mlflow

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

Quality

70%

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 ./skills/mlops/mlflow/SKILL.md

Quality

Content

68%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.

The body is highly actionable with comprehensive executable examples and a clear reference structure, but it suffers from redundancy and lacks validation checkpoints around destructive model-registry operations.

Suggestions

Consolidate the three separate autologging treatments into a single section to remove redundancy and tighten the token budget.

Add explicit validation/verification steps around destructive model-registry stage transitions (e.g., confirm the target version and stage, verify after transition) to lift workflow clarity above 3.

Trim marketing figures ("20,000+ organizations", "23k+ stars") and avoid inlining deep registry/tracking/deployment detail that already lives in the reference files, pointing there instead.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient code, but it is noticeably redundant — autologging appears in Quick Start, a dedicated Autologging section, and again in Integration Examples — and includes marketing fluff ("20,000+ organizations", "23k+ stars" stated twice) that could be trimmed.	3 / 5
Actionability	Abundant copy-paste-ready, executable code covers the common cases — tracking, autologging, model registry, searching runs, and deployment — matching the level-5 anchor for fully executable guidance.	5 / 5
Workflow Clarity	Content is organized as a feature catalog rather than sequenced workflows, and destructive Production stage transitions (archive_existing_versions=True) have no validation/verification checkpoint, capping workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Three real reference files (tracking.md, model-registry.md, deployment.md) are clearly signaled in a "See Also" section and the body is well-sectioned, though much of the inlined content overlaps the references, leaving it just below the level-5 anchor.	4 / 5
	Total	15 / 20 Passed

Description

71%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.

The description is specific and action-oriented with good trigger terms and a clear MLflow niche, but it omits an explicit "Use when…" trigger clause, capping completeness at 3.

Suggestions

Add an explicit "Use when…" trigger clause, e.g., "Use when tracking ML experiments, managing a model registry, deploying models, or reproducing ML runs with MLflow."

Include more natural user phrasings such as "log metrics", "log hyperparameters", and "model serving" to broaden trigger coverage.

Drop the marketing-style tag "- framework-agnostic ML lifecycle platform" or fold it into the trigger clause to keep the description lean.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Track ML experiments", "manage model registry with versioning", "deploy models to production", "reproduce experiments" — giving comprehensive coverage of the platform's capabilities, matching the level-5 anchor's multi-action example.	5 / 5
Completeness	The "what" is clearly stated via four concrete actions, but there is no "Use when…" clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms like "ML experiments", "model registry", "deploy models", and "MLflow" are present, but common variations users say (e.g., "log metrics", "hyperparameters", "model serving") are missing, so it sits just below the comprehensive level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Naming the MLflow platform gives it a clear, distinct niche with minimal conflict risk, though the generic ML-lifecycle framing leaves minor overlap with adjacent MLOps skills, placing it just below the level-5 anchor.	4 / 5
	Total	16 / 20 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 (705 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: OpenLAIR/dr-claw
Path: skills/mlops/mlflow/SKILL.md
Commit: 4b35756

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.