression). Use for 'which TF regulates gene X', 'which genes does TF Y target', regulatory pathway reconstruction. Distinguishes direct (binding) vs indirect (co-expression) regulatory evidence.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

72%

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 concrete tool calls and a clear multi-phase workflow, but loses points for some explanatory padding and the absence of explicit validation/verification checkpoints on batch data-retrieval operations.

Suggestions

Add explicit validation/verification steps (e.g., 'verify enriched terms have adjusted_p_value < 0.05 before reporting; if none qualify, broaden the library and re-run') to the workflow phases so batch operations include a validate-fix-retry loop.

Tighten the opening evidence-grading paragraph and histone-mark definitions to assume Claude's domain knowledge, keeping only the decision-relevant distinctions (e.g., T1 vs T3 evidence ordering).

Consider moving the lengthy per-tool parameter tables into a references file so the main SKILL.md reads as a workflow overview pointing to one-level-deep tool details.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with terse tool parameter blocks and JSON examples, but includes some explanatory prose (the opening evidence-grading paragraph, histone-mark meanings) that partly restates domain knowledge Claude already knows. Not level 3 because this padding could be tightened; not level 1 because the bulk is lean tool documentation.	2 / 3
Actionability	Provides concrete, executable tool calls with real parameter blocks and valid JSON examples (e.g., {"search": "TP53", "limit": 5}) that are copy-paste ready. Not level 2 because the guidance is fully concrete rather than pseudocode or incomplete.	3 / 3
Workflow Clarity	Clear multi-phase sequence (Phase 0-7) with input disambiguation and use patterns, but no explicit validation/verification checkpoints (validate->fix->retry) on batch enrichment operations. Capped at 2 per the rubric because validation checkpoints are missing for batch operations.	2 / 3
Progressive Disclosure	Single-file skill with no bundle files, organized into clear one-level sections (When to Use, Workflow phases, Common Mistakes, Patterns, Evidence Grading) with no nested references. Not level 2 because the content is well-organized and appropriately sectioned for a single-file skill.	3 / 3
	Total	10 / 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 excellent: it names concrete capabilities tied to specific databases, provides explicit natural-language triggers covering both 'what' and 'when', and occupies a distinct niche unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions with specific data sources: 'TF-target inference (JASPAR motifs, ChIP-seq)', 'motif scanning', 'eQTL integration', 'perturbation evidence'. Not level 2 because it lists several specific concrete actions rather than a single domain-action pair.	3 / 3
Completeness	Explicitly answers both what ('TF-target inference... motif scanning, eQTL integration') and when ('Use for "which TF regulates gene X"...'). Not level 2 because the 'when' trigger clause is explicit, not merely implied.	3 / 3
Trigger Term Quality	Includes natural phrasing users would say: 'which TF regulates gene X', 'which genes does TF Y target', 'regulatory pathway reconstruction'. Not level 2 because it covers common natural variations rather than only a single keyword.	3 / 3
Distinctiveness Conflict Risk	Distinct niche (gene regulatory networks) with specific triggers unlikely to overlap with other skills. Not level 2 because the triggers ('which TF regulates gene X', JASPAR/ChIP-seq/eQTL) are specific to this domain.	3 / 3
	Total	12 / 12 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: plugin/skills/tooluniverse-gene-regulatory-networks/SKILL.md
Commit: 089eb8e

Reviewed: about 5 hours 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.