setting-up-experiment-tracking

Implement machine learning experiment tracking using MLflow or Weights & Biases. Configures environment and provides code for logging parameters, metrics, and artifacts. Use when asked to "setup experiment tracking" or "initialize MLflow". Trigger with relevant phrases based on skill purpose.

Quality

52%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/ai-ml/experiment-tracking-setup/skills/setting-up-experiment-tracking/SKILL.md

Quality

Content

20%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a verbose description of a code-providing skill that contains no actual code or commands, with generic filler sections and no real bundled reference materials. It needs to be cut to a lean overview plus executable snippets that point to the real scripts.

Suggestions

Replace the 'How It Works', 'Instructions', 'Output', and 'Error Handling' prose with concrete, copy-paste install/initialization commands (e.g. `pip install mlflow` and an `mlflow.set_tracking_uri(...)` snippet) plus a W&B equivalent.

Add a validation checkpoint to the workflow (e.g. verify `mlflow ui` runs or that `wandb login` succeeded) before declaring setup complete.

Actually create the referenced scripts under scripts/ and link to them from the body (e.g. 'Logging code: see [scripts/log_experiment_metrics.py](scripts/log_experiment_metrics.py)') instead of leaving them as unchecked README todos.

Dimension	Reasoning	Score
Conciseness	Padded with sections restating concepts Claude already knows (Overview, How It Works prose, Best Practices, Integration, generic Instructions/Output/Error Handling/Resources); despite being a code-providing skill it contains no executable code, wasting tokens.	1 / 3
Actionability	Describes rather than instructs — 'The skill will: 1. Install the mlflow Python package. 2. Generate example code ...' but never provides the install commands or the logging code; scripts are only listed as unchecked README todos.	1 / 3
Workflow Clarity	A four-step sequence exists in 'How It Works', but it lacks concrete commands and any validation/verification checkpoints for the environment setup and install steps.	2 / 3
Progressive Disclosure	The body does not link out to the bundled scripts; the references/assets/scripts dirs contain only placeholder READMEs (scripts README is an unchecked todo list), so there are no real one-level-deep detail files to navigate to.	2 / 3
	Total	6 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with concrete capabilities and an explicit use-when trigger. Its main weakness is the generic trailing trigger guidance and missing natural W&B/wandb trigger variations.

Dimension	Reasoning	Score
Specificity	Names concrete actions across two tools: 'Configures environment and provides code for logging parameters, metrics, and artifacts' — multiple specific capabilities, not vague.	3 / 3
Completeness	Clearly states both what it does and when to use it via an explicit 'Use when asked to ...' clause.	3 / 3
Trigger Term Quality	Includes natural triggers ('setup experiment tracking', 'initialize MLflow') but closes with generic filler 'Trigger with relevant phrases based on skill purpose' and omits wandb/Weights & Biases variations.	2 / 3
Distinctiveness Conflict Risk	A clear niche (ML experiment tracking) with explicit triggers makes it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/ai-ml/experiment-tracking-setup/skills/setting-up-experiment-tracking/SKILL.md
Commit: 15940c5

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.