domino-experiment-tracking

Track traditional ML experiments in Domino using the MLflow-based Experiment Manager. Covers experiment setup, auto-logging for sklearn/TensorFlow/PyTorch, manual logging, artifact storage, run comparison, and model registration. Use when training ML models, logging metrics and parameters, comparing model runs, or registering models.

Quality

76%

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 ./skills/experiment-tracking/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

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

A concise, actionable quick-start with good tables, but its progressive-disclosure structure is undermined by three referenced files that are absent from the bundle, and the comparison/registry workflows lack sequencing and validation.

Suggestions

Add the missing referenced files (MLFLOW-BASICS.md, COMPARING-RUNS.md, MODEL-REGISTRY.md) to a references/ directory, or remove the links and inline the essential content so navigation is not broken.

Provide a short numbered workflow with a verification checkpoint for model registration (e.g., confirm the registered model version/stage before declaring success) since it is a stateful operation.

Tighten the intro sentence and de-duplicate the unique-experiment-name guidance so it appears once instead of in both the Critical Configuration section and the code comment.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes MLflow knowledge rather than explaining basics, but the opener 'This skill provides comprehensive knowledge...' and the repeated unique-experiment-name warning are minor padding that could be trimmed.	4 / 5
Actionability	Quick Start offers copy-paste executable code, the Supported Frameworks table gives concrete autolog commands, and env-var/doc links are specific; the undefined `model`/`X_train`/`y_train` in the example is a minor gap.	4 / 5
Workflow Clarity	The core autolog flow is sequenced in Quick Start, but the comparison and model-registry workflows are only pointed at (missing) files, and there are no validation/checkpoint steps for stateful operations like model registration.	3 / 5
Progressive Disclosure	The SKILL.md is well-sectioned and signals three detail files, but MLFLOW-BASICS.md, COMPARING-RUNS.md, and MODEL-REGISTRY.md do not exist anywhere in the bundle (no references/ directory), so the navigation links are broken and the promised detail is unreachable.	2 / 5
	Total	13 / 20 Passed

Description

92%Weight 40%Scale 1-5

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: specific, distinct, and complete with both a capability list and an explicit Use-when trigger clause. Only minor room to expand trigger-term synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'experiment setup, auto-logging for sklearn/TensorFlow/PyTorch, manual logging, artifact storage, run comparison, and model register' — giving comprehensive coverage rather than vague abstractions.	5 / 5
Completeness	Explicitly answers both 'what' (the tracked capabilities) and 'when' via a concrete 'Use when...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrases are present ('training ML models, logging metrics and parameters, comparing model runs, or registering models'), but coverage stops short of the synonyms/variations needed for a 5.	4 / 5
Distinctiveness Conflict Risk	The Domino-specific, MLflow-Experiment-Manager framing carves a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: dominodatalab/domino-claude-plugin
Path: skills/experiment-tracking/SKILL.md
Commit: d86698d

Reviewed: 14 hours 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.