evaluating-machine-learning-models

Build this skill allows AI assistant to evaluate machine learning models using a comprehensive suite of metrics. it should be used when the user requests model performance analysis, validation, or testing. AI assistant can use this skill to assess model accuracy, p... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Quality

16%

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 ./plugins/ai-ml/model-evaluation-suite/skills/evaluating-machine-learning-models/SKILL.md

Quality

Content

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

The body is a template-like wall of generic sections with no executable guidance, no real workflow detail, and references to non-existent script files. It adds little that Claude does not already know and fails to instruct concretely.

Suggestions

Replace generic sections with a concrete worked example showing the actual /eval-model invocation, required parameters, and expected output format.

Remove filler sections (Overview, Best Practices, Prerequisites, Output, Resources) that restate common knowledge, keeping only actionable guidance.

Either add the referenced scripts (evaluate_model.py, metrics_calculator.py) to ./scripts or remove the dangling references to files that do not exist.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic filler sections (Overview, How It Works, Best Practices, Prerequisites, Output, Resources) restating what Claude already knows, e.g. 'The skill produces structured output relevant to the task.'	1 / 3
Actionability	It provides no executable code or concrete commands — only vague directives like 'Invoke the /eval-model command' and 'Review the generated output' without parameters, examples, or usage.	1 / 3
Workflow Clarity	Steps are generic and unspecific (e.g. 'Provide necessary context and parameters', 'Apply modifications as needed') with no sequence detail and no validation checkpoints for batch evaluation operations.	1 / 3
Progressive Disclosure	The body is organized into sections, but it references bundle files (scripts like evaluate_model.py) that are not actually present in ./scripts, and most content is generic inline text that adds no navigational value.	2 / 3
	Total	5 / 12 Passed

Description

25%

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 padded with filler, contains a truncation artifact, and uses generic boilerplate trigger language rather than concrete actions or natural keywords. It weakly answers 'what' but fails to provide genuine 'when' guidance.

Suggestions

Replace generic filler with concrete actions, e.g. 'Evaluate ML model accuracy, precision, recall, and F1-score; compare models side by side.'

Replace 'Use when appropriate context detected' with natural trigger phrases a user would say, e.g. 'Use when the user asks to evaluate, benchmark, or compare model performance.'

Use third-person voice and remove the truncated 'assess model accuracy, p...' fragment and 'Build this skill' preamble.

Dimension	Reasoning	Score
Specificity	The description uses vague phrasing like 'comprehensive suite of metrics' and a truncated 'assess model accuracy, p...' rather than naming concrete actions, matching the vague/abstract anchor.	1 / 3
Completeness	It states a partial 'what' (evaluate ML models with metrics) and includes a 'Use when' clause, but the 'when' is generic and implied rather than explicit, capping completeness at 2.	2 / 3
Trigger Term Quality	The trigger guidance is generic boilerplate — 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose' — with no natural keywords a user would actually say.	1 / 3
Distinctiveness Conflict Risk	The 'evaluate machine learning models' domain is somewhat specific but the generic trigger language and broad metrics framing means it could overlap with other ML/performance skills.	2 / 3
	Total	6 / 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
Path: plugins/ai-ml/model-evaluation-suite/skills/evaluating-machine-learning-models/SKILL.md
Commit: 15940c5

Reviewed: about 3 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.