CtrlK
BlogDocsLog inGet started
Tessl Logo

elastic-net-feature-selection

Use when selecting predictive genes or other molecular features from bulk expression matrices for binary case-vs-control classification with elastic net logistic regression, including coefficient path and cross-validation plots. Trigger keywords: elastic net, glmnet, feature selection, binary classification, lambda.min, lambda.1se. NOT for: survival/Cox modeling, multiclass outcomes, single-cell data, or non-expression tables.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./awesome-med-research-skills/Data Analysis/elastic-net-feature-selection/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, highly actionable skill body with good progressive disclosure and a validated workflow. The main weaknesses are repeated explanatory content (conciseness) and references to bundled test data that does not actually exist in the package.

Suggestions

State the 'alpha=0 ridge writes empty selected_features.csv' behavior once (e.g. in the Output Files table) and remove the duplicate explanations in the Automatic Alpha Selection and Feature Selection Rule sections to recover tokens.

Either add a tests/data/ directory with the sample expression_matrix.csv, groups.csv, and genes.csv referenced by the Testing and cli-guide sections, or rewrite those commands to use placeholder user-supplied file paths so they are runnable as written.

Drop the 'Last updated: 2026-04-20 | Version: 1.0.0' footer (or move version info into a deprecated/changes section), and trim the Methods paragraph that re-explains L1/L2 elastic-net penalties Claude already knows.

DimensionReasoningScore

Conciseness

The body is mostly efficient tables and command blocks, but the 'alpha=0 ridge → empty selected_features.csv' note is stated three times (Output Files table, Automatic Alpha Selection, Feature Selection Rule), the Methods section restates the L1/L2 elastic-net concept Claude already knows, and a time-sensitive 'Last updated / Version' footer adds noise.

3 / 5

Actionability

Fully parameterized, copy-paste-ready Rscript invocations cover first-run, fixed-alpha, conservative-lambda, and custom-label cases plus a complete arguments table. The one gap is the Testing section, whose commands target tests/data/* files that are not present in the bundle.

4 / 5

Workflow Clarity

A clearly sequenced four-step Workflow opens with an explicit 'Step 1: Validate Input' checkpoint (existence, empty-data, column, sample-match, out-of-scope label rejection) and the Error Handling table provides a cause→solution→read-more feedback loop, so the batch-operation cap at 3 does not apply.

4 / 5

Progressive Disclosure

The 'When to Read External Files' table gives well-signaled, one-level-deep navigation to references/algorithm.md, cli-guide.md, and troubleshooting.md (all present in the bundle), with detail appropriately split out; the dangling references to a non-existent tests/data/ directory are the main organization gap.

4 / 5

Total

15

/

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.

A strong, specific description with explicit trigger keywords and a clear use/boundary structure in appropriate third-person voice. Minor headroom only in trigger-term synonym coverage.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'selecting predictive genes', 'elastic net logistic regression', 'coefficient path and cross-validation plots' for 'binary case-vs-control classification' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

It explicitly answers both 'what' (feature selection via elastic net LR with coefficient/CV plots) and 'when' ('Use when selecting predictive genes…for binary case-vs-control classification'), supplemented by a concrete 'NOT for:' boundary.

5 / 5

Trigger Term Quality

It explicitly enumerates natural trigger keywords ('elastic net', 'glmnet', 'feature selection', 'binary classification', 'lambda.min', 'lambda.1se'), but a few common synonyms a user might say (e.g. 'regularized regression', 'gene/biomarker selection') are absent.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — elastic net feature selection on bulk expression matrices for binary classification — and the 'NOT for: survival/Cox, multiclass, single-cell, non-expression tables' clause minimizes overlap with adjacent skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
aipoch/medical-research-skills
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.