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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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 largely generic template filler with no executable code, relying on describes-rather-than-instructs phrasing and restating concepts Claude already knows. It needs concrete MLflow/W&B code and validation steps, or aggressive trimming of the placeholder sections.

Suggestions

Replace the filler sections (Output, Resources, Prerequisites, Instructions, Error Handling) with concrete content or remove them entirely, as they currently add tokens without information.

Add executable code examples for both tools (e.g. `mlflow.log_param/log_metric/log_artifact` and `wandb.init/log`) instead of stating that code 'will be generated'.

Add validation checkpoints to the workflow (confirm package install succeeded, verify MLflow server / W&B project connection) and reference real scripts once they exist rather than TODO checkboxes.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic template filler Claude gains nothing from ('The skill produces structured output relevant to the task.', 'Project documentation / Related skills and commands') and restates basic ML concepts Claude already knows (MLflow vs W&B tradeoffs, consistent logging). Matches the verbose/padded anchor; not level 2 because there is little efficient content to salvage.	1 / 3
Actionability	No executable code or commands appear anywhere; the Examples section only says 'Generate example code for logging parameters...' rather than showing mlflow.log_param() or wandb.init() calls. It describes rather than instructs, matching the vague/no-concrete-code anchor.	1 / 3
Workflow Clarity	'How It Works' lists a 4-step sequence (Analyze Context, Configure Environment, Initialize Tracking, Provide Code Snippets), so a sequence exists, but there are no validation checkpoints (e.g. verify install/server connection), capping it at 2 per the missing-validation guideline. Not level 1 because steps are clearly ordered; not level 3 because no feedback/verification loop exists.	2 / 3
Progressive Disclosure	The body is organized into sections but never references the bundle files, and the bundle dirs hold only placeholder READMEs (scripts listed as non-existent TODO checkboxes '[ ] initialize_mlflow.py'). Structure exists but there is no real one-level-deep navigation to detailed material. Not level 1 because sections are organized; not level 3 because no signaled references to actual detail files exist.	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.

The description clearly communicates what the skill does and when to use it, with concrete actions and a distinct niche. Its main weakness is trigger coverage: W&B/wandb variants and 'track experiments' phrasing are absent, and the final sentence is vague filler.

Suggestions

Add natural W&B triggers such as 'track experiments with wandb', 'set up Weights & Biases', or 'log metrics to W&B' so coverage matches the MLflow triggers.

Remove the vacuous filler 'Trigger with relevant phrases based on skill purpose.' since it adds no real trigger term.

Consider including the 'track experiments' phrasing users are likely to say, not just 'setup experiment tracking'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Configures environment and provides code for logging parameters, metrics, and artifacts') across a named domain and two named tools (MLflow, W&B), matching the multi-action anchor. Voice is third-person/imperative with no first/second-person penalty.	3 / 3
Completeness	Explicitly states both what it does ('Implement... experiment tracking... logging parameters, metrics, and artifacts') and when to use it ('Use when asked to "setup experiment tracking" or "initialize MLflow"'), matching the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Includes two natural phrases ('setup experiment tracking', 'initialize MLflow') but misses common W&B variations (e.g. 'wandb', 'track experiments'), and the trailing 'Trigger with relevant phrases based on skill purpose' is generic filler rather than a real trigger. Not level 3 because coverage of natural terms is incomplete; not level 1 because genuine user-sayable phrases are present.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (ML experiment tracking with MLflow/W&B) with distinct triggers, making conflict with unrelated skills unlikely; not level 2 because the domain is well-scoped rather than broadly overlapping.	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
Commit: 2cafb23

Reviewed: 2 days 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.