flow-nexus-platform

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

2.04x

Quality

41%

Does it follow best practices?

Impact

94%

2.04x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/flow-nexus-platform/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 identifies a specific platform (Flow Nexus) and lists broad capability areas, which provides some distinctiveness and domain context. However, it lacks concrete action verbs describing what operations are performed, omits a 'Use when...' clause entirely, and uses category labels rather than specific capabilities. The description reads more like a feature list heading than actionable skill selection guidance.

Suggestions

Add a 'Use when...' clause specifying explicit triggers, e.g., 'Use when the user asks about Flow Nexus, managing sandboxes, deploying apps to Flow Nexus, or handling Flow Nexus payments and challenges.'

Replace category labels with concrete actions, e.g., 'Authenticates users, creates and manages sandboxes, deploys applications, processes payments, and configures challenges on the Flow Nexus platform.'

Include natural keyword variations users might say, such as 'login', 'deploy', 'billing', 'sandbox environment', or the platform's common abbreviations.

Dimension	Reasoning	Score
Specificity	The description names a specific domain ('Flow Nexus platform') and lists several action areas (authentication, sandboxes, app deployment, payments, challenges), but these are categories rather than concrete actions. It doesn't describe what specific operations are performed (e.g., 'create sandboxes', 'deploy apps', 'process payments').	2 / 3
Completeness	The description answers 'what' at a high level (platform management across several areas) but completely lacks any 'when' guidance — there is no 'Use when...' clause or equivalent explicit trigger guidance. Per the rubric, a missing 'Use when...' clause should cap completeness at 2, and since the 'what' is also only partially specified, a score of 1 is appropriate.	1 / 3
Trigger Term Quality	It includes some relevant keywords like 'authentication', 'sandboxes', 'app deployment', 'payments', and 'challenges', which users might mention. However, 'Flow Nexus' is a specific platform name that helps, but common variations or alternative phrasings are missing (e.g., 'login', 'deploy', 'billing').	2 / 3
Distinctiveness Conflict Risk	The mention of 'Flow Nexus platform' provides some distinctiveness since it's a specific platform name. However, broad terms like 'authentication', 'payments', and 'app deployment' could overlap with other skills that handle those domains in different contexts.	2 / 3
	Total	7 / 12 Passed

Implementation

50%

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 for every operation, which is its primary strength. However, it is severely bloated—a monolithic document that tries to be both a reference manual and a skill guide, including pricing tables, tips lists, category enumerations, and troubleshooting sections that don't belong in a single SKILL.md. The lack of validation checkpoints in workflows and the absence of bundle files to offload detailed content significantly weaken its effectiveness.

Suggestions

Split this into multiple files (e.g., AUTH.md, SANDBOX.md, PAYMENTS.md, CHALLENGES.md, STORAGE.md) and make SKILL.md a concise overview with links to each, dramatically reducing token usage.

Remove informational content Claude doesn't need (subscription tier details, pricing tables, achievement type descriptions, tips for success, category lists) or move them to a separate REFERENCE.md.

Add explicit validation checkpoints to workflows—e.g., after sandbox_create check sandbox_status before executing code; after challenge_submit verify the response before marking complete.

Remove the troubleshooting section and support/resources links, which are user-facing documentation rather than actionable skill instructions for Claude.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~700+ lines. Massive amounts of content that could be split into separate files. Includes extensive lists of tips, best practices, categories, pricing tiers, achievement types, and troubleshooting that are informational rather than instructional. Much content (e.g., explaining what subscription tiers include, cost optimization tips, challenge tips for success) doesn't teach Claude how to do anything new.	1 / 3
Actionability	Every API call is shown with concrete, executable MCP tool invocations including realistic parameters. The code examples are copy-paste ready with clear parameter names and values, covering the full range of platform operations.	3 / 3
Workflow Clarity	The Quick Start Guide provides a sequential 5-step workflow, but lacks validation checkpoints. There's no guidance on checking if sandbox creation succeeded before executing code, no error handling between steps, and no feedback loops for destructive operations like sandbox deletion or file deletion.	2 / 3
Progressive Disclosure	Uses HTML details/summary tags for advanced patterns at the bottom, which is a good technique. However, the main body is a monolithic wall of content (~700 lines) that should be split into separate files (e.g., sandbox management, payments, challenges). No bundle files exist to offload content to, and the inline content is far too long for a single SKILL.md.	2 / 3
	Total	8 / 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 (1158 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
Commit: 9d4a9ea

Reviewed: 6 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.