CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

scikit-learn

Supports machine learning in Python with scikit-learn. Applies when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

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

75%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 pinned-version install commands, runnable example scripts, and genuine one-level-deep reference disclosure. Its main cost is token efficiency: the 'When to Use' section, the double reference enumeration, and the overlapping Quick Start example could be consolidated without losing information.

Suggestions

Remove the "When to Use This Skill" section (or compress it to one line) — it duplicates the frontmatter description and the "Use this skill for" sentence in the Overview.

Merge the "Reference Documentation" bullet lists into the existing "Core Capabilities" linking paragraph so each reference file is enumerated only once.

Replace the Quick Start classification example with a pointer to scripts/classification_pipeline.py (or shorten it to the pipeline-fit pattern only), keeping the mixed-data ColumnTransformer example as the sole inline demonstration.

DimensionReasoningScore

Conciseness

The body is dense and mostly high-value, but it duplicates itself: "When to Use This Skill" restates the frontmatter description, the "Reference Documentation" section re-enumerates the same files already linked under "Core Capabilities", and the Quick Start classification example overlaps the bundled classification_pipeline.py script. This matches anchor 3 (mostly efficient but could be tightened); it does not reach 4 because multiple sections could be trimmed without losing information.

3 / 5

Actionability

Fully executable guidance throughout: pinned install commands ("uv pip install \"scikit-learn==1.9.1\""), copy-paste runnable script invocations ("uv run --no-project --with scikit-learn==1.9.1 ... python scripts/classification_pipeline.py"), and concrete troubleshooting fixes. Inline snippets using caller-provided X, y are explicitly justified as illustrative adaptations, and the two bundled scripts cover the common cases end-to-end — anchor 5.

5 / 5

Workflow Clarity

Clear sequence from installation through version check to quick-start examples and runnable scripts, plus an error-recovery section (ConvergenceWarning → increase max_iter or scale features). Not a 5 because script runs lack expected-output or explicit verification checkpoints, which anchor 5 requires.

4 / 5

Progressive Disclosure

All eight references/*.md files and both scripts/*.py files referenced in the body exist, are one level deep, and are linked with per-file content summaries — matching anchor 4 (good structure, references mostly clear). The duplicated enumeration of reference files across "Core Capabilities" and "Reference Documentation" is the minor organization gap that keeps it below 5.

4 / 5

Total

16

/

20

Passed

Description

83%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: third-person, explicit 'Applies when' trigger guidance covering the main ML task areas, and a clear statement of what the skill provides. Its only weaknesses are a few missing natural synonyms (sklearn, cross-validation) and some trigger terms broad enough to overlap with neighboring data-science skills.

DimensionReasoningScore

Specificity

Lists several specific capability areas — "supervised learning (classification, regression)", "clustering, dimensionality reduction", "hyperparameter tuning", "building ML pipelines" — with only minor gaps. Not a 5 because the framing verbs "Supports" and "Provides comprehensive reference documentation" describe areas rather than the fully concrete actions of the anchor-5 example.

4 / 5

Completeness

Explicitly answers both: what ("Supports machine learning in Python with scikit-learn... Provides comprehensive reference documentation") and when ("Applies when working with supervised learning..., unsupervised learning..., model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines"). Both are stated with concrete trigger phrases in third-person voice, matching the anchor-5 example; a 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Good keyword coverage with natural phrases users would say ("machine learning", "classification", "clustering", "model evaluation", "hyperparameter tuning", "preprocessing", "ML pipelines"). A few natural terms are missing — notably "sklearn", "cross-validation", and "train a model" — keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

"scikit-learn" plus the parenthesized algorithm areas define a clear niche, but generic terms like "model evaluation", "preprocessing", and "pipelines" create minor overlap risk with adjacent data-science skills (e.g., pandas, PyTorch, or general data-cleaning skills), matching anchor 4 rather than 5.

4 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

K-Dense-AI/scientific-agent-skills

Path

skills/scikit-learn/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.