evaluating-machine-learning-models

Evaluate trained machine learning models with the right metrics and comparison logic. Use for benchmark review, threshold selection, calibration, validation, and model comparison; not for feature engineering or leakage auditing.

Quality

62%

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 ./bundled/skills/evaluating-machine-learning-models/SKILL.md

Quality

Content

37%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 concise and well-organized at a section level but offers little actionable guidance: no code, no evaluation workflow, and no links to the bundled scripts and references that would make it executable. It reads as a scope statement rather than an operating manual.

Suggestions

Add a concrete evaluation workflow (load predictions -> compute metrics via scripts/metrics_calculator.py -> compare models -> report) with validation checkpoints so Claude can execute it step by step.

Reference the bundled resources inline, e.g. 'See scripts/evaluate_model.py to run evaluation' and 'See references/metrics_definitions.md for metric definitions', so progressive disclosure points to real files.

Include one or two executable snippets or exact commands (e.g. invoking evaluate_model.py with example args) to move from descriptive to actionable guidance.

Dimension	Reasoning	Score
Conciseness	Lean and does not over-explain concepts Claude already knows; the Overview and intro line ('Use this skill when the model exists...') are minor generic framing that could be trimmed.	4 / 5
Actionability	Provides only high-level descriptions and output lists ('Metric suite recommendations', 'Model comparison tables') with no executable code or commands, and never references the bundled scripts in ./scripts/.	2 / 5
Workflow Clarity	No sequenced workflow or validation checkpoints are present, even though model evaluation is a multi-step process; the body only lists when/what/outputs rather than steps.	1 / 5
Progressive Disclosure	Section structure is clean, but the body references none of the existing bundle files (evaluate_model.py, metrics_calculator.py, references/metrics_definitions.md), so navigation to the bundled detail is missing.	3 / 5
	Total	10 / 20 Passed

Description

87%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, well-scoped description that clearly states what the skill does and when to use it, with good trigger-term coverage and explicit boundaries against neighboring skills. The only minor gap is the slightly generic 'right metrics and comparison logic' framing.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('benchmark review, threshold selection, calibration, validation, and model comparison'), but the lead phrase 'with the right metrics and comparison logic' is slightly generic compared to the comprehensive-coverage anchor.	4 / 5
Completeness	Explicitly answers both what ('Evaluate trained machine learning models with the right metrics and comparison logic') and when ('Use for ...; not for ...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural keywords a user would say ('benchmark review', 'threshold selection', 'calibration', 'validation', 'model comparison'); a few common synonyms and metric names (e.g. 'model evaluation', AUC/F1) are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (post-training model evaluation) with explicit boundary carve-outs ('not for feature engineering or leakage auditing') that minimize overlap with adjacent skills.	5 / 5
	Total	18 / 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
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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/evaluating-machine-learning-models/SKILL.md
Commit: d5ae560

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.