CtrlK
BlogDocsLog inGet started
Tessl Logo

training-machine-learning-models

Build train machine learning models with automated workflows. Analyzes datasets, selects model types (classification, regression), configures parameters, trains with cross-validation, and saves model artifacts. Use when asked to "train model" or "evalua... Trigger with relevant phrases based on skill purpose.

40

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

20%

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

The body reads as a generic skill template: it describes an ML training workflow at a high level with no executable code or commands, and leaves placeholder sections ('Output', 'Resources', 'Instructions', 'Error Handling') that add no skill-specific value. Bundle files exist in assets/ but are never linked from the body.

Suggestions

Replace the generic 'Instructions', 'Output', 'Resources', and 'Error Handling' placeholder sections with skill-specific content or remove them; link to the actual bundle files (e.g., assets/evaluation_report_template.md, assets/example_dataset.csv) instead of 'Project documentation'.

Add at least one concrete, executable example — e.g., a scikit-learn snippet showing train_test_split, model.fit, cross_val_score, and joblib.dump of the artifact — so the guidance is copy-paste ready rather than descriptive.

Insert validation checkpoints into the workflow, such as verifying input data shape/target presence before training and reporting cross-validation metrics before saving the model artifact.

DimensionReasoningScore

Conciseness

Much of the body is generic, non-informative boilerplate that earns no token budget — 'The skill produces structured output relevant to the task', 'Resources: Project documentation', and 'Instructions: 1. Invoke this skill when the trigger conditions are met ... Apply modifications as needed' could describe any skill.

1 / 3

Actionability

It describes rather than instructs: examples only say the skill 'will select a suitable classification algorithm ... train the model using cross-validation', with no executable code, commands, library choices, or parameter specifics anywhere in the body.

1 / 3

Workflow Clarity

The 'How It Works' section gives a clear three-step sequence (data analysis, model selection/training, evaluation/persistence), but there are no validation checkpoints, no concrete commands, and the 'Error Handling' section is generic, so checkpoints are missing or implicit.

2 / 3

Progressive Disclosure

The body is organized into sections, but it never references the real bundle files that exist (assets/evaluation_report_template.md, assets/example_dataset.csv, assets/requirements.txt); the 'Resources' section lists only placeholder text, so the available references are not signaled or navigable.

2 / 3

Total

6

/

12

Passed

Description

60%

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 states a clear set of concrete capabilities but its trigger guidance is broken and placeholder-filled: 'evalua...' is truncated mid-word and 'Trigger with relevant phrases based on skill purpose' is a template instruction left in the final text. The 'what' is strong; the 'when' is present but not usable as written.

Suggestions

Fix the truncated trigger clause — complete 'evalua...' (e.g., 'evaluate a model') and replace the placeholder 'Trigger with relevant phrases based on skill purpose' with concrete natural-language triggers users would actually say.

Add trigger-term variations such as 'train a model', 'evaluate model performance', 'fit a classifier/regressor', and 'cross-validate' to improve coverage and distinctiveness.

Correct the opening 'Build train machine learning models' to a grammatical form like 'Train and evaluate machine learning models' to match the third-person voice used in the rest of the description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Analyzes datasets, selects model types (classification, regression), configures parameters, trains with cross-validation, and saves model artifacts' — matching the multiple-specific-actions anchor; the 'Build train' phrasing is a minor grammar slip but does not reduce the action specificity.

3 / 3

Completeness

The 'what' is clearly answered, and a 'Use when...' clause exists, but the 'when' is truncated ('evalua...') and followed by a placeholder, so it does not 'clearly answer both what AND when with explicit triggers' as required for a 3.

2 / 3

Trigger Term Quality

'Use when asked to "train model"' is a natural phrase, but coverage is thin and damaged: 'evalua...' is truncated mid-word and 'Trigger with relevant phrases based on skill purpose' is a placeholder meta-instruction rather than real trigger terms.

2 / 3

Distinctiveness Conflict Risk

The ML-model-training niche (classification/regression, cross-validation, model artifacts) is identifiable, but the single generic 'train model' trigger and placeholder language mean it could still overlap with adjacent ML/data skills.

2 / 3

Total

9

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.