Name: scikit-learn
Rating: 56.8 (1 reviews)
Author: administrakt0r

scikit-learn

Machine learning in Python with scikit-learn. Use for classification, regression, clustering, model evaluation, and ML pipelines.

Quality

66%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/scikit-learn/SKILL.md

The canonical home for this skill is scikit-learn in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

50%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 rich with executable examples and reasonable structure, but it is overlong, re-explains familiar ML concepts, references bundle files that are missing, and lacks explicit validation checkpoints in its workflows.

Suggestions

Trim redundant 'When to use' sections and elementary explanations of concepts Claude already knows to reclaim token budget.

Provide the missing references/*.md and scripts/*.py files referenced in the body, or remove the references so navigation is not broken.

Add explicit validation/evaluation checkpoints to the numbered workflows (e.g., verify fit succeeded, check metric thresholds before declaring success) and fix the 'uv uv pip' install typo.

Dimension	Reasoning	Score
Conciseness	The ~510-line body is noticeably verbose, repeatedly re-explaining concepts Claude already knows (e.g., 'Classification: Predicting discrete categories', 'Always use Pipelines') and duplicating per-capability 'When to use' sections, with padded explanatory bullets throughout.	2 / 5
Actionability	It provides numerous concrete, copy-paste-ready code blocks and explicit run commands, though the referenced scripts/ files are absent and the installation snippet contains a duplicated 'uv uv pip' token.	4 / 5
Workflow Clarity	Numbered workflow sequences are present, but validation checkpoints are absent and verification of results is only implicit, leaving sequence present but checkpoints missing.	3 / 5
Progressive Disclosure	References are clearly signaled with 'See:' lines, but the referenced references/.md and scripts/.py files do not exist in the bundle, so the navigation is broken and the large inline body should itself be split.	3 / 5
	Total	12 / 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, third-person description that pairs a clear capability statement with an explicit use clause and concrete task keywords. The main gap is that the 'when' trigger phrasing reads as a task list rather than natural user-utterance triggers.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions — 'classification, regression, clustering, model evaluation, and ML pipelines' — covering the core scikit-learn surface comprehensively.	5 / 5
Completeness	It gives a clear 'what' (ML with scikit-learn) and an explicit 'Use for...' 'when' clause, but the 'when' is a task list rather than concrete user-utterance triggers, keeping it below the 5 anchor.	4 / 5
Trigger Term Quality	Natural terms like 'Machine learning', 'classification', 'regression', and 'clustering' are present, but common synonyms and user-facing phrasings such as 'train a model' or 'predict' are missing, so it falls short of the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The scikit-learn/classical-ML niche is clearly scoped with distinct triggers and minimal overlap risk against unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (522 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
referenced_paths_exist	Referenced path issues: 13 missing	Warning

	Total	12 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/scikit-learn/SKILL.md
Commit: 57c135b

Reviewed: 2 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.