agent-neural-network
Agent skill for neural-network - invoke with $agent-neural-network
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-neural-network35
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
0%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 description is critically deficient across all dimensions. It provides only a name and invocation command without explaining capabilities, use cases, or trigger conditions. Claude would have no basis for selecting this skill appropriately from a skill library.
Suggestions
Add specific concrete actions the skill performs (e.g., 'Trains neural network models, performs inference, visualizes network architectures, tunes hyperparameters')
Include an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks about training models, deep learning, building neural networks, or ML predictions')
Remove the invocation command from the description and replace with functional content that distinguishes this from other ML-related skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for neural-network' is completely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command, not functional information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'neural-network' which is technical jargon. No natural user terms like 'train model', 'deep learning', 'AI', 'machine learning', or specific tasks are included. | 1 / 3 |
Distinctiveness Conflict Risk | 'Neural-network' is extremely broad and could conflict with any ML/AI-related skill. There are no specific triggers or use cases to distinguish it from other machine learning skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable overview of neural network capabilities with useful MCP tool examples, but reads more like a capability description than actionable guidance. The workflow section is too abstract, lacking concrete step-by-step instructions with validation checkpoints. The content would benefit from trimming explanatory prose Claude already knows and adding executable end-to-end examples.
Suggestions
Replace the abstract 6-step workflow with a concrete example showing the full sequence: data prep → cluster init → train → validate → deploy, with explicit validation checkpoints between steps
Remove or drastically condense the 'Neural architectures you specialize in' and 'Quality standards' sections - Claude knows these concepts
Add a complete end-to-end example showing how to train a simple model and run inference, including error handling and what to do if training fails
Extract advanced topics (federated learning, distributed consensus, model compression) to separate reference files and link to them
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Contains some unnecessary explanation (e.g., listing neural architecture types Claude already knows, verbose quality standards). The toolkit section is efficient, but the surrounding prose could be significantly tightened. | 2 / 3 |
Actionability | Provides concrete JavaScript/MCP tool examples which are helpful, but they appear to be pseudocode-style demonstrations rather than complete executable workflows. Missing actual data preparation, error handling, and real usage patterns. | 2 / 3 |
Workflow Clarity | The 6-step ML workflow is abstract and descriptive rather than actionable. No validation checkpoints, no error recovery steps, no concrete sequence showing how to chain the MCP tools together for a complete training-to-deployment flow. | 1 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one file. For a skill this comprehensive, advanced topics like federated learning, distributed training topology, and model compression should reference separate detailed guides. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%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.
- Reviewed
Table of Contents
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.