ml-pipeline-workflow
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.
Install with Tessl CLI
npx tessl i github:Dicklesworthstone/pi_agent_rust --skill ml-pipeline-workflow66
Quality
56%
Does it follow best practices?
Impact
73%
0.98xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/machine-learning-ops/skills/ml-pipeline-workflow/SKILL.mdDiscovery
92%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 clearly articulates capabilities and includes explicit trigger guidance. It uses appropriate third-person voice and covers the MLOps domain comprehensively. The main weakness is potential overlap with related skills in the ML/data engineering space.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'data preparation', 'model training', 'validation', and 'production deployment'. Describes the full pipeline scope clearly. | 3 / 3 |
Completeness | Clearly answers both what ('Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment') and when ('Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'ML pipelines', 'MLOps', 'model training', 'deployment workflows'. These are terms practitioners commonly use when requesting this type of work. | 3 / 3 |
Distinctiveness Conflict Risk | While MLOps is a specific domain, there could be overlap with general ML skills, data engineering skills, or deployment/DevOps skills. The description doesn't clearly distinguish from adjacent skills like pure model training or infrastructure automation. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a high-level overview document or tutorial introduction rather than actionable guidance for Claude. It extensively lists concepts, tools, and patterns that Claude already understands while providing almost no executable code or specific implementation details. The content would benefit from dramatic reduction and replacement of descriptions with concrete, working examples.
Suggestions
Replace the incomplete code stubs with fully executable examples - show a complete minimal pipeline implementation rather than skeleton code with 'see elsewhere' comments
Remove explanations of what MLOps tools are (Airflow, MLflow, etc.) and instead show specific configuration or code for using them
Add explicit validation checkpoints with concrete commands, e.g., 'Run `python validate_data.py --schema schema.json` before proceeding to training'
Cut the document by 70% - remove the 'What This Skill Provides', 'Integration Points', and 'Common Patterns' sections which describe rather than instruct
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations of concepts Claude already knows (what MLOps is, what DAGs are, what orchestration tools do). Lists many tools and patterns without providing actionable guidance, padding content significantly. | 1 / 3 |
Actionability | Almost no executable code - the Python snippets are incomplete stubs with comments like 'See assets/...' or just variable definitions. The YAML example is a skeleton. Everything defers to external files that may not exist, providing no copy-paste ready guidance. | 1 / 3 |
Workflow Clarity | Steps are listed in sequence (Data → Training → Validation → Deployment) but lack validation checkpoints and feedback loops. No explicit verification steps between phases, no error recovery guidance, just high-level descriptions of what each phase does. | 2 / 3 |
Progressive Disclosure | References external files (references/, assets/) which is good structure, but the main document is still a monolithic wall of text with too much inline content. The 'Progressive Disclosure' section ironically adds more content rather than organizing it better. | 2 / 3 |
Total | 6 / 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.