flow-nexus-neural

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

7.38x

Quality

51%

Does it follow best practices?

Impact

96%

7.38x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./ai-ml/flow-nexus-neural-mattnigh-skills-collection/SKILL.md

Quality

Content

50%Weight 40%Scale 1-5

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 a clear section structure, but it is held back by significant content repetition, a monolithic structure with no bundled references, and missing validation checkpoints in the distributed-training workflow. It is a useful but over-padded reference document.

Suggestions

Remove redundant architecture examples: the 'Architecture Patterns' section and parts of 'Common Use Cases' re-show feedforward/LSTM/transformer code already present in 'Core Capabilities' — keep one canonical set and cross-reference it.

Move the full per-endpoint JSON response payloads (or the bulk API reference) into a bundled reference file (e.g. references/api.md) and keep SKILL.md to quick-start examples plus links, trimming inline response blocks to key fields.

Add explicit validation checkpoints to the distributed-training workflow (e.g. verify cluster_status shows nodes 'active' before starting training; poll training_status and retry/terminate on stall) to lift workflow clarity above the batch-operation cap of 3.

Dimension	Reasoning	Score
Conciseness	The ~740-line body noticeably repeats material: feedforward/LSTM/transformer architecture examples appear in 'Core Capabilities', again in 'Common Use Cases', and again in 'Architecture Patterns', and every endpoint ships a full JSON response block — 'several unnecessary padded sections' rather than 'some' tightening.	2 / 5
Actionability	Concrete, copy-paste-ready MCP tool calls with full config objects cover the common cases (train, predict, templates, distributed clusters), but the GAN example leaves generator/discriminator layers as '[...]' placeholders, a minor gap that keeps it just below fully executable.	4 / 5
Workflow Clarity	The distributed-training flow is sequenced (init → deploy nodes → connect → train → monitor → terminate), but it lacks explicit validation checkpoints for a batch/heavy operation, so per the rubric cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Section headers are well organized, but the entire API reference (tool calls plus response payloads) is inlined in a single 740-line SKILL.md with no bundled reference files, fitting 'some structure but content that should be separate is inline' rather than well-split score-4 organization.	3 / 5
	Total	12 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 clear and reasonably specific about what the skill does but lacks any explicit 'when to use it' trigger guidance, which caps completeness. Trigger-term coverage is adequate but misses common ML synonyms. It is a competent but incomplete description rather than an exemplary one.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks to train, deploy, or run inference on neural networks, or mentions distributed/federated training, E2B sandboxes, or the Flow Nexus marketplace'.

Include natural synonyms users actually say — 'machine learning models', 'deep learning', 'model training and inference' — alongside 'neural networks' to broaden trigger-term coverage.

List a couple more concrete actions (run inference, browse/deploy marketplace templates, manage distributed clusters) so the capability set reads as comprehensive rather than two-action.

Dimension	Reasoning	Score
Specificity	Names the domain ('neural networks') and two concrete actions ('Train and deploy') but omits other capabilities the body covers (inference, templates, marketplace, distributed clusters), matching the '1-2 concrete actions, not comprehensive' anchor rather than the broader score-4 list.	3 / 5
Completeness	It gives a clear 'what' ('Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus') but has no 'Use when...' clause or equivalent trigger guidance, so per the rubric guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	'Train and deploy neural networks' are natural phrases, but common synonyms users say ('machine learning models', 'deep learning', 'model training') are missing, fitting 'some relevant keywords but missing common variations or synonyms' rather than the comprehensive score-4 coverage.	3 / 5
Distinctiveness Conflict Risk	The Flow Nexus product name plus neural-network/distributed-training specifics carve a fairly distinct niche, with only minor overlap risk against sibling skills (flow-nexus-sandbox, flow-nexus-swarm), matching 'mostly distinct; minor overlap risk'.	4 / 5
	Total	13 / 20 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 (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	14 / 16 Passed

Repository: majiayu000/claude-skill-registry-data
Path: ai-ml/flow-nexus-neural-mattnigh-skills-collection/SKILL.md
Commit: a1e9f44

Reviewed: about 19 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.