agent-data-ml-model

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

1.16x

Quality

—

Does it follow best practices?

Impact

93%

1.16x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

35%

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

The body mixes a misplaced, verbose YAML configuration block with a reasonably structured but incomplete ML guide. The markdown section offers a usable pipeline skeleton, but lacks validation steps and concrete model details, and the config noise hurts token efficiency.

Suggestions

Remove or relocate the inline YAML configuration block; keep SKILL.md focused on actionable ML instructions.

Replace the 'ModelClass()' placeholder with a concrete estimator and add validation/checkpoint steps (e.g., evaluate metrics before deployment, rollback on failure).

Split detailed reference material into bundle files under references/ and link to them one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body opens with a ~120-line YAML configuration block (triggers, capabilities, hooks, constraints) that is not actionable instruction and pads the skill with context Claude does not need, dominating the token budget.	1 / 3
Actionability	The sklearn Pipeline code example is mostly executable, but it uses a placeholder 'ModelClass()' rather than a concrete model, and the surrounding workflow steps stay abstract instead of giving copy-paste-ready guidance.	2 / 3
Workflow Clarity	The five-step ML workflow is sequenced, but there are no validation checkpoints or feedback loops for batch training and deployment — operations the body itself flags as confirmation-required — capping clarity at 2.	2 / 3
Progressive Disclosure	The markdown portion has organized sections, but the large inline YAML config block is monolithic content that should live elsewhere, and no bundle files exist to offload detail, so structure is only partial.	2 / 3
	Total	7 / 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 a bare invocation stub with no statement of capabilities or trigger conditions, failing every dimension. It reads as a placeholder rather than a usable skill description.

Suggestions

Rewrite the description to list concrete ML actions (e.g., 'Train, evaluate, and serialize ML models; build preprocessing pipelines').

Add an explicit 'Use when...' clause naming natural trigger terms users would say, such as 'machine learning', 'train a model', 'classifier', or 'notebook'.

Replace the technical identifier 'data-ml-model' with user-facing language and a distinct niche to reduce conflict with other skills.

Dimension	Reasoning	Score
Specificity	The description only states 'Agent skill for data-ml-model - invoke with $agent-data-ml-model', naming no concrete actions or capabilities, just an invocation hint.	1 / 3
Completeness	It answers neither 'what does this do' (no actions described) nor 'when should Claude use it' (no 'Use when...' clause), so both halves are missing.	1 / 3
Trigger Term Quality	It contains no natural keywords a user would say; 'data-ml-model' is a technical identifier, not language users actually use when they need the skill.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic and provides no distinct triggers, so it would conflict with many other skills and fail to differentiate.	1 / 3
	Total	4 / 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
Commit: 8ae8752

Reviewed: 2 days 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.