arboreto

Infer gene regulatory networks (GRNs) from gene expression matrices using GRNBoost2 or GENIE3; use when analyzing bulk or single-cell RNA-seq to identify TF→target regulatory relationships.

Quality

85%

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

76%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.

Actionable and well-structured content with executable examples and appropriately split reference files. The main weaknesses are missing validation/verification for a batch inference operation and minor redundancy between the body and the algorithms reference.

Suggestions

Add an explicit validation/verification checkpoint to the workflow — e.g., confirm the input matrix has genes as columns and verify the output edge list is non-empty and sorted by importance before declaring success — to lift workflow clarity above the batch-operation cap of 3.

Remove the algorithm method explanations ('uses gradient boosting...', 'uses random forests...') from the body since they duplicate references/algorithms.md and describe concepts Claude already knows; keep only the practical guidance on which to pick.

Tighten the 'When to Use' list so it does not restate the frontmatter description, preserving token budget for guidance Claude does not already have.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and minimal padding, but the 'When to Use' bullets restate the description and the 'Algorithms' section explains method behavior (gradient boosting vs random forest) that Claude already knows, so it is not fully lean.	4 / 5
Actionability	Provides two copy-paste-ready, fully executable CLI invocations covering both algorithms, with the referenced script (scripts/infer_network.py) present and matching the documented flags, covering the common cases.	5 / 5
Workflow Clarity	The single-command flow is unambiguous, but this is a batch operation (whole expression matrix → network) with no input validation or output-verification checkpoints described, so per the batch-operation cap it cannot exceed 3.	3 / 5
Progressive Disclosure	Good structure with a clear overview and well-signaled one-level-deep references to real files (references/algorithms.md, references/distributed_computing.md), but the body's 'Algorithms' and 'Implementation Details' duplicate content also found in algorithms.md, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

95%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 states both capability and trigger conditions using natural domain terminology with good synonym coverage. The only minor gap is that the listed actions are facets of a single inference task rather than multiple distinct operations.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('Infer gene regulatory networks', 'identify TF→target regulatory relationships') with two named algorithms, but the actions are variations of one inference task rather than several distinct operations, so it falls just below the comprehensive-coverage anchor.	4 / 5
Completeness	Explicitly answers both 'what' ('Infer gene regulatory networks from gene expression matrices using GRNBoost2 or GENIE3') and 'when' ('use when analyzing bulk or single-cell RNA-seq to identify TF→target regulatory relationships') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural domain terms and synonyms a user would say — 'gene regulatory networks (GRNs)', 'gene expression matrices', 'bulk or single-cell RNA-seq', 'GRNBoost2 or GENIE3', 'TF→target' — giving comprehensive keyword coverage including acronyms and data-type variants.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (GRN inference from RNA-seq via two specific algorithms) with distinct triggers, making conflict with other skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/arboreto/SKILL.md
Commit: 63c61d3

Reviewed: 3 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.