agent-data-ml-model

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

1.16x

Quality

28%

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

50%

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

The body gives a usable, well-structured ML workflow with a concrete code example, but is weighed down by an oversized inline YAML config block, placeholder code, a typo, and missing validation checkpoints for risky training/deployment steps.

Suggestions

Move the embedded YAML config block (triggers, capabilities, constraints, hooks) into a separate reference file and keep SKILL.md as a concise overview pointing to it.

Replace the 'ModelClass()' placeholder with a concrete estimator and fix the 'Feature scaling$normalization' typo so the code example is copy-paste ready.

Add explicit validation checkpoints to the workflow, e.g. 'Evaluate on held-out data before deployment' and 'If metrics fall below threshold, tune hyperparameters and retrain'.

Dimension	Reasoning	Score
Conciseness	The markdown instructions are reasonably lean, but the body opens with a ~120-line embedded YAML config block (triggers, capabilities, hooks, integration) that largely restates configuration rather than teaching Claude anything new, so it could be tightened.	2 / 3
Actionability	A concrete, mostly-executable sklearn Pipeline example is provided, but it uses a placeholder 'ModelClass()' and contains a broken token ('Feature scaling$normalization'), so it is not fully copy-paste ready.	2 / 3
Workflow Clarity	A clear five-step ML workflow is sequenced with sub-bullets, but there are no explicit validation checkpoints (e.g. evaluate-before-deploy, retrain-on-failure) for batch training and model-deployment operations the rubric flags as needing feedback loops.	2 / 3
Progressive Disclosure	Sections are organized with clear headers, but no bundle files exist and the large inline YAML config block is content that should live in a separate reference file, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	8 / 12 Passed

Description

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 boilerplate that restates the skill name and invocation syntax without explaining any concrete ML capabilities or when to use the skill. It fails specificity, trigger quality, and completeness outright.

Suggestions

Rewrite the description to list concrete actions, e.g. 'Build, train, and evaluate machine learning models; preprocess data and prepare models for deployment.'

Add an explicit trigger clause: 'Use when the user asks to create or train an ML model, build a classification/regression pipeline, or work with .ipynb/.pkl/.h5 model artifacts.'

Use third-person action verbs and natural user terms (e.g. 'train model', 'classification', 'neural network') instead of the skill identifier and '$invoke' syntax.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for data-ml-model - invoke with $agent-data-ml-model' names no concrete actions at all — it only restates the skill name and an invocation syntax, matching the vague/abstract anchor.	1 / 3
Completeness	It answers neither 'what does this do' (only restates the skill name) nor 'when should Claude use it' (no 'Use when...' clause), failing both halves of the completeness criterion.	1 / 3
Trigger Term Quality	'data-ml-model' and 'invoke with $agent-data-ml-model' are a skill identifier and invocation syntax, not natural terms a user would say when they need ML help, so there are no usable natural keywords.	1 / 3
Distinctiveness Conflict Risk	It names a specific skill niche (data-ml-model) so it would not collide with unrelated skills, but the phrasing is generic boilerplate ('Agent skill for X - invoke with $X') that is identical across sibling agent skills, so overlap risk remains.	2 / 3
	Total	5 / 12 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/claude-flow
Path: .agents/skills/agent-data-ml-model/SKILL.md
Commit: 26c35b5

Reviewed: about 2 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.