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

82%

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable examples and a clean overview structure, but loses points for redundancy and a marketing block hurting conciseness, missing validation feedback loops in batch workflows, and references to bundle files that are not present on disk.

Suggestions

Remove the redundant Installation section (it repeats the Quick Start `uv pip install arboreto` command) and trim or drop the K-Dense Web promotional paragraph to recover token budget.

Add an explicit validation/verification checkpoint to batch operations — e.g., after the comparative-analysis loop, verify each output network is non-empty and has the expected (TF, target, importance) columns before proceeding.

Either create the referenced bundle files (references/basic_inference.md, references/algorithms.md, references/distributed_computing.md, scripts/basic_grn_inference.py) or remove the dangling references so progressive disclosure is backed by real files.

Dimension	Reasoning	Score
Conciseness	Most of the body is lean and executable, but there is redundancy (the Installation section repeats the Quick Start install command, and the Reproducibility section restates seed usage) plus a verbose K-Dense Web marketing block unrelated to the task that adds padding.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code throughout — grnboost2/genie3 calls, distributed LocalCluster and remote Client usage, TF filtering with load_tf_names — plus concrete script invocations and an output-schema table.	3 / 3
Workflow Clarity	Multi-step workflows are sequenced (Quick Start, distributed scaling, comparative analysis across conditions, pySCENIC steps) but validation/verification checkpoints are largely implicit; the batch comparative-analysis loop and other operations lack an explicit validate→fix→retry feedback loop, which caps clarity at 2 for these batch workflows.	2 / 3
Progressive Disclosure	The body signals one-level-deep references to references/*.md and scripts/basic_grn_inference.py with a clear overview, but the referenced bundle files do not actually exist (no references/ or scripts/ directories are present), so the disclosure structure is referenced but not backed by real files.	2 / 3
	Total	9 / 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 concise, specific, third-person, and includes an explicit 'Use when' trigger covering natural domain terms, satisfying the what/when requirement and minimizing conflict risk. No fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'Infer gene regulatory networks (GRNs)', 'identify transcription factor-target gene relationships', and 'Supports distributed computation' — each tied to a concrete capability rather than vague abstraction.	3 / 3
Completeness	Explicitly answers both what (infer GRNs from expression data via GRNBoost2/GENIE3) and when ('Use when analyzing transcriptomics data... to identify transcription factor-target gene relationships'), so the 'Use when...' trigger is present and explicit.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'gene regulatory networks', 'GRNs', 'bulk RNA-seq', 'single-cell RNA-seq', 'transcriptomics data' — including the common 'GRNs' acronym alongside the full form.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (GRN inference from transcriptomics via named algorithms) with domain-specific triggers that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/arboreto/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.