flow-nexus-neural

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

7.38x

Quality

37%

Does it follow best practices?

Impact

96%

7.38x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ai-ml/flow-nexus-neural/SKILL.md

Quality

Discovery

32%

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 too terse and lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill over others. While it names a specific domain and two actions, it relies on product-specific jargon (E2B, Flow Nexus) without explaining what those are or providing natural trigger terms users would actually say. The description needs both more concrete capability details and explicit trigger guidance.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'train model', 'deep learning', 'machine learning', 'deploy ML model', 'distributed training', 'GPU training'.

Expand the capability list with specific actions beyond 'train and deploy', such as 'configure distributed training jobs, monitor training progress, manage model checkpoints, scale across sandbox instances'.

Briefly clarify what 'E2B sandboxes' and 'Flow Nexus' are so Claude can match user requests that don't use those exact product names.

Dimension	Reasoning	Score
Specificity	Names the domain (neural networks, distributed sandboxes) and two actions (train and deploy), but lacks comprehensive detail about specific capabilities beyond those two high-level actions.	2 / 3
Completeness	Describes what it does (train and deploy neural networks) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also thin, so this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant keywords like 'neural networks', 'train', 'deploy', and 'distributed', but 'E2B sandboxes' and 'Flow Nexus' are product-specific jargon that users may not naturally use. Missing common variations like 'deep learning', 'model training', 'ML', 'machine learning'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'E2B sandboxes' and 'Flow Nexus' adds some distinctiveness, but 'train and deploy neural networks' is broad enough to overlap with other ML/AI-related skills. The product-specific terms help somewhat but aren't sufficient to clearly carve out a unique niche.	2 / 3
	Total	7 / 12 Passed

Implementation

42%

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

The skill is highly actionable with concrete, executable MCP tool calls and detailed response examples, which is its primary strength. However, it is excessively verbose with significant redundancy (architecture patterns shown multiple times, use cases duplicating earlier examples), and everything is crammed into a single monolithic file rather than being split into an overview with references to detailed sub-documents. Workflow clarity is adequate but lacks explicit validation checkpoints for distributed operations.

Suggestions

Reduce content by 60-70%: keep a concise overview with one example per capability in SKILL.md, and move detailed architecture patterns, common use cases, and full API response examples into separate reference files (e.g., ARCHITECTURES.md, EXAMPLES.md, API-REFERENCE.md).

Remove duplicated architecture definitions — they appear in the training examples, the 'Architecture Patterns' section, and again in 'Common Use Cases'.

Add explicit validation checkpoints to the distributed training workflow (e.g., verify cluster status is 'ready' before deploying nodes, confirm all nodes are 'active' before starting training, validate training metrics before proceeding to inference).

Cut the example JSON responses to only the most essential ones — Claude can infer response shapes from one or two examples rather than needing them for every single endpoint.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~500+ lines. Massive amounts of repetition — architecture patterns are shown in examples AND repeated in a dedicated section. Response JSON examples pad the content significantly. The 'Common Use Cases' section largely duplicates earlier examples with minor variations. Claude doesn't need this level of redundancy.	1 / 3
Actionability	Every capability includes concrete, copy-paste-ready MCP tool calls with full parameter objects and example responses. The code is specific and executable with real function signatures, parameters, and expected JSON outputs.	3 / 3
Workflow Clarity	The distributed training section has a reasonable sequence (init → deploy nodes → connect → train → monitor → terminate), but there are no explicit validation checkpoints or error-recovery feedback loops between steps. The troubleshooting section is separate and reactive rather than integrated into workflows. For operations involving distributed cluster management, missing validation gates caps this at 2.	2 / 3
Progressive Disclosure	This is a monolithic wall of text with everything inlined. The architecture patterns, common use cases, and detailed API examples could all be split into separate reference files. The 'Related Skills' and 'Resources' sections at the bottom hint at external references but the body itself contains far too much detail for a SKILL.md overview.	1 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (739 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: majiayu000/claude-skill-registry
Commit: d156cd1

Reviewed: about 2 hours 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.