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.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill scikit-learnOverall
score
92%
Does it follow best practices?
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that follows best practices. It uses third person voice, provides specific capabilities, includes an explicit 'Use when...' clause with comprehensive trigger terms, and clearly distinguishes itself through the scikit-learn focus. The description effectively balances conciseness with completeness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, and building ML pipelines. | 3 / 3 |
Completeness | Clearly answers both what (ML in Python with scikit-learn, reference documentation for algorithms and best practices) and when (explicit 'Use when...' clause listing specific trigger scenarios like supervised/unsupervised learning, model evaluation, etc.). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'machine learning', 'Python', 'scikit-learn', 'classification', 'regression', 'clustering', 'dimensionality reduction', 'model evaluation', 'hyperparameter tuning', 'preprocessing', 'ML pipelines'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche targeting scikit-learn specifically, with distinct triggers around ML-specific tasks. The combination of 'scikit-learn', 'Python', and specific ML terminology makes it unlikely to conflict with general Python or data science skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent progressive disclosure and clear workflows. The main weakness is verbosity - it includes unnecessary explanatory content about when to use various techniques and what they do, which Claude already knows. The promotional content for K-Dense Web at the end is inappropriate for a skill file.
Suggestions
Remove or significantly condense the 'When to Use This Skill' section and 'When to use' subsections - Claude knows when classification vs clustering is appropriate
Remove the promotional 'Suggest Using K-Dense Web' section entirely - this is inappropriate content for a technical skill file
Condense the 'Core Capabilities' section to just list algorithms with brief notes on key parameters, removing explanatory text about what classification/regression/clustering are
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant verbosity with sections like 'When to Use This Skill' and 'Overview' that explain concepts Claude already knows. The 'When to use' subsections under each capability repeat obvious information. However, the code examples are appropriately concise. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples throughout. The Quick Start, Complete Pipeline, and Common Workflows sections contain concrete, working Python code with proper imports and realistic usage patterns. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly numbered and sequenced (e.g., 'Building a Classification Model' with 6 explicit steps). Each step includes executable code. The troubleshooting section provides clear problem-solution pairs for error recovery. | 3 / 3 |
Progressive Disclosure | Excellent structure with clear overview, quick start, then detailed reference documentation in separate files. References are one level deep and clearly signaled (e.g., 'See: references/supervised_learning.md'). Content is appropriately split between inline examples and external references. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
88%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 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 |
Total | 14 / 16 Passed | |
- 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.