scikit-learn

Machine learning in Python with scikit-learn. Use 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

71%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/coding/scikit-learn/SKILL.md

Quality

Content

60%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 highly actionable with concrete code and a clean reference/script split, but it is padded by redundant sections (Common Workflows duplicating Quick Start, a Reference Documentation section duplicating inline pointers) and algorithm lists Claude already knows.

Suggestions

Collapse or remove the 'Common Workflows' section, which duplicates the Quick Start pipeline and clustering examples; keep one canonical worked example and defer variants to the reference files.

Delete the standalone 'Reference Documentation' section since each capability subsection already signals its reference file inline, or consolidate all pointers into that single section instead of repeating them.

Trim the 'Core Capabilities' algorithm enumerations (e.g., per-scaler and per-encoder descriptions) to bare names with links, since Claude already knows what StandardScaler or OneHotEncoder do.

Dimension	Reasoning	Score
Conciseness	The ~525-line body is noticeably verbose: 'Common Workflows' re-walks the Quick Start examples, the 'Reference Documentation' section re-lists every reference file already pointed to inline, and the 'Core Capabilities' algorithm enumerations restate concepts Claude already knows.	2 / 5
Actionability	Multiple concrete, mostly copy-paste-ready Python examples (classification, mixed-data pipeline, clustering, tuning) plus real executable scripts, but some snippets reference undefined variables (X, y) leaving minor gaps.	4 / 5
Workflow Clarity	Numbered multi-step workflows for classification (6 steps) and clustering (4 steps) are clearly sequenced with an end evaluation/silhouette checkpoint, but lack explicit validate->fix->retry feedback loops.	4 / 5
Progressive Disclosure	Well-signaled one-level-deep references (six real references/.md files and two real scripts/.py) with a dedicated navigation section, but SKILL.md inlines substantial detail (algorithm lists, two full workflows, troubleshooting) that could live in references.	4 / 5
	Total	14 / 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, well-structured description that explicitly states both capabilities and trigger conditions with concrete, natural keyword coverage. It would benefit from trimming the meta 'comprehensive reference documentation' clause and adding a few high-frequency natural terms.

Suggestions

Remove or tighten the trailing 'Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.' since it describes the skill's contents rather than a user-facing capability.

Add high-frequency natural trigger terms users actually say, such as 'cross-validation', 'train/test split', and 'feature engineering', to broaden keyword coverage.

Sharpen distinctiveness by signaling 'classical/traditional machine learning' more explicitly to reduce overlap with deep-learning or LLM-focused skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas (classification, regression, clustering, dimensionality reduction, model evaluation, hyperparameter tuning, preprocessing, pipelines), but the trailing 'Provides comprehensive reference documentation...' is descriptive meta rather than a concrete action, leaving minor action-level gaps.	4 / 5
Completeness	Clearly answers both 'what' ('Machine learning in Python with scikit-learn') and 'when' via an explicit 'Use when working with...' clause enumerating concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage of natural terms users would say (supervised/unsupervised learning, classification, regression, clustering, hyperparameter tuning, preprocessing, ML pipelines) with some synonym variation, though a few common natural phrases (e.g., cross-validation, feature engineering, train/test split) are absent.	4 / 5
Distinctiveness Conflict Risk	The scikit-learn / classical-ML framing carves a mostly distinct niche with specific triggers, though 'machine learning' broadly invites minor overlap with related deep-learning or general data-science skills.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (525 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/scikit-learn/SKILL.md
Commit: 3a6c3a9

Reviewed: about 20 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.