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

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-neural-network/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an extremely weak description that provides virtually no useful information for skill selection. It lacks any concrete actions, trigger terms, use-case guidance, or distinguishing details. It reads more like a label than a description and would be nearly impossible for Claude to correctly select from a pool of skills.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Builds, trains, and evaluates neural network models using frameworks like PyTorch or TensorFlow. Supports architectures including CNNs, RNNs, and transformers.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about training neural networks, building deep learning models, configuring layers, or optimizing model performance.'

Remove the invocation syntax ('invoke with $agent-neural-network') from the description and replace it with domain-specific keywords that help distinguish this skill from other ML-related skills.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It only says 'Agent skill for neural-network' which is entirely vague and abstract, providing no information about what the skill actually does.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance.	1 / 3
Trigger Term Quality	The only keyword present is 'neural-network', which is a broad technical term. There are no natural user-facing trigger terms like 'train model', 'deep learning', 'classify', 'predict', etc. The invocation syntax '$agent-neural-network' is not a natural user phrase.	1 / 3
Distinctiveness Conflict Risk	'Neural-network' is extremely broad and could overlap with any ML, AI, deep learning, or data science skill. There is nothing to distinguish this from other potential machine learning related skills.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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

This skill is primarily a persona description and knowledge dump rather than actionable instructions. It spends most of its tokens explaining ML concepts Claude already knows (what LSTMs are, what GANs do) while providing minimal concrete guidance on how to actually use the Flow Nexus tools effectively. The three code examples are the only valuable content, but they lack context on expected outputs, error handling, and practical chaining.

Suggestions

Remove all explanatory content about neural network types and ML concepts—Claude already knows these. Focus exclusively on Flow Nexus-specific tool usage, parameters, and behaviors.

Add concrete workflow examples showing how to chain the MCP tools together (e.g., init cluster → train → validate → predict) with expected responses and error handling at each step.

Add explicit validation checkpoints: how to check training status, verify model quality before deployment, and handle failed training runs.

Split advanced topics (federated learning, distributed consensus) into a separate reference file and keep SKILL.md focused on the core train/predict workflow.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive lists of concepts Claude already knows (neural architecture types, ML workflow steps, quality standards). The bullet-point lists describing feedforward networks, LSTMs, CNNs, etc. add zero value—Claude knows what these are. Most of the content is descriptive padding rather than actionable instruction.	1 / 3
Actionability	The JavaScript code examples showing the MCP tool calls with specific parameter structures are concrete and useful. However, much of the content is vague guidance ('consider scalability, reproducibility') rather than executable instructions, and there's no guidance on error handling, expected responses, or how to chain these tools together in practice.	2 / 3
Workflow Clarity	The 6-step 'ML workflow approach' is generic and abstract with no validation checkpoints, no error recovery steps, and no concrete commands at each stage. For operations involving distributed training and model deployment (which are complex and potentially destructive), the complete absence of validation steps and feedback loops is a significant gap.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files, no clear separation between quick-start and advanced content, and no navigation structure. Everything from basic tool usage to advanced federated learning concepts is dumped into a single flat document.	1 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: f547cec

Reviewed: 4 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.