arboreto

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

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%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.

Strong, actionable content with excellent progressive disclosure and executable examples. The main weaknesses are mild redundancy, an inline time-sensitive version/date that belongs in a deprecated section, and the absence of validation checkpoints in the workflow.

Suggestions

Move the time-sensitive upstream version/date ("PyPI 0.1.6, 2021-02-09") into a dedicated 'Version / compatibility' or deprecated-patterns section instead of the Overview, and remove the Overview restatement of the frontmatter description.

Add an explicit validation/verification checkpoint to the core workflow (e.g., after inference, verify the output DataFrame has expected TF/target/importance columns and non-empty rows before saving).

Deduplicate the Quick Start code block versus the Common Use Cases section to tighten token usage.

Dimension	Reasoning	Score
Conciseness	Mostly lean and code-focused, but the Overview restates the frontmatter description, Quick Start code is duplicated in Common Use Cases, and time-sensitive version/date info ("PyPI 0.1.6 (2021-02-09, latest)") sits inline rather than in a deprecated/old-patterns section, which the rubric penalizes.	3 / 5
Actionability	Provides copy-paste-ready code with real imports and working grnboost2/genie3 calls, plus a fully executable argparse script (scripts/basic_grn_inference.py) covering the common inference cases with concrete flags.	5 / 5
Workflow Clarity	The load → infer → save sequence is present and the distributed path is step-sequenced, but there are no explicit validation or verification checkpoints; the operation is non-destructive so no hard cap applies, yet checkpoints remain absent.	3 / 5
Progressive Disclosure	The body gives a concise overview and clearly signals one-level-deep references (references/basic_inference.md, references/algorithms.md, references/distributed_computing.md) plus a runnable script, all of which exist as real files; content is appropriately split and easy to navigate.	5 / 5
	Total	16 / 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 exemplary: concrete actions, named algorithms, explicit use-when triggers with natural bioinformatics terms, and a clearly distinct niche. It answers both what and when without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Infer gene regulatory networks", "identify transcription factor-target gene relationships and regulatory interactions", "Supports distributed computation") and names the specific algorithms GRNBoost2 and GENIE3, giving comprehensive coverage.	5 / 5
Completeness	Explicitly states what it does (infer GRNs via named scalable algorithms) and gives a concrete "Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships" trigger clause answering both what and when.	5 / 5
Trigger Term Quality	Includes natural terms a bioinformatician would actually say — "gene regulatory networks", "GRNs", "transcriptomics data", "bulk RNA-seq", "single-cell RNA-seq", "regulatory interactions" — with synonyms and specific data types covered.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear specialized niche (GRN inference from expression data) with distinctive triggers unlikely to collide 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: K-Dense-AI/scientific-agent-skills
Path: skills/arboreto/SKILL.md
Commit: b2a92ba

Reviewed: 3 days 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.