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

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/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 incomplete for skill selection purposes. While it names a specific domain (neural networks in E2B sandboxes with Flow Nexus), it doesn't list enough concrete actions or provide trigger guidance. The product-specific terminology may help with distinctiveness but hurts discoverability since users are unlikely to use those exact terms.

Suggestions

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

Expand the capability list with more specific actions, e.g., 'configure distributed training jobs, monitor training progress, deploy trained models to endpoints, manage sandbox environments'.

Include common user-facing synonyms and variations such as 'ML', 'machine learning', 'deep learning', 'model deployment', '.pt files', '.h5 files' to improve trigger term coverage.

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 verbs.	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, warranting a 1.	1 / 3
Trigger Term Quality	Includes relevant terms like 'neural networks', 'distributed', and 'deploy', but 'E2B sandboxes' and 'Flow Nexus' are product-specific jargon that users may not naturally say. 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 general ML/AI skills. The product-specific terms help but the core action is generic.	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 realistic examples covering the full API surface. However, it is extremely verbose and repetitive — architecture examples appear multiple times, common use cases largely duplicate earlier sections, and Claude already knows what LSTMs and transformers are best for. The monolithic structure with no bundle files means everything is crammed into one massive document with no progressive disclosure.

Suggestions

Reduce content by 60%+: remove the 'Architecture Patterns' section (duplicates earlier examples), collapse 'Common Use Cases' into brief references to the earlier examples, and eliminate 'Best for:' descriptions that Claude already knows.

Split into multiple files: keep SKILL.md as a concise overview with quick-start examples, and move detailed API examples to REFERENCE.md, architecture patterns to ARCHITECTURES.md, and distributed training to DISTRIBUTED.md.

Add explicit validation checkpoints to the distributed training workflow: verify cluster status is 'ready' before deploying nodes, confirm all nodes are 'active' before starting training, and include error recovery steps inline rather than in a separate troubleshooting section.

Remove all response JSON examples except one representative one — Claude can infer response structures from the tool definitions and doesn't need 8+ response examples.

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. Common use cases duplicate earlier examples. Response JSON examples add bulk without teaching Claude anything new. The 'Best for:' descriptions for each architecture are things Claude already knows.	1 / 3
Actionability	Every capability has concrete, executable MCP tool calls with full parameter objects and expected response JSON. The examples are copy-paste ready with realistic configurations, and cover the full lifecycle from training to inference to cluster management.	3 / 3
Workflow Clarity	The distributed training workflow (init cluster → deploy nodes → connect → train → monitor → terminate) is sequenced but lacks explicit validation checkpoints. There's no 'verify cluster is ready before training' step, no error handling between steps, and no feedback loops for failed node deployments. The troubleshooting section is separate rather than integrated into workflows.	2 / 3
Progressive Disclosure	Everything is in one monolithic file with no bundle files to offload content to. The architecture patterns, common use cases, and detailed API examples could all be in separate referenced files. The document is a wall of code examples that would benefit enormously from splitting into overview + detailed references.	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: ruvnet/ruflo
Commit: 844f68d

Reviewed: 4 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.