CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 a well-structured, largely executable CLI skill guide with explicit validation and an error-recovery loop. The main issues are minor: a redundant validation example, an interpretation section restating common PCA knowledge, and example/test-data paths that don't exist in the bundle.

Suggestions

Remove or trim the Interpretation Guide section (content Claude already knows) and replace the duplicated Validation command with a short pointer to the Quick Examples to tighten conciseness.

Add the tests/data sample files referenced by Quick Examples and Validation, or change the examples to use placeholder paths consistent with the bundle's actual contents, so the commands are runnable as-is.

Fold the deliverables into the description's what-list (explained variance, sample scores, feature loadings, diagnostic figures) so the frontmatter describes analysis outcomes rather than only mechanical features.

DimensionReasoningScore

Conciseness

The body is efficient — argument tables, commands, and output listings with no conceptual padding about what PCA is — matching the score-4 anchor of efficient content with minor trims possible. Not 5 because the "Interpretation Guide" section explains what Claude already knows ("Use proportion_variance and cumulative_variance to decide how many components to retain") and the Validation section's second command duplicates the first Quick Example nearly verbatim.

4 / 5

Actionability

Commands are concrete and copy-paste shaped ("Rscript scripts/main.R --data_file tests/data/sample_pca_1.csv --sample_id_column SampleID ...") covering basic, auto-detect, and unscaled cases, near the score-5 anchor. Held at 4 because the examples and validation reference tests/data/ files that do not exist in the bundle, so they are not runnable as-is.

4 / 5

Workflow Clarity

The "Minimal Workflow" gives a clear sequence (confirm input → run script → check outputs) and the Validation section adds an explicit checkpoint ("verify that tests/validation_output/table/pca_summary.csv exists") with an error-recovery feedback loop: six named SKILL_* error codes plus "If the issue is not obvious, read references/troubleshooting.md". This matches the score-5 anchor of clear sequence, explicit validation, and feedback loops for error recovery.

5 / 5

Progressive Disclosure

The body is a lean overview with a "Read These Files When Needed" table cleanly signaling one-level-deep references (references/algorithm.md, cli-guide.md, troubleshooting.md — all verified to exist, with no nested references). Not 5 because one referenced path, tests/data/ for "Sample test data", does not exist in the bundle, leaving a minor navigation gap.

4 / 5

Total

17

/

20

Passed

Description

78%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 description with an explicit use-when trigger and several concrete capabilities in third-person voice. Its main weakness is that the what-list enumerates mechanical features (validation, directory creation, format export) instead of the analysis outcomes the skill actually delivers.

DimensionReasoningScore

Specificity

The description lists several concrete actions ("automatic numeric feature selection, parameter validation, result directory creation, and CSV or TXT format result export"), matching the score-4 anchor of several specific actions with minor gaps. It falls short of 5 because the actions are implementation features rather than the skill's analytic deliverables (explained variance, loadings, sample scores, figures are never mentioned).

4 / 5

Completeness

It explicitly answers both parts: the when-clause "Use when performing PCA principal component dimensionality reduction on tabular numeric data" and a what-list "Supports command-line parameter input, automatic numeric feature selection...". Not 5 because the what is a feature list that omits the actual analysis outputs, and the when uses a single trigger phrasing rather than concrete trigger variations.

4 / 5

Trigger Term Quality

It includes the core natural phrases a user would say — "PCA", "principal component", "dimensionality reduction", "tabular numeric data", "CSV or TXT" — matching good keyword coverage with a few natural terms missing. Not 5 because synonyms and extensions users commonly say ("reduce features", "reduce dimensions", ".csv") are absent.

4 / 5

Distinctiveness Conflict Risk

"PCA principal component dimensionality reduction" is a clear niche with distinct, specific triggers and minimal conflict risk with other skills. Not 4 because the trigger terms are distinctive enough that overlap with generic tabular-data or statistics skills is minimal.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.