svm-model-importance-analysis

Use when you need a standardized R CLI workflow to run two-class SVM-RFE feature ranking on an expression-like matrix, choose an informative feature count from cross-validated error, and generate reproducible ranking and error plots. NOT for regression, multi-class classification, missing-value imputation, or remote data fetching.

Quality

87%

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

82%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 body is well-structured and highly actionable with a clear navigation table, executable commands, and built-in validation. Weakest on conciseness (a large styling-arg table) and progressive disclosure (broken references to a non-existent tests/ directory).

Suggestions

Move the verbose plot-styling argument rows (--svm_error_*_color, cex, lty, label_pos, etc.) into references/cli-guide.md and keep only the core analytical flags in SKILL.md.

Either add the referenced tests/ directory (tests/data/, tests/run_tests.R) or remove the Testing-section commands and 'tests/data' nav-table row that point to files not shipped in the bundle.

Add an explicit numbered validate->fix->retry sequence (e.g. run -> check exit code 0 -> on SKILL_* error consult troubleshooting.md -> re-run) to strengthen the workflow feedback loop.

Dimension	Reasoning	Score
Conciseness	Body is lean and assumes Claude's knowledge (no SVM concept padding), but the long table of plot-styling arguments (line colors, cex, lty, etc.) is detail that could live in references/cli-guide.md.	4 / 5
Actionability	Provides fully executable, copy-paste-ready Rscript commands with concrete arguments, concrete CSV input examples, and a direct test command covering the common cases.	5 / 5
Workflow Clarity	Validation is present via exit codes (0/1), standardized error codes, path containment checks, and a troubleshooting reference, but the body lacks an explicit numbered validate->fix->retry feedback loop.	4 / 5
Progressive Disclosure	The 'When to Read External Files' navigation table cleanly maps situations to one-level-deep reference files that exist, but the body also references tests/data/ and tests/run_tests.R which are not present in the bundle.	4 / 5
	Total	17 / 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 highly distinct, with concrete trigger phrasing and a useful negative boundary. The only weakness is trigger-term breadth — it could add common synonyms and file extensions users naturally mention.

Suggestions

Add a few natural synonyms and file extensions to broaden trigger matching, e.g. 'feature selection', 'model importance', or '.csv/.tsv expression matrices'.

Consider including 'feature selection' alongside 'feature ranking' since users often phrase the request that way.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'run two-class SVM-RFE feature ranking', 'choose an informative feature count from cross-validated error', 'generate reproducible ranking and error plots' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (three concrete actions) and 'when' via the 'Use when you need...' clause, plus a concrete 'NOT for...' negative boundary.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('SVM-RFE feature ranking', 'cross-validated error', 'ranking and error plots'), but missing common synonyms and file extensions a user might actually say, so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (two-class SVM-RFE on expression-like matrices) with explicit exclusions ('NOT for regression, multi-class classification...'), keeping conflict risk minimal.	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/svm-model-importance-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~9 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.