mlflow

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/ml-training/mlflow/SKILL.md

Quality

Content

65%

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

A highly actionable, code-rich reference for MLflow, but it is verbose with redundant framework repeats and inline content that duplicates dedicated reference files, and it lacks validation checkpoints in its model-registry workflows.

Suggestions

Move the detailed tracking, model-registry, and deployment sections into the existing reference files and keep SKILL.md as a concise overview that links to them, improving progressive disclosure and conciseness.

Collapse the repeated per-framework autolog/start_run examples into a single representative example plus a table of supported frameworks to cut redundancy.

Add explicit validation checkpoints (e.g. verify a model version's stage/tags before promoting to Production) to the model-registry workflow to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The ~700-line body is mostly tight code blocks but repeats the same autolog/start_run pattern across Logging Models, Autologging, and Integration Examples, and explains concepts Claude already knows ("Experiment: Logical container for related runs") plus marketing stats, so it could be tightened rather than earning the lean level-3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python and shell examples (mlflow.start_run, log_param/metric/model, mlflow models serve, mlflow server) with concrete arguments, matching the level-3 fully-executable anchor and above the level-2 pseudocode case.	3 / 3
Workflow Clarity	Capability flows (log → register → transition stages → load) are sequenced, but there are no explicit validation checkpoints or feedback loops for risky production stage transitions, capping it at level 2 rather than the level-3 explicit-validation anchor.	2 / 3
Progressive Disclosure	Reference files (tracking.md, model-registry.md, deployment.md) exist and are linked in See Also, but full tracking, registry, and deployment guides are duplicated inline and the references are only signaled at the end, fitting level-2's 'content that should be separate is inline' rather than the well-split level-3.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific, third-person description with strong capability verbs and a clear MLflow niche, but it omits an explicit "Use when..." trigger clause, capping completeness at 2.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when tracking ML experiments, managing a model registry, or deploying models with MLflow') to lift completeness to 3.

Include common user phrasings like 'experiment tracking' and 'model versioning' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Track ML experiments", "manage model registry with versioning", "deploy models to production", "reproduce experiments" — matching the level-3 anchor of multiple specific concrete actions rather than the level-2 single-domain phrasing.	3 / 3
Completeness	Clearly answers "what" with four concrete capabilities but provides no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 rather than reaching the explicit-when level 3.	2 / 3
Trigger Term Quality	Contains natural terms a user would say ("track ML experiments", "model registry", "deploy models", "reproduce experiments", "MLflow") with good coverage; not merely technical jargon, so it sits above level 2's "missing common variations".	3 / 3
Distinctiveness Conflict Risk	The "MLflow - framework-agnostic ML lifecycle platform" niche with MLflow/model-registry/experiment-tracking triggers is clearly distinguishable and unlikely to fire for unrelated skills, matching the level-3 clear-niche anchor.	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
skill_md_line_count	SKILL.md is long (706 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/ml-training/mlflow/SKILL.md
Commit: 52845c3

Reviewed: about 13 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.