rf-model-importance-analysis

Use when you need a standardized R CLI workflow to train a two-class random forest model from an expression-like feature matrix, rank variable importance, and generate reproducible error and importance plots. NOT for regression tasks, multi-class classification, missing-value imputation, preprocessing, or remote data fetching.

Quality

89%

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

86%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.

The content is highly actionable and well-structured, with copy-paste commands, a complete argument reference, and clean progressive disclosure to verified external files. The only meaningful gap is minor redundancy across command examples and an implicit rather than explicit validation/feedback loop for batch runs.

Suggestions

De-duplicate the basic Rscript command: keep one canonical example in Quick Start and have the Usage and Testing sections reference it or show only the differing flags, to reduce token cost.

Add an explicit post-run validation checkpoint (e.g., check exit code 0, confirm output_dir/plot/*.pdf and table/*.csv exist, re-run or consult troubleshooting.md on failure) to strengthen the workflow feedback loop.

Consider moving the large argument table (or the rarely-tuned plot-styling flags) into references/cli-guide.md, leaving only the essential flags inline in SKILL.md to tighten the overview.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and is mostly efficient reference material, but the basic Rscript command is near-duplicated across Quick Start, Usage, and the Testing section, offering a minor trimming opportunity that keeps it just below fully lean.	4 / 5
Actionability	Copy-paste-ready Rscript commands with concrete paths and arguments cover the standard, tuned, and plot-only cases, backed by a complete argument table and concrete input/output examples — fully executable guidance.	5 / 5
Workflow Clarity	Clear entry points (three Quick Start modes), a situation-to-file navigation table, and explicit Stop Conditions provide a sound sequence with exit codes and standardized error codes as checkpoints, though an explicit verify-then-retry feedback loop for batch runs is only implicit.	4 / 5
Progressive Disclosure	The body is an overview that offloads detail to verified one-level-deep references (algorithm.md, troubleshooting.md, cli-guide.md, scripts/main.R) with a clear 'When to Read External Files' table mapping situation to file and purpose, giving easy navigation with no nested references.	5 / 5
	Total	18 / 20 Passed

Description

92%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 specific, complete, and distinctive, with explicit what/when guidance and a clear negative boundary that sharply limits conflict risk. It is only slightly held back from a perfect score by somewhat jargon-heavy trigger terms that omit casual synonyms and file extensions.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'train a two-class random forest model', 'rank variable importance', 'generate reproducible error and importance plots' — with comprehensive coverage of the niche, matching the anchor for listing multiple specific concrete actions.	5 / 5
Completeness	Explicitly answers what (train, rank importance, generate plots) and when (explicit 'Use when you need a standardized R CLI workflow...' trigger) plus an explicit NOT-for boundary, matching the anchor for clearly answering both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural domain terms ('random forest', 'variable importance', 'expression matrix', 'R CLI') but leans technical and omits common synonyms and file extensions, so it sits above 'some relevant keywords' yet short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	A narrow niche (two-class RF importance from an expression matrix via R CLI) with an explicit exclusion list (regression, multiclass, imputation, preprocessing, fetching) yields a clear niche with minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Data Analysis/rf-model-importance-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~6 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.