tuning-hyperparameters
Optimize machine learning model hyperparameters using grid search, random search, or Bayesian optimization. Finds best parameter configurations to maximize performance. Use when asked to "tune hyperparameters" or "optimize model". Trigger with relevant phrases based on skill purpose.
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill tuning-hyperparameters45
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
85%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 solid skill description with clear capabilities and explicit trigger guidance. The main weakness is the final sentence 'Trigger with relevant phrases based on skill purpose' which is meaningless filler that should be replaced with additional natural trigger terms. The description would benefit from more keyword variations users might naturally say.
Suggestions
Remove the vague filler sentence 'Trigger with relevant phrases based on skill purpose' and replace with additional natural trigger terms like 'parameter tuning', 'model optimization', 'hyperparameter search', 'GridSearchCV', 'Optuna'
Add file type or framework mentions if applicable (e.g., 'scikit-learn models', 'PyTorch', 'TensorFlow') to improve trigger term coverage
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'grid search, random search, or Bayesian optimization' and 'Finds best parameter configurations to maximize performance'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (optimize hyperparameters using specific methods) and when (explicit 'Use when asked to...' clause with trigger phrases). The 'Use when' clause is present and explicit. | 3 / 3 |
Trigger Term Quality | Includes some natural keywords like 'tune hyperparameters' and 'optimize model', but the final sentence 'Trigger with relevant phrases based on skill purpose' is vague filler that adds no value. Missing common variations like 'parameter tuning', 'model optimization', 'hyperparameter search', or 'ML tuning'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on hyperparameter optimization with distinct ML-specific triggers. Unlikely to conflict with general coding or data processing skills due to specific terminology like 'hyperparameters', 'grid search', 'Bayesian optimization'. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is a template-style placeholder that provides no actionable guidance for hyperparameter tuning. It explains concepts Claude already understands, lacks any executable code examples, and contains generic boilerplate sections ('Prerequisites', 'Instructions', 'Error Handling') that add no value. The skill fails to deliver on its promise of helping with hyperparameter optimization.
Suggestions
Replace the verbose explanations with executable Python code examples showing grid search with scikit-learn's GridSearchCV and Bayesian optimization with Optuna
Remove generic template sections (Prerequisites, Instructions, Error Handling, Integration) and replace with specific parameter configurations and search space definitions
Add concrete code snippets for each search strategy (grid, random, Bayesian) that can be directly adapted for different models
Include validation steps such as checking for data leakage in cross-validation and verifying search completion before reporting results
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations of concepts Claude already knows (what hyperparameter tuning is, how ML works). The 'Overview', 'How It Works', 'When to Use', and 'Integration' sections are largely redundant padding that don't add actionable value. | 1 / 3 |
Actionability | No executable code provided despite being a code-generation skill. Examples describe what the skill 'will do' rather than showing actual implementation. The 'Instructions' section is completely generic ('Invoke this skill when trigger conditions are met') with no concrete guidance. | 1 / 3 |
Workflow Clarity | The 'How It Works' section describes abstract steps without any concrete implementation details. No validation checkpoints, no error recovery workflows, and no actual sequence of commands or code to execute. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. Content is poorly organized with redundant sections (Overview, How It Works, When to Use all overlap). The 'Resources' section mentions documentation but provides no actual links. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 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.