mlflow-tracking-setup
Mlflow Tracking Setup - Auto-activating skill for ML Training. Triggers on: mlflow tracking setup, mlflow tracking setup Part of the ML Training skill category.
36
3%
Does it follow best practices?
Impact
96%
0.96xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/mlflow-tracking-setup/SKILL.mdQuality
Discovery
7%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 extremely minimal and fails to communicate what the skill actually does beyond its title. It lacks concrete actions, meaningful trigger terms (the same phrase is duplicated), and has no explicit 'Use when...' guidance. The only redeeming quality is that 'mlflow' is a specific enough technology name to provide some distinctiveness.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Configures MLflow tracking server, sets up experiment logging, defines tracking URIs, and initializes artifact storage for ML experiments.'
Add an explicit 'Use when...' clause with natural trigger terms like 'Use when the user needs to set up MLflow, configure experiment tracking, log ML metrics, track model training runs, or set up a tracking URI.'
Remove the duplicated trigger term and expand with natural variations users might say, such as 'experiment tracking', 'log metrics', 'MLflow server setup', 'tracking URI configuration'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only says 'Mlflow Tracking Setup' without listing any concrete actions like configuring experiment tracking, logging metrics, setting up artifact stores, or creating runs. It is extremely vague about what the skill actually does. | 1 / 3 |
Completeness | The 'what' is barely addressed beyond the title, and the 'when' is only implied through a duplicated trigger phrase. There is no explicit 'Use when...' clause explaining when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | The trigger terms are just 'mlflow tracking setup' repeated twice. It misses natural variations users might say like 'experiment tracking', 'log metrics', 'MLflow server', 'tracking URI', 'mlflow configure', or 'model logging'. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'mlflow' provides some specificity that distinguishes it from generic ML skills, but 'ML Training' category and lack of detail about what specifically it does with MLflow could cause overlap with other ML training or experiment tracking skills. | 2 / 3 |
Total | 5 / 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 an empty shell with no substantive content. It consists entirely of meta-descriptions about what the skill would do without actually providing any actionable guidance, code examples, or concrete instructions for setting up MLflow tracking. It fails on every dimension of the rubric.
Suggestions
Add concrete, executable code examples showing MLflow tracking setup (e.g., `mlflow.set_tracking_uri()`, `mlflow.start_run()`, logging parameters/metrics/artifacts).
Provide a clear step-by-step workflow: configure tracking URI → create experiment → instrument training code → verify logged runs, with validation at each step.
Remove all meta-description sections (Purpose, When to Use, Capabilities, Example Triggers) and replace with actual technical content like configuration snippets, common patterns, and troubleshooting tips.
Include specific examples for common frameworks (PyTorch, TensorFlow, sklearn) showing how to integrate MLflow tracking into training loops.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and meta-description. It explains what the skill does in abstract terms without providing any actual technical content about MLflow tracking setup. Every section restates the same vague idea. | 1 / 3 |
Actionability | There is zero concrete guidance—no code, no commands, no configuration examples, no specific steps for setting up MLflow tracking. It only describes rather than instructs. | 1 / 3 |
Workflow Clarity | No workflow is defined. The skill claims to provide 'step-by-step guidance' but contains no actual steps, sequences, or validation checkpoints. | 1 / 3 |
Progressive Disclosure | The content is a monolithic block of vague descriptions with no references to detailed materials, no links to examples or configuration files, and no meaningful structural organization. | 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
87f14eb
- 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.