building-automl-pipelines
Build automated machine learning pipelines with feature engineering, model selection, and hyperparameter tuning. Use when automating ML workflows from data preparation through model deployment. Trigger with phrases like "build automl pipeline", "automate ml workflow", or "create automated training pipeline".
46
50%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/ai-ml/automl-pipeline-builder/skills/building-automl-pipelines/SKILL.mdQuality
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 well-crafted skill description that covers all key dimensions effectively. It provides specific capabilities, explicit trigger guidance with natural user phrases, and a clear 'Use when' clause. The description is concise, uses third person voice correctly, and carves out a distinct niche around automated ML pipeline construction.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'feature engineering', 'model selection', 'hyperparameter tuning', and covers the pipeline from 'data preparation through model deployment'. | 3 / 3 |
Completeness | Clearly answers both 'what' (build automated ML pipelines with feature engineering, model selection, hyperparameter tuning) and 'when' (explicit 'Use when' clause and 'Trigger with phrases' providing concrete activation guidance). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms like 'build automl pipeline', 'automate ml workflow', 'create automated training pipeline', plus domain terms like 'feature engineering', 'model selection', 'hyperparameter tuning' that users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to automated ML pipelines specifically, with distinct triggers like 'automl pipeline' and 'automated training pipeline' that are unlikely to conflict with general data science or individual ML model skills. | 3 / 3 |
Total | 12 / 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 essentially a hollow outline with no actionable content. It contains no executable code, no concrete examples, and defers all substantive guidance to reference files that don't exist. The instructions are abstract directives that Claude already knows how to reason about, making the entire skill redundant rather than instructive.
Suggestions
Add a concrete, executable Python code example showing a minimal AutoML pipeline (e.g., using PyCaret or Auto-sklearn) with actual imports, data loading, training, and evaluation in the main SKILL.md.
Replace the vague 11-step instruction list with a concrete workflow that includes specific validation checkpoints (e.g., 'Verify no columns have >50% missing values before proceeding', 'Confirm leaderboard has at least 3 models before selecting best').
Either provide the referenced bundle files (implementation.md, errors.md, examples.md) with real content, or inline the essential guidance directly in SKILL.md.
Remove the prerequisites section and resources descriptions—Claude already knows what these libraries do and what classification/regression means. Use that space for actual implementation patterns and gotchas.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is verbose and padded with unnecessary context. The prerequisites section lists things Claude already knows (understanding problem types, knowledge of evaluation metrics). The Resources section explains what each library does, which Claude already knows. The numbered instructions are vague and don't add actionable value. | 1 / 3 |
Actionability | There is no executable code, no concrete commands, no specific examples, and no copy-paste ready snippets. The instructions are entirely abstract ('Identify problem type', 'Define evaluation metrics', 'Load training data using Read tool') with no concrete implementation. All real content is deferred to reference files that don't exist in the bundle. | 1 / 3 |
Workflow Clarity | The 11 numbered steps are vague directives without validation checkpoints, feedback loops, or error recovery. For a complex multi-step pipeline involving data processing and model training, there are no verification steps. The workflow lacks any concrete sequencing—steps like 'Perform initial data quality assessment' give no indication of what to check or what constitutes a pass/fail. | 1 / 3 |
Progressive Disclosure | The skill references three external files (implementation.md, errors.md, examples.md) but none of them exist in the bundle. The SKILL.md itself contains almost no substantive content—it's essentially an empty shell pointing to nonexistent references. This is worse than a monolithic wall of text because there's no content anywhere. | 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
6e9558f
- 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.