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

88%

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

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.

A highly actionable, code-rich skill body with well-organized references to real bundle files. Main weaknesses are redundant boilerplate across use cases and missing validation checkpoints in the (batch-capable) workflows.

Suggestions

Add an explicit validation/checklist step before inference (e.g., verify genes-as-columns orientation and that tf_names match gene names) so batch and multi-condition workflows have a checkpoint.

Deduplicate the install command and collapse the three near-identical use-case code blocks into one parameterized example, relying on references for variations.

Move the multi-condition and multi-seed reproducibility examples into a reference file, keeping SKILL.md as a lean overview pointing to references/.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and code-driven, but the install command is duplicated (Quick Start and Installation sections), the `if __name__ == '__main__'` boilerplate recurs across three use-case blocks, and the seed concept is restated in Reproducibility after already being shown.	4 / 5
Actionability	Fully executable, copy-paste-ready code throughout — quick start, algorithm comparison, distributed clients, and three use cases — plus a runnable CLI script invocation covering the common case.	5 / 5
Workflow Clarity	Steps are present (load → infer → save) but lack validation checkpoints; the multi-condition loop is a batch operation with no verify step, and data-format/TF-name checks appear only in Troubleshooting rather than as inline checkpoints.	3 / 5
Progressive Disclosure	Good structure with real one-level-deep references clearly signaled ("See references/basic_inference.md", "For detailed algorithm comparison…references/algorithms.md") and a ready script, but the body inlines three full use-case code blocks plus reproducibility/troubleshooting that keep it from a lean overview.	4 / 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.

A strong, third-person description that concisely states the capability, names the concrete algorithms, and gives an explicit "Use when" trigger with natural domain keywords. No fluff or over-claims; every phrase earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Infer gene regulatory networks", "identify transcription factor-target gene relationships and regulatory interactions", "Supports distributed computation") plus named algorithms (GRNBoost2, GENIE3), giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both what (infer GRNs, identify TF-target relationships) and when ("Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq)") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms researchers actually say — "gene regulatory networks", "GRNs", "transcriptomics data", "bulk RNA-seq", "single-cell RNA-seq" — including synonyms and the GRN acronym.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (GRN inference from transcriptomics data) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/arboreto/SKILL.md
Commit: 3a6c3a9

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.