pca-dimensionality-reduction

Use when performing PCA principal component dimensionality reduction on tabular numeric data. Supports command-line parameter input, automatic numeric feature selection, parameter validation, result directory creation, and CSV or TXT format result export.

Quality

86%

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 body is well-structured, actionable, and uses progressive disclosure effectively with real reference files. The main improvement is folding the redundant Quick Examples and Validation section together and adding an inline error-recovery loop.

Suggestions

Consolidate the Quick Examples and Validation sections to reduce overlap with the Primary Command and Core Arguments table.

Add an explicit validate-fix-retry loop in the Minimal Workflow (e.g., on SKILL_* errors, consult references/troubleshooting.md and rerun) rather than only pointing to it from Common Errors.

Trim the Input Requirements and Outputs sections to the essential constraints, moving exhaustive field lists into a reference file.

Dimension	Reasoning	Score
Conciseness	Largely lean with tables and copy-paste commands and no padding about what PCA is conceptually; the three Quick Examples plus a separate Validation section slightly exceed what is needed and could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout (Primary Command, three Quick Examples, Validation) with a concrete argument table covering the common cases.	5 / 5
Workflow Clarity	The Minimal Workflow is clearly sequenced and includes a verification checkpoint (confirm output files exist; Validation section checks pca_summary.csv), but there is no inline validate-fix-retry loop for the batch run, deferring recovery to troubleshooting.md.	4 / 5
Progressive Disclosure	Clear overview body with a well-signaled 'Read These Files When Needed' table pointing one level deep to real bundle files (references/algorithm.md, cli-guide.md, troubleshooting.md, scripts/main.R), keeping detail out of the main file.	5 / 5
	Total	18 / 20 Passed

Description

87%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 strong, explicitly pairing a clear trigger ('Use when...') with a concrete list of capabilities for a well-scoped niche. It could be sharpened by leading with the analytical outputs (explained variance, loadings, scores) rather than CLI plumbing details.

Dimension	Reasoning	Score
Specificity	Names the domain (PCA on tabular numeric data) and lists several concrete capabilities ('command-line parameter input, automatic numeric feature selection, parameter validation, result directory creation, and CSV or TXT format result export'), though several items describe CLI mechanics rather than the analytical outputs PCA produces.	4 / 5
Completeness	Explicitly answers both what (PCA dimensionality reduction with the listed capabilities) and when ('Use when performing PCA principal component dimensionality reduction on tabular numeric data').	5 / 5
Trigger Term Quality	Includes natural terms users would say ('PCA', 'principal component', 'dimensionality reduction', 'tabular numeric data') but the phrase 'PCA principal component dimensionality reduction' is somewhat jargon-stuffed and omits common synonyms/extensions.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (PCA on tabular numeric data via CLI) with distinct triggers and minimal overlap risk with unrelated skills.	5 / 5
	Total	18 / 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/pca-dimensionality-reduction/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.