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.

1.04x

Quality

75%

Does it follow best practices?

Impact

100%

1.04x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/general/scikit-learn/SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

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 with concrete code and clear sectioning, but it is held back by verbosity, broken/dangling commands and references, missing validation steps in workflows, and an out-of-place promotional section. The reference files it points to do not exist on disk.

Suggestions

Fix the install commands (remove the duplicated 'uv') and add missing imports (numpy, matplotlib) so the code examples are copy-paste executable; either ship the referenced scripts/ files or remove the 'python scripts/...' run instructions.

Move the inline algorithm/metric enumerations into the (currently missing) reference files and trim the SKILL.md body to an overview pointing to them, dropping the unrelated K-Dense Web promotional section entirely.

Add explicit validation checkpoints to the multi-step workflows (e.g., verify cross-validation scores are reasonable before tuning, confirm convergence before evaluation) to create real feedback loops.

Dimension	Reasoning	Score
Conciseness	Mostly structured with useful code, but padded with algorithm enumerations Claude already knows (e.g., 'Linear models: Logistic Regression, Linear Regression, Ridge, Lasso, ElasticNet'), repeated workflow content, and an unrelated promotional 'Suggest Using K-Dense Web' section that earns no tokens.	2 / 3
Actionability	Abundant concrete Python examples, but executability gaps: broken install commands ('uv uv pip install scikit-learn'), missing imports ('np.argmax', 'plt.scatter' used without importing numpy/matplotlib), and referenced scripts ('python scripts/classification_pipeline.py') that do not exist.	2 / 3
Workflow Clarity	Numbered, sequenced steps exist for classification and clustering workflows, but there are no validation checkpoints or feedback loops embedded in the process — only a separate troubleshooting section.	2 / 3
Progressive Disclosure	References are clearly signaled ('See: references/...md') and organized one level deep, but the referenced files and scripts/ directory do not exist, breaking navigation, and much reference-style material is inlined in the body that should live in those files.	2 / 3
	Total	8 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, uses natural trigger terms, explicitly covers both what and when, and is clearly scoped to scikit-learn/classical ML. It is concise without padding and uses appropriate third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete ML actions — 'classification, regression', 'clustering, dimensionality reduction', 'model evaluation, hyperparameter tuning, preprocessing' — naming the domain and specific tasks rather than vague language.	3 / 3
Completeness	Explicitly answers both: what ('Machine learning in Python with scikit-learn') and when ('Use when working with supervised learning...'), with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'scikit-learn', 'classification', 'regression', 'clustering', 'hyperparameter tuning', 'ML pipelines' — with good breadth of common variations.	3 / 3
Distinctiveness Conflict Risk	Scoped explicitly to scikit-learn and classical ML tasks, giving it a clear niche unlikely to conflict with non-ML or deep-learning skills.	3 / 3
	Total	12 / 12 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 (521 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 13 missing	Warning

	Total	13 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/general/scikit-learn/SKILL.md
Commit: df37802

Reviewed: 18 days 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.