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%

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 executable code and good progressive disclosure to real bundle files, but it carries redundancy (repeated install and Dask-client snippets) and lacks explicit validation checkpoints in its workflows. Tightening the repeated examples and adding a verify step would lift the two weaker dimensions.

Suggestions

Consolidate the duplicated install command and the Dask LocalCluster/Client setup (currently shown in both Distributed Computing and Reproducibility) into one place and reference it from the other.

Trim the three Common Use Cases examples that repeat the identical grnboost2 call, or fold the distinguishing detail (tf_names, seed, multi-condition loop) into one parameterized example.

Add an explicit verification checkpoint after inference — e.g., inspect the output DataFrame shape/columns or check for empty results — so the workflow has a validate-then-proceed step.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with actionable code, but redundancy that could be tightened: the install command appears twice (Quick Start and Installation), the Dask client/LocalCluster setup is repeated in Distributed Computing and again in Reproducibility, and the Common Use Cases examples repeat the same grnboost2 call several times.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code and specific commands — `uv pip install arboreto`, `python scripts/basic_grn_inference.py expression_data.tsv output_network.tsv --tf-file tfs.txt --seed 777`, and complete import/inference snippets — matching the executable anchor.	3 / 3
Workflow Clarity	The basic flow is sequenced (load → infer → save) with a useful "Critical" note on the __main__ guard, but there are no explicit validation/verification checkpoints for this batch compute operation, and Troubleshooting gives hints rather than a validate→fix→retry loop.	2 / 3
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references ("See: references/basic_inference.md", "For detailed algorithm comparison...: references/algorithms.md", "For cluster setup...: references/distributed_computing.md") plus a ready-to-run script; all four referenced bundle files exist.	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 concise, specific, and complete, naming concrete algorithms and explicit trigger conditions in third-person voice. It clearly communicates both capability and when to invoke it without fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Infer gene regulatory networks (GRNs) from gene expression data", "using scalable algorithms (GRNBoost2, GENIE3)", "identify transcription factor-target gene relationships and regulatory interactions", and "Supports distributed computation" — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what ("Infer gene regulatory networks... using GRNBoost2, GENIE3") and when ("Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships"), with an explicit "Use when" trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "gene regulatory networks", "GRNs", "gene expression data", "transcriptomics data", "bulk RNA-seq", "single-cell RNA-seq", "transcription factor-target gene relationships" — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche — GRN inference from transcriptomics data via named algorithms — with distinct triggers unlikely to fire for unrelated skills; third-person voice ("Infer", "Supports") avoids the first/second-person penalty.	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
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: 52845c3

Reviewed: about 11 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.