agent-neural-network

Agent skill for neural-network - invoke with $agent-neural-network

1.60x

Quality

—

Does it follow best practices?

Impact

96%

1.60x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

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 content provides concrete MCP tool examples and a sequenced workflow, but it is padded with role-play and concept explanations Claude already knows, and the workflow lacks validation checkpoints. It would benefit from trimming filler and adding concrete error-handling steps.

Suggestions

Remove or condense the 'Neural architectures you specialize in' explanations and role-play intro; assume Claude knows what feedforward/LSTM/CNN/GAN networks are.

Add explicit validation/feedback steps to the ML workflow (e.g., check training loss convergence, validate model metrics before deployment, retry on failure).

Split the architecture reference and API toolkit into separate reference files (e.g. references/architectures.md, references/toolkit.md) and keep SKILL.md as a concise overview.

Dimension	Reasoning	Score
Conciseness	The body mixes genuinely useful code blocks with role-play framing ('You are a Flow Nexus Neural Network Agent, an expert...') and re-teaches known concepts ('Feedforward: Classic dense networks', 'LSTM/RNN: Sequence modeling'), so it could be tightened.	2 / 3
Actionability	Concrete MCP code calls with full parameter schemas are present, but the surrounding workflow steps are abstract ('Determine computational requirements and distributed training strategy') and lack executable specifics.	2 / 3
Workflow Clarity	Six numbered steps are sequenced, but there are no validation checkpoints or feedback loops for a batch/destructive-domain task like model training and deployment, which caps clarity at 2.	2 / 3
Progressive Disclosure	No bundle files exist and the skill is a single ~80-line monolithic document; section headers provide some structure, but content like the architecture reference and quality standards could be split out.	2 / 3
	Total	8 / 12 Passed

Description

22%

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 name restatement plus invocation boilerplate that fails to convey concrete capabilities or usage triggers. It would be hard for a user (or Claude) to know when this skill applies versus generic ML tooling.

Suggestions

Replace the generic 'Agent skill for neural-network - invoke with $agent-neural-network' with concrete actions, e.g. 'Train, deploy, and manage distributed neural networks...'.

Add an explicit 'Use when...' clause naming natural user triggers such as 'train a neural network', 'distributed model training', or 'deploy a deep learning model'.

Drop the invocation syntax from the description; it does not help with capability recognition or trigger matching.

Dimension	Reasoning	Score
Specificity	The description is 'Agent skill for neural-network - invoke with $agent-neural-network', which restates the skill name and gives an invocation hint but names no concrete actions, matching the vague/no-actions anchor.	1 / 3
Completeness	There is no substantive 'what' (only 'Agent skill for neural-network') and no 'when'/'Use when' trigger clause, so both halves are weak or missing.	1 / 3
Trigger Term Quality	'neural-network' is a relevant keyword a user might say, but it is just the skill name with no common variations like 'train model', 'deep learning', or 'deploy model'.	2 / 3
Distinctiveness Conflict Risk	'neural-network' identifies a recognizable niche, but it is broad and could overlap with general deep-learning or ML-deployment skills.	2 / 3
	Total	6 / 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.