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.

Quality

43%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/ai-ml/neural-network-builder/skills/building-neural-networks/SKILL.md

Quality

Content

37%Weight 40%Scale 1-3

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

The content is well-sectioned and outlines a plausible workflow, but it stays at an abstract, descriptive level — no executable commands, config examples, or validation steps — and fails to connect to its own bundle files, leaving it more of an overview than actionable guidance.

Suggestions

Add a concrete, copy-paste-ready example of the build-nn command and a sample configuration so Claude knows exactly what to execute.

Insert a validation/verification checkpoint after the build step (e.g., how to confirm the network was constructed correctly) to raise workflow clarity.

Reference the actual bundle files inline (e.g., link to scripts/build_network.py and assets/example_configurations/) so progressive disclosure is realized rather than implied.

Dimension	Reasoning	Score
Conciseness	The body is mostly organized but padded with conceptual restatement Claude already knows (the Overview and Best Practices re-explain layer types, regularization, and tuning) rather than adding new, specific guidance.	2 / 3
Actionability	Guidance is abstract — 'Generate the configuration for the build-nn command, specifying...' with no actual config example, command syntax, or executable code; it describes the process rather than instructing concretely.	1 / 3
Workflow Clarity	Steps are listed (analyze → generate config → execute build) but there are no validation checkpoints or error-recovery feedback loops, and the build operation has no verification step.	2 / 3
Progressive Disclosure	Sections are organized and bundle files exist (scripts/, assets/, references/) but the body never signals or links to them, so navigation to detailed materials is not realized despite the structure being present.	2 / 3
	Total	7 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 identifies a clear domain and a couple of concrete actions but is undermined by placeholder phrasing, a truncated 'assistance...' clause, and a non-explicit trigger ('Use when appropriate context detected') that reads as boilerplate rather than real trigger guidance.

Suggestions

Replace the truncated 'assistance...' and 'Use when appropriate context detected' with an explicit 'Use when...' clause naming concrete natural triggers (e.g., building, modifying, or designing a neural network architecture).

List the specific concrete actions (e.g., define layers, configure activation functions, set training parameters) instead of generic phrases like 'construct and configure'.

Remove the meta-instruction 'Trigger with relevant phrases based on skill purpose' — it describes the skill system, not what this skill does.

Dimension	Reasoning	Score
Specificity	Names the domain (neural networks) and some concrete actions ('construct and configure', 'creation', 'modification') but is not comprehensive — most capability detail is replaced by filler like 'assistance...' and 'Use when appropriate context detected'.	2 / 3
Completeness	It states what the skill does but the 'when' is only vaguely implied via 'Use when appropriate context detected' rather than an explicit 'Use when...' clause with concrete triggers, capping completeness at 2.	2 / 3
Trigger Term Quality	Includes some relevant phrases ('new neural network', 'modification of an existing one') but is padded with unnatural boilerplate ('Trigger with relevant phrases based on skill purpose') rather than the terms a user would naturally say.	2 / 3
Distinctiveness Conflict Risk	The neural-network-builder niche is fairly specific, yet the generic boilerplate ('assistance...', 'appropriate context detected') weakens distinctiveness and leaves room for overlap with general ML skills.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/ai-ml/neural-network-builder/skills/building-neural-networks/SKILL.md
Commit: 4c47e33

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.