tracking-model-versions

Build this skill enables AI assistant to track and manage ai/ml model versions using the model-versioning-tracker plugin. it should be used when the user asks to manage model versions, track model lineage, log model performance, or implement version control f... Use when appropriate context detected. 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

80%

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

The content body is well-structured, concise, and actionable, providing concrete MLflow commands, realistic examples, and a useful error-handling table. Its main weaknesses are missing validation checkpoints around destructive registry transitions and incomplete bundle navigation (unreferenced files, a stale scripts README, and a broken resource link).

Suggestions

Add an explicit validation checkpoint before promoting a model to Production (e.g., compare metrics against baseline and confirm before `transition_model_version_stage()`), with a fix-and-retry loop.

Reconcile the bundle: reference versioning_diagram.png and scripts/version_control.py from the body, and fix the scripts/README which lists nonexistent files (model_registry_client.py, performance_logger.py, version_control.sh).

Fix the broken Weights & Biases Model Registry link in the Resources section or remove the empty entry.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense: a one-paragraph overview, a tight prerequisites list, eight concrete numbered steps, focused examples, and a compact error table, with no padding explaining what MLflow or model versioning is.	3 / 3
Actionability	Steps cite real, executable MLflow calls (`mlflow experiments list`, `mlflow.<flavor>.log_model()`, `mlflow.register_model()`, `client.transition_model_version_stage()`, `mlflow.search_runs()`) and the examples include concrete hyperparameters and metrics, with a referenced complete workflow YAML.	3 / 3
Workflow Clarity	The eight-step sequence is clearly ordered and step 1 verifies connectivity, but registry stage transitions and archiving of prior production versions are destructive/batch operations with no explicit validation checkpoint before promotion; checkpoints are otherwise only implicit or relegated to the error table.	2 / 3
Progressive Disclosure	The body correctly signals one-level-deep references to real asset files (`assets/model_card_template.md`, `assets/example_mlflow_workflow.yaml`), but other bundle files are unreferenced (versioning_diagram.png, scripts/version_control.py), the scripts README lists files that do not exist, and the Resources section has a broken Weights & Biases link.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 garbled and auto-generated, opening with 'Build this skill enables AI assistant to...' and truncating mid-phrase ('version control f...') before collapsing into placeholder trigger text. It names a real niche and some actions but fails to clearly and cleanly state what the skill does and when to use it.

Suggestions

Rewrite the description in clean third person without the 'Build this skill enables AI assistant to...' framing and the truncated 'f...' text.

Replace the placeholder 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.' with concrete trigger phrases users would actually say (e.g., model versions, MLflow registry, model lineage, model cards).

Add concrete tool-specific keywords (MLflow, DVC, Weights & Biases, model registry) to improve trigger term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('track and manage ai/ml model versions', 'track model lineage', 'log model performance', 'implement version control'), but the actions are fairly generic verbs and the phrase is truncated mid-word ('version control f...').	2 / 3
Completeness	Attempts both 'what' and 'when' ('it should be used when the user asks to...'), but the trigger clause is truncated and the remainder is generic placeholder guidance rather than clear explicit triggers, so it does not clearly answer 'when'.	2 / 3
Trigger Term Quality	Includes some relevant natural phrases ('manage model versions', 'track model lineage', 'log model performance') but misses common variations (MLflow, model registry, DVC, Weights & Biases) and falls back to placeholder text ('Trigger with relevant phrases based on skill purpose').	2 / 3
Distinctiveness Conflict Risk	The ML model-versioning niche is somewhat specific, but the generic 'implement version control' phrasing and placeholder triggers leave overlap with general version-control skills.	2 / 3
	Total	8 / 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.