agent-data-ml-model
Agent skill for data-ml-model - invoke with $agent-data-ml-model
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-data-ml-model40
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
0%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 critically deficient across all dimensions. It provides only a technical invocation command without explaining what the skill does, when to use it, or any natural trigger terms. This would make it nearly impossible for Claude to correctly select this skill from a pool of available options.
Suggestions
Add specific concrete actions the skill performs (e.g., 'Trains machine learning models, performs data preprocessing, evaluates model performance, generates predictions')
Include an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user mentions training models, ML pipelines, predictions, datasets, or model evaluation')
Remove the invocation command from the description and replace with capability-focused content that distinguishes this from other data or ML skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for data-ml-model' is completely abstract and doesn't describe what the skill actually does. | 1 / 3 |
Completeness | Missing both 'what does this do' and 'when should Claude use it'. The description only provides an invocation command with no explanation of capabilities or use cases. | 1 / 3 |
Trigger Term Quality | Contains only technical jargon ('agent skill', 'data-ml-model') and an invocation command. No natural keywords a user would say like 'train model', 'machine learning', 'predict', or 'dataset'. | 1 / 3 |
Distinctiveness Conflict Risk | 'data-ml-model' is extremely generic and could conflict with any data processing, machine learning, or modeling skill. No distinct triggers or niche defined. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable overview of ML development workflows but lacks the concrete, executable guidance needed for effective Claude instruction. The content is more of a conceptual outline than actionable instructions, with generic lists of steps Claude already understands. The single code example is helpful but uses placeholders rather than real implementations.
Suggestions
Replace descriptive workflow lists with specific, executable code examples for each major task (e.g., actual hyperparameter tuning with GridSearchCV, specific preprocessing for different data types)
Add validation checkpoints to the workflow, such as 'Verify no data leakage: assert X_test not in training pipeline' or 'Check class balance before training'
Remove or drastically reduce the YAML frontmatter metadata that doesn't provide instructional value - focus the token budget on actionable content
Include concrete error handling patterns for common ML failures (e.g., convergence issues, memory errors, data type mismatches)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary explanation (e.g., listing obvious ML workflow steps like 'Exploratory data analysis' that Claude already knows). The YAML frontmatter is excessively verbose with metadata that doesn't add instructional value. | 2 / 3 |
Actionability | Provides one concrete code example with a standard ML pipeline structure, but much of the content is descriptive lists rather than executable guidance. The code example uses placeholder 'ModelClass()' instead of a real implementation, and lacks specific commands for common tasks. | 2 / 3 |
Workflow Clarity | Steps are listed in a logical sequence (Data Analysis → Preprocessing → Model Development → Evaluation → Deployment), but there are no validation checkpoints, error recovery steps, or feedback loops for training failures or data quality issues. | 2 / 3 |
Progressive Disclosure | Content is structured with clear sections and headers, but everything is inline in a single file. For a complex ML skill, advanced topics like hyperparameter tuning, specific model architectures, or deployment patterns could be split into referenced files. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.