flow-nexus-neural

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

2.63x

Quality

57%

Does it follow best practices?

Impact

95%

2.63x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

65%

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

The body is highly actionable with concrete, executable MCP examples and responses, but it is an oversized inline API dump with redundant examples and no progressive disclosure via separate reference files. Workflow sequencing exists but omits validation checkpoints for risky batch operations.

Suggestions

Move the exhaustive API reference and architecture-pattern blocks into separate reference files (e.g. REFERENCE.md, ARCHITECTURES.md) and keep SKILL.md as a concise overview with one-level-deep links.

Deduplicate the LSTM and transformer examples that recur across the core, use-case, and architecture sections.

Add explicit validation/verification checkpoints to the distributed-training workflow (e.g. verify cluster status is healthy before deploying nodes, confirm training progress before scaling).

Dimension	Reasoning	Score
Conciseness	The ~720-line body is a mostly-efficient API reference of executable calls, but it carries notable redundancy (LSTM and transformer examples each recur across core, use-case, and architecture-pattern sections) and could be tightened without losing clarity.	2 / 3
Actionability	Provides fully executable MCP tool invocations with complete parameters, inline comments on valid option values, and example JSON responses — copy-paste ready guidance throughout.	3 / 3
Workflow Clarity	Multi-step distributed training is sequenced (init → deploy → connect → train → monitor → terminate), but destructive/batch cluster operations lack explicit validation checkpoints, capping this dimension at 2.	2 / 3
Progressive Disclosure	Content is well sectioned by headers, but it is monolithic — the full API reference, architecture patterns, and use cases are all inline in SKILL.md with no bundle files present to offload detail.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 product niche and a couple of concrete actions, but it omits any explicit "Use when" trigger guidance and relies on product jargon over natural user terms. It is competent but not exemplary on any dimension.

Suggestions

Add an explicit trigger clause, e.g. "Use when training, deploying, or running inference on neural networks, or when the user mentions distributed model training, E2B sandboxes, or Flow Nexus."

Broaden the action list beyond "train and deploy" to cover inference, template deployment, distributed clusters, and model publishing.

Swap some product jargon for natural user vocabulary (e.g. "deep learning", "model training", "predictions") to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("neural networks") and two concrete actions ("Train and deploy"), but the action list is not comprehensive — inference, templating, distributed clusters, and publishing are not mentioned.	2 / 3
Completeness	It states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some relevant terms a user might say ("neural networks", "distributed") but leans on product jargon ("E2B sandboxes", "Flow Nexus") and omits common variations like "deep learning", "model training", or "inference".	2 / 3
Distinctiveness Conflict Risk	The Flow Nexus / E2B sandbox framing gives it a distinct niche, but the missing trigger guidance means it could still overlap with generic ML training 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
skill_md_line_count	SKILL.md is long (757 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: ruvnet/ruvector
Path: .claude/skills/flow-nexus-neural/SKILL.md
Commit: 6a6c39e

Reviewed: about 14 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.