optuna-study-creator
Optuna Study Creator - Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna study creator Part of the ML Training skill category.
36
3%
Does it follow best practices?
Impact
96%
1.02xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/optuna-study-creator/SKILL.mdQuality
Discovery
7%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 description is extremely minimal and essentially just restates the skill name without providing any meaningful detail about capabilities, use cases, or natural trigger terms. It fails to help Claude understand when to select this skill over others and provides no concrete actions or explicit usage guidance.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Creates Optuna studies for hyperparameter optimization, defines search spaces, configures samplers and pruners, and sets up objective functions for ML model tuning.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about hyperparameter tuning, hyperparameter optimization, Optuna studies, parameter search, HPO, or optimizing ML model performance.'
Remove the duplicate trigger term ('optuna study creator' is listed twice) and expand with varied natural language phrases users might actually say.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the tool ('Optuna Study Creator') and category ('ML Training') but does not describe any concrete actions like creating hyperparameter search spaces, defining objectives, running optimization trials, or configuring samplers/pruners. | 1 / 3 |
Completeness | The description barely answers 'what does this do' beyond the name itself, and the 'when' clause is essentially just restating the skill name as a trigger rather than providing meaningful usage context. There is no explicit 'Use when...' guidance. | 1 / 3 |
Trigger Term Quality | The trigger terms are just 'optuna study creator' repeated twice. It misses natural user phrases like 'hyperparameter tuning', 'hyperparameter optimization', 'optuna', 'study', 'trial', 'objective function', 'parameter search', or 'HPO'. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'Optuna' is fairly specific to a particular library, which provides some distinctiveness. However, the vague 'ML Training' category could overlap with other ML-related skills, and the lack of concrete capability descriptions makes it harder to distinguish from other hyperparameter or ML optimization skills. | 2 / 3 |
Total | 5 / 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 is an empty template with no actual content about Optuna study creation. It consists entirely of generic boilerplate that describes what the skill would do without providing any actionable guidance, code examples, or workflows. It adds zero value beyond what Claude already knows about Optuna.
Suggestions
Add executable Python code showing how to create an Optuna study, define an objective function, and run optimization (e.g., `study = optuna.create_study(direction='minimize'); study.optimize(objective, n_trials=100)`)
Include a concrete workflow: 1) Define objective function with trial.suggest_* calls, 2) Create study with storage/sampler config, 3) Run optimization, 4) Extract best params and validate results
Remove all meta-description sections ('When to Use', 'Capabilities', 'Example Triggers') and replace with actual technical content covering common patterns like pruning, multi-objective optimization, and storage backends
Add specific examples showing integration with PyTorch/TensorFlow training loops, including how to structure the objective function and report intermediate values for pruning
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and boilerplate. It explains nothing Claude doesn't already know, repeats 'optuna study creator' excessively, and provides zero actual technical content about Optuna study creation. | 1 / 3 |
Actionability | There is no concrete code, no executable commands, no specific examples of creating an Optuna study. The content is entirely abstract descriptions like 'Provides step-by-step guidance' without actually providing any guidance. | 1 / 3 |
Workflow Clarity | No workflow steps are defined at all. There is no sequence, no validation, no actual process described for creating an Optuna study. The skill claims to provide 'step-by-step guidance' but contains none. | 1 / 3 |
Progressive Disclosure | The content is a monolithic block of meta-description with no actual technical content to organize. There are no references to detailed files, no structured sections with real content, and no navigation to deeper materials. | 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 — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3076d78
- 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.