ai-engineer
Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered applications with emphasis on practical, scalable solutions.
39
24%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./ai-engineer/skills/SKILL.mdQuality
Discovery
14%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 reads more like a resume summary or persona definition than a skill description. It uses first-person-style framing ('Expert AI/ML engineer specializing in...') rather than describing concrete actions, lacks any 'Use when...' trigger guidance, and is far too broad to be distinguishable from other skills in a large skill library.
Suggestions
Replace the persona-style framing with specific concrete actions the skill performs, e.g., 'Trains and fine-tunes ML models, builds data preprocessing pipelines, deploys models as REST APIs, integrates model inference into applications.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about training models, building ML pipelines, model deployment, inference optimization, or working with frameworks like PyTorch, TensorFlow, or scikit-learn.'
Narrow the scope to a more distinct niche or clearly enumerate sub-capabilities to reduce conflict risk with other engineering or data-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'specializing in machine learning model development, deployment, and integration' and 'building intelligent features, data pipelines, and AI-powered applications.' These are broad domain claims rather than concrete, specific actions. No specific operations (e.g., 'train models', 'build REST API endpoints', 'create feature engineering pipelines') are listed. | 1 / 3 |
Completeness | The description provides a vague 'what' (ML model development, deployment, integration) but completely lacks any 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent statement telling Claude when to select this skill. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'machine learning', 'AI', 'ML', 'data pipelines', 'model development', 'deployment' that users might naturally use. However, it misses many common variations and specific terms users would say (e.g., 'train a model', 'fine-tune', 'inference', 'TensorFlow', 'PyTorch', 'scikit-learn', 'neural network'). | 2 / 3 |
Distinctiveness Conflict Risk | The description is extremely broad, covering all of AI/ML engineering, data pipelines, and 'AI-powered applications.' This would easily conflict with any other skill related to data processing, software engineering, or AI tasks. The scope is too wide to carve out a distinct niche. | 1 / 3 |
Total | 5 / 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 reads more like a role description or persona definition than an actionable skill. It tells Claude what kind of engineer to be rather than providing concrete, executable guidance for specific tasks. The content lacks code examples, specific commands, worked scenarios, or any copy-paste-ready material, making it largely redundant with Claude's existing knowledge of ML engineering practices.
Suggestions
Replace abstract workflow steps with concrete, executable examples—e.g., a specific MLflow experiment tracking setup, a FastAPI model serving template, or a drift detection script.
Remove the 'Tools and Platforms' section entirely or replace it with specific configuration patterns or integration code that Claude wouldn't already know.
Add at least 2-3 worked examples showing input scenarios and expected output artifacts (e.g., an evaluation summary template, a deployment checklist with actual items to verify).
Add explicit validation checkpoints with concrete commands or checks in the workflow, such as specific offline metric thresholds, bias check scripts, or rollback trigger definitions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably structured and avoids excessive verbosity, but includes broad capability listings and tool enumerations that Claude already knows. Sections like 'Tools and Platforms' and 'Core Capabilities' are essentially lists of things Claude is already familiar with, adding little unique value. | 2 / 3 |
Actionability | The skill is entirely abstract and descriptive—no concrete code, commands, examples, or copy-paste-ready guidance. Every section describes what to do at a high level ('Audit the use case', 'Establish baselines') without showing how. There are no executable snippets, specific configurations, or worked examples. | 1 / 3 |
Workflow Clarity | The workflow section provides a numbered sequence of steps with some validation mentioned (step 4: 'Validate with offline metrics, safety checks, and controlled rollouts'), but the steps are high-level and lack explicit validation checkpoints, feedback loops, or error recovery paths. The rollback triggers in step 5 are mentioned but not defined. | 2 / 3 |
Progressive Disclosure | The content is organized into clear sections with headers, which aids readability. However, there are no references to external files for deeper content, and several sections (Core Capabilities, Tools and Platforms) contain inline lists that could either be removed (Claude knows these) or linked to detailed guides. The flat structure is acceptable but doesn't leverage progressive disclosure. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- OpenRoster-ai/awesome-openroster
- Commit
09aef5d
- 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.