agent-data-ml-model
Agent skill for data-ml-model - invoke with $agent-data-ml-model
45
17%
Does it follow best practices?
Impact
93%
1.16xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-data-ml-model/SKILL.mdQuality
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 essentially a placeholder that provides no useful information about the skill's capabilities, triggers, or use cases. It reads as an auto-generated label rather than a functional description. Claude would have no basis for selecting this skill appropriately from a list of available skills.
Suggestions
Replace the generic label with specific concrete actions the skill performs, e.g., 'Trains machine learning models, performs data preprocessing, evaluates model performance, and generates predictions.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about training models, making predictions, feature engineering, data pipelines, or ML workflows.'
Remove the invocation syntax ('invoke with $agent-data-ml-model') from the description and focus on capability and trigger information that helps Claude decide when to select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for data-ml-model' is entirely vague and abstract, providing no information about what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The only terms present are 'data-ml-model' and '$agent-data-ml-model', which are internal identifiers rather than natural keywords a user would say. No natural language trigger terms like 'machine learning', 'train model', 'predict', etc. are included. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic — 'data-ml-model' could overlap with any data processing, machine learning, or modeling skill. There are no distinct triggers or niche identifiers to differentiate it from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is mostly a high-level overview of ML concepts that Claude already knows, wrapped in an extremely verbose YAML frontmatter configuration block. The body content reads like a textbook table of contents rather than actionable instructions — it lists what to do without providing specific, executable guidance. The single code example is helpful but incomplete (uses placeholder class), and the workflow lacks validation checkpoints critical for ML pipelines.
Suggestions
Remove or drastically reduce explanations of basic ML concepts Claude already knows (EDA, feature scaling, cross-validation, etc.) and focus on project-specific patterns, conventions, or non-obvious decisions.
Replace the placeholder 'ModelClass()' with concrete, executable examples for the most common use cases (e.g., a complete classification pipeline with RandomForestClassifier including evaluation output).
Add explicit validation checkpoints to the workflow, such as 'Verify no data leakage before training', 'Check metric thresholds before proceeding to deployment', and error recovery guidance when model performance is insufficient.
Extract detailed content (e.g., hyperparameter tuning strategies, deployment templates, evaluation metric selection) into separate referenced files to keep SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The vast majority of the file is YAML frontmatter configuration that is not actionable skill content. The body content itself lists high-level responsibilities and workflow steps that Claude already knows (e.g., 'Handle missing values', 'Feature scaling/normalization', 'Cross-validation setup'). These are basic ML concepts that don't need to be spelled out. | 1 / 3 |
Actionability | There is one concrete code example showing a sklearn pipeline pattern, which is somewhat useful but uses a placeholder 'ModelClass()' rather than a real class. The workflow steps are descriptive bullet points rather than executable instructions — they tell Claude what to do conceptually but not how specifically. | 2 / 3 |
Workflow Clarity | The 5-step ML workflow is sequenced logically, but lacks validation checkpoints, error recovery steps, or feedback loops. For example, there's no explicit step to validate data quality before proceeding, no guidance on what to do if model performance is poor, and no verification after model serialization. | 2 / 3 |
Progressive Disclosure | The content has some structure with sections (responsibilities, workflow, code patterns, best practices), but everything is inline in a single file with no references to external files for detailed topics like hyperparameter tuning guides, evaluation metric details, or deployment templates. The massive YAML frontmatter also clutters the file. | 2 / 3 |
Total | 7 / 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.
- Repository
- ruvnet/ruflo
- Commit
3d8f171
- 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.