building-neural-networks
Execute this skill allows AI assistant to construct and configure neural network architectures using the neural-network-builder plugin. it should be used when the user requests the creation of a new neural network, modification of an existing one, or assistance... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
16
3%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/ai-ml/neural-network-builder/skills/building-neural-networks/SKILL.mdQuality
Discovery
7%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 severely weakened by placeholder text ('Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.') and an incomplete capability list that trails off with ellipsis. It fails to provide actionable trigger terms and reads as a template that was never properly filled in, making it nearly useless for skill selection among multiple options.
Suggestions
Replace the placeholder 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.' with explicit trigger guidance, e.g., 'Use when the user asks to build, design, or configure a neural network, mentions layers, architectures, or deep learning model creation.'
Complete the truncated capability list with specific actions, e.g., 'Constructs neural network architectures, adds and configures layers (dense, convolutional, recurrent), sets activation functions, defines optimizers and loss functions, and exports model configurations.'
Remove the first-person/imperative framing ('Execute this skill allows AI assistant') and rewrite in third person, e.g., 'Constructs and configures neural network architectures using the neural-network-builder plugin.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | While it mentions 'construct and configure neural network architectures' and references a plugin name, the description trails off with '...' and the actual capabilities are vague. It doesn't list specific concrete actions like 'add layers, set hyperparameters, define loss functions'. | 1 / 3 |
Completeness | The 'what' is partially stated but incomplete (trails off with '...'). The 'when' clause is entirely placeholder text ('Use when appropriate context detected') with no explicit triggers, which is effectively missing. | 1 / 3 |
Trigger Term Quality | The description ends with the generic filler 'Trigger with relevant phrases based on skill purpose' which provides zero actual trigger terms. Natural keywords like 'neural network', 'deep learning', 'model architecture', 'layers', 'training' are mostly absent or buried in vague phrasing. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'neural-network-builder plugin' and 'neural network architectures' does carve out a somewhat specific domain, but the vague trailing text and lack of concrete triggers could cause overlap with general ML/AI coding skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is almost entirely generic boilerplate with no actionable content. It never shows the actual syntax for the `build-nn` command, provides no configuration schemas or real code examples, and fills its length with vague descriptions of what Claude would do rather than concrete instructions on how to do it. Every section reads like a template placeholder rather than genuine skill content.
Suggestions
Add the actual `build-nn` command syntax with complete, executable examples showing real configuration parameters (e.g., layer definitions, activation functions, hyperparameters) for at least one architecture type.
Remove all generic boilerplate sections (Prerequisites, Instructions, Output, Error Handling, Resources) that contain no skill-specific information, and replace with concrete command references and configuration schemas.
Show a complete end-to-end example with the exact command invocation and expected output, including validation steps to verify the generated network architecture is correct.
Define the configuration format/schema that `build-nn` expects (JSON, YAML, CLI flags, etc.) so Claude knows exactly what to generate rather than abstractly 'generating configuration'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanation of concepts Claude already knows. Sections like 'Overview', 'How It Works', 'Best Practices', 'Integration', 'Prerequisites', 'Instructions', 'Output', 'Error Handling', and 'Resources' are filled with generic platitudes and boilerplate that add no actionable information. Nearly every sentence describes rather than instructs. | 1 / 3 |
Actionability | No concrete code, commands, configuration schemas, or executable examples anywhere. The examples describe what 'the skill will' do at a high level but never show actual configuration syntax, command invocations with arguments, or expected output. The `build-nn` command is mentioned but never demonstrated with actual parameters or syntax. | 1 / 3 |
Workflow Clarity | The 'How It Works' section lists three abstract steps (analyzing, generating, executing) with no concrete details, no validation checkpoints, and no error recovery loops. The examples similarly describe abstract steps without showing actual commands or verification. The 'Instructions' section is completely generic boilerplate. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of generic text with no references to external files, no bundle files to support it, and no meaningful structure that aids navigation. Sections like 'Resources' point to nothing specific ('Project documentation', 'Related skills and commands'). Content is poorly organized with redundant sections. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
69c73e9
- 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.