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.
90
86%
Does it follow best practices?
Impact
100%
1.31xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly defines a specific bioinformatics capability with concrete algorithms, data types, and use cases. It uses proper third-person voice, includes an explicit 'Use when' clause with rich trigger terms, and occupies a highly distinctive niche. The description is concise yet comprehensive, covering what the skill does, when to use it, and what it supports.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Infer gene regulatory networks (GRNs)', 'scalable algorithms (GRNBoost2, GENIE3)', 'identify transcription factor-target gene relationships and regulatory interactions', 'distributed computation for large-scale datasets'. These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (infer GRNs using GRNBoost2/GENIE3, identify TF-target relationships, supports distributed computation) and 'when' (explicit 'Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a bioinformatics user would say: 'gene regulatory networks', 'GRNs', 'gene expression data', 'GRNBoost2', 'GENIE3', 'transcriptomics', 'bulk RNA-seq', 'single-cell RNA-seq', 'transcription factor', 'target gene', 'regulatory interactions'. These are the exact terms domain users would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: gene regulatory network inference is a very specific bioinformatics task. The mention of specific algorithms (GRNBoost2, GENIE3) and specific data types (RNA-seq, scRNA-seq) makes it extremely unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid skill with excellent actionability—every section contains executable code examples covering the main use cases. Progressive disclosure is well-handled with clear references to deeper materials. The main weaknesses are some redundancy between sections (Quick Start vs Common Use Cases, duplicate installation) and the lack of explicit validation/verification steps in the workflow, which is important for computational biology analyses where silent failures are common.
Suggestions
Add a validation step after inference (e.g., check network shape, verify TF names appear in results, sanity-check importance score distribution) to create a proper feedback loop.
Remove the duplicate installation section and consolidate the Quick Start example with the 'Basic GRN Inference' section to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundancy—the Quick Start and Common Use Cases sections overlap significantly, and the algorithm comparison section explains things Claude could infer. The installation section appears twice. Some sections like 'Integration with pySCENIC' add marginal value. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code throughout, with concrete examples for multiple use cases (single-cell, bulk RNA-seq, distributed computing). Commands are specific and complete with proper imports and guards. | 3 / 3 |
Workflow Clarity | While individual code examples are clear, there's no explicit validation workflow—no steps to verify the output network makes sense, no data validation before running inference, and no feedback loop for handling issues like empty results or poor quality networks. For a computational biology pipeline, validation checkpoints would be important. | 2 / 3 |
Progressive Disclosure | The skill has a clear overview with well-signaled one-level-deep references to `references/basic_inference.md`, `references/algorithms.md`, and `references/distributed_computing.md`. It also points to a ready-to-run script. The main file provides enough to get started while deferring detailed content appropriately. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
25e1c0f
- Reviewed
Table of Contents
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.