agent-data-ml-model

Agent skill for data-ml-model - invoke with $agent-data-ml-model

1.16x

Quality

35%

Does it follow best practices?

Impact

93%

1.16x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-data-ml-model/SKILL.md

Quality

Content

46%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 contains a useful, executable ML workflow and code template but is weighed down by a large inlined YAML agent-config block that belongs in a separate file, and lacks explicit validation checkpoints in the training workflow.

Suggestions

Move the 120-line YAML config block (triggers, capabilities, constraints, hooks) into a separate bundled file (e.g. references/agent-config.yaml) and reference it from the body, restoring token efficiency and progressive disclosure.

Add an explicit validation/feedback checkpoint to the workflow, e.g. after Evaluation: 'If validation metric < target, adjust hyperparameters and retrain; only proceed to Deployment Prep when the metric is acceptable.'

Replace the ModelClass() placeholder in the code example with a concrete classifier/regressor snippet or a short enumerated list of common algorithm choices so the example is copy-paste-ready.

Dimension	Reasoning	Score
Conciseness	The body inlines a ~120-line YAML agent-config block (triggers, capabilities, hooks with echo statements, examples) that adds heavy token padding with little instructional value, matching anchor 2 ('noticeably verbose; several unnecessary padded sections'); the lean markdown workflow section keeps it from dropping to 1.	2 / 5
Actionability	The code-patterns section gives a concrete, executable sklearn Pipeline example (train_test_split, StandardScaler, fit, score) and the workflow lists specific steps, fitting anchor 4 ('mostly executable guidance; concrete code with minor gaps'); it stops short of 5 because ModelClass() is a placeholder rather than copy-paste-ready for a concrete case.	4 / 5
Workflow Clarity	A clear 5-step ML workflow (Data Analysis -> Preprocessing -> Model Development -> Evaluation -> Deployment Prep) is sequenced, but explicit validation checkpoints and feedback loops (e.g. 'if metric below threshold, retrain') are missing or implicit, matching anchor 3; it cannot reach 4 without explicit checkpoints for this batch-training process.	3 / 5
Progressive Disclosure	No bundle files exist and the body inlines a large config block that clearly belongs in a separate file, with no references or signaled navigation, matching anchor 2 ('content that clearly belongs in separate files is inlined'); the section headers in the markdown portion are not enough to reach 3 given the dominant inlined config.	2 / 5
	Total	11 / 20 Passed

Description

25%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 an auto-generated template that names a domain and an invocation command but describes no capabilities, no natural trigger phrases, and no use-conditions, making it nearly indistinguishable from other templated agent skills.

Suggestions

Replace the templated line with concrete actions, e.g. 'Build, train, and evaluate machine learning models: preprocess data, engineer features, tune hyperparameters, and prepare models for deployment.'

Add an explicit 'Use when...' clause with natural trigger phrases such as 'machine learning', 'train a classifier/regressor', 'neural network', or 'ML pipeline'.

Include user-facing file extensions and synonyms (.ipynb, .pkl, .h5, .joblib) so the skill triggers on real user phrasing rather than the skill's own internal name.

Dimension	Reasoning	Score
Specificity	The description ('Agent skill for data-ml-model - invoke with $agent-data-ml-model') names the domain but states zero concrete actions, matching anchor 2 ('Names the domain but actions are minimal or generic') rather than 1 only because it does identify a domain; it cannot reach 3 because no concrete capability verbs are present.	2 / 5
Completeness	It offers only a vague 'what' ('Agent skill for data-ml-model') and no 'when' trigger guidance at all, matching anchor 2 ('Has a vague what and no when'); per the rubric a missing 'Use when...' clause caps completeness at 3, and this is well below that, so it cannot be 3.	2 / 5
Trigger Term Quality	The only keyword is the skill's own technical identifier 'data-ml-model' plus an invocation hint ('$agent-data-ml-model'), with no natural user phrases like 'train model' or 'machine learning', fitting anchor 2 ('one or two generic keywords; missing the natural phrases users say') and falling short of 3 which requires relevant keywords.	2 / 5
Distinctiveness Conflict Risk	The phrasing is a generic template ('Agent skill for X - invoke with $X') that every sibling agent skill would share, giving high overlap risk as in anchor 2; the bare domain name is not enough to reach 3's 'somewhat specific but could still overlap'.	2 / 5
	Total	8 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/agent-data-ml-model/SKILL.md
Commit: fa13ee4

Reviewed: about 5 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.