flow-nexus-platform

Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges

5.55x

Quality

50%

Does it follow best practices?

Impact

100%

5.55x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

46%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 — nearly every platform operation has a concrete, parameterized example — but it is a 1,155-line monolithic API dump with no bundle files, no validation checkpoints around destructive operations, and substantial padding (tier marketing, generic tips, version history). It needs to be split into per-domain reference files with the SKILL.md reduced to an overview plus quick start.

Suggestions

Split the ~70-tool call reference into one-level-deep reference files per domain (e.g. references/sandboxes.md, references/payments.md, references/challenges.md) and reduce SKILL.md to an overview, quick start, and clearly signaled pointers.

Add validation checkpoints to the Quick Start and destructive workflows: check auth_status after login, verify sandbox_status before sandbox_execute, and confirm sandbox_status/logs before sandbox_delete and storage_delete.

Cut padding that earns no tokens: subscription tier marketing copy, "Tips for Success" listicles, Version History, and generic best practices, plus drop tool-call signatures that duplicate schemas already exposed by the MCP tool definitions.

Dimension	Reasoning	Score
Conciseness	At ~1,155 lines the body inlines a full call reference for ~70 MCP tools whose schemas are already exposed via the tool definitions themselves, plus padded marketing (subscription tiers), generic tips ("Start Simple: Begin with beginner challenges to build confidence"), a Version History, and best-practices filler. Several padded sections and unnecessary reference material match anchor 2; it avoids anchor 1 only because most of the bulk is concrete reference rather than explanations of concepts Claude already knows.	2 / 5
Actionability	Nearly every operation ships a concrete, parameterized call (e.g. sandbox_create with template, env_vars, install_packages, timeout; a complete two-sum submission example). Minor gaps: undefined placeholders (sourceCodeString, databaseConfig, chunks) and undocumented return values keep it below anchor 5's copy-paste-ready bar.	4 / 5
Workflow Clarity	The Quick Start Guide sequences five steps (register → billing → sandbox → deploy → challenge), but validation checkpoints are absent — no auth_status check before proceeding, no sandbox_status before execution, and no verification before destructive calls (sandbox_delete, storage_delete). The missing-validation cap for destructive/batch operations holds this at anchor 3; it is not 4 because the gaps are pervasive rather than minor.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the entire API reference, tier pricing, and troubleshooting are inlined in one monolithic SKILL.md — content that clearly belongs in separate files. The <details> blocks and table of contents are partial mitigation, but this fits anchor 2 (content that belongs in separate files is inlined) more than anchor 3's "could be better organized".	2 / 5
	Total	11 / 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 has a clear "what" anchored by a distinctive brand name, but it consists of a noun list rather than concrete actions, includes the buzzword "Comprehensive", and entirely lacks a "when to use" trigger clause. Missing synonyms (credits, billing, storage, login) further limit its discoverability.

Suggestions

Add an explicit trigger clause, e.g. "Use when managing Flow Nexus accounts, creating or running cloud sandboxes, deploying apps from the template store, checking credit balances, or submitting coding challenges."

Replace the noun list with concrete actions and drop the buzzword, e.g. "Registers and authenticates Flow Nexus users, creates and executes code in cloud sandboxes, publishes and deploys apps, manages credits and payments, and submits challenge solutions."

Include natural synonyms users would say — login, credits/billing, storage, templates, leaderboards — so the description covers all major body sections, not just five.

Dimension	Reasoning	Score
Specificity	Names the domain ("Flow Nexus platform management") and enumerates five capability areas ("authentication, sandboxes, app deployment, payments, and challenges"), but these are bare capability nouns rather than concrete actions, and "Comprehensive" is buzzword padding. It lists several areas like anchor 4 but without the specific actions anchor 4 requires.	3 / 5
Completeness	The "what" is clear ("platform management - authentication, sandboxes, app deployment, payments, and challenges"), but there is no "Use when..." clause or equivalent explicit trigger guidance anywhere, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Terms like "authentication", "sandboxes", "app deployment", "payments", and "challenges" are plausibly user-spoken, but common variations and synonyms are missing ("login", "credits", "billing", "storage", "publish", "templates", "leaderboard"), and whole body sections have no keyword representation. Fits anchor 3 (some relevant keywords, missing variations) more than 4.	3 / 5
Distinctiveness Conflict Risk	"Flow Nexus" is a distinctive brand name, making false-trigger risk low; the capability list ("platform management - authentication... payments") is generic on its own, giving minor overlap risk with generic platform/billing skills. Best fits anchor 4; not 5 because the non-brand portion is broad.	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 (1176 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-platform/SKILL.md
Commit: 4b59352

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.