flow-nexus-neural

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

2.07x

Quality

37%

Does it follow best practices?

Impact

79%

2.07x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/flow-nexus-neural/SKILL.md

Quality

Content

42%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 skill is highly actionable with concrete, executable MCP tool call examples and clear response formats, which is its primary strength. However, it is extremely verbose and repetitive, with architecture examples duplicated across sections, and all content crammed into a single monolithic file with no progressive disclosure. Workflow clarity is adequate but lacks explicit validation checkpoints and error-recovery loops for multi-step distributed training operations.

Suggestions

Reduce content by 50-60%: eliminate the duplicated 'Architecture Patterns' section (already shown in examples), trim response JSON examples to one or two representative cases, and remove 'Best for' descriptions that Claude already knows.

Split into multiple files: move detailed API examples to a REFERENCE.md, architecture patterns to ARCHITECTURES.md, and common use cases to EXAMPLES.md, keeping SKILL.md as a concise overview with links.

Add explicit validation checkpoints to the distributed training workflow, e.g., 'Verify cluster status is ready before deploying nodes' and 'Check node health before starting training'.

Integrate error handling into workflows rather than relegating it to a separate troubleshooting section — e.g., after starting training, show a check-and-retry loop.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~500+ lines. Massive amounts of repetition — architecture patterns are shown in full examples AND repeated in the 'Architecture Patterns' section. Response JSON examples add bulk without teaching Claude anything new. The 'Common Use Cases' section largely duplicates earlier examples with minor variations. Claude doesn't need explanations like 'Best for: Classification, regression, simple pattern recognition'.	1 / 3
Actionability	The skill provides fully concrete, copy-paste-ready MCP tool calls with complete parameter structures and example responses. Every capability is demonstrated with executable code including specific parameter values, making it very clear exactly how to invoke each tool.	3 / 3
Workflow Clarity	The distributed training section shows a reasonable multi-step workflow (init cluster → deploy nodes → connect → train → monitor → terminate), but there are no explicit validation checkpoints or error-recovery feedback loops. The troubleshooting section is separate and reactive rather than integrated into the workflow. For destructive operations like cluster termination, there's no confirmation or validation step.	2 / 3
Progressive Disclosure	This is a monolithic wall of content with no bundle files to offload detail into. The architecture patterns, common use cases, and detailed API examples could all be split into separate reference files. Everything is inlined into a single massive document with no meaningful progressive disclosure structure — just flat sections one after another.	1 / 3
	Total	7 / 12 Passed

Description

32%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 is concise but underdeveloped. It names a specific domain and two actions but lacks a 'Use when...' clause, comprehensive capability listing, and natural trigger terms that users would commonly use. The product-specific terms (E2B, Flow Nexus) help with distinctiveness but hurt discoverability since users are unlikely to mention them.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about training ML models, deploying neural networks, distributed model training, or running deep learning workloads in sandboxes.'

Expand the capability list with specific actions beyond 'train and deploy', such as 'configure distributed training, monitor training runs, manage GPU resources, export trained models.'

Include natural user-facing trigger terms like 'machine learning', 'deep learning', 'ML model', 'model training', 'GPU training' alongside the product-specific terminology.

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 as product-specific terms, but 'train and deploy neural networks' is broad enough to overlap with other ML/AI-related skills.	2 / 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: ruvnet/claude-flow
Path: .agents/skills/flow-nexus-neural/SKILL.md
Commit: 913f9ea

Reviewed: 3 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.