flow-nexus-platform

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

2.04x

Quality

53%

Does it follow best practices?

Impact

94%

2.04x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

57%

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 — almost entirely concrete, copy-paste-ready MCP tool calls — but it is an over-long monolithic reference padded with a redundant Quick Start and promotional/reference material, and its multi-step workflows lack the validation checkpoints the rubric requires for destructive and batch operations.

Suggestions

Split the ~1158-line monolith into one-level-deep reference files (e.g. authentication.md, sandboxes.md, payments.md) with a concise SKILL.md overview linking to them, replacing the inline <details> pseudo-disclosure with real file-based progressive disclosure.

Remove the redundant 'Quick Start Guide' (it duplicates five earlier sections) and trim promotional content (subscription tiers, credit pricing, 'Tips for Success', 'Ways to Earn', Seraphina marketing) to what Claude needs to act.

Add explicit validation/feedback checkpoints to risky workflows — e.g. check sandbox_status/logs after execute, verify storage_get_url after upload, and confirm before sandbox_delete/storage_delete — so workflow clarity can reach 3.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows (no 'what is a sandbox' tutorials), so it is above score 1, but at ~1158 lines it is heavily padded: the 'Quick Start Guide' repeats tool calls already shown (user_register, sandbox_create, template_deploy, challenge_submit), and subscription tiers, credit pricing, 'Tips for Success', 'Ways to Earn', and Queen Seraphina marketing prose are reference/promotional content that does not earn its tokens.	1.5 / 3
Actionability	Nearly every section is a concrete, copy-paste-ready MCP tool invocation with full parameter objects (e.g. mcp__flow-nexus__sandbox_create with template, env_vars, install_packages), matching the score-3 anchor 'Fully executable code/commands; specific examples; copy-paste ready'; placeholder values like 'sandbox_id' are normal and acceptable.	3 / 3
Workflow Clarity	The 'Quick Start Guide' provides a clear 5-step sequence (register -> billing -> sandbox -> deploy -> challenge), but there are no validation checkpoints or feedback loops for destructive/batch operations like sandbox_delete, storage_delete, or chunked uploads; per the rubric this caps workflow clarity at 2 rather than 3.	2 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the skill is a monolithic ~1158-line file with a TOC and section headers plus inline <details> tags, but ~1000+ lines of API reference that should be split into separate files (AUTH.md, SANDBOXES.md, PAYMENTS.md) remain inline, matching the score-2 anchor of content that should be separate being inline; it is not score 1 because organization is decent and references are not deeply nested.	2 / 3
	Total	8.5 / 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 names the domain and several capability areas but uses category-nouns rather than concrete actions and lacks any explicit 'Use when...' trigger clause, capping completeness and trigger quality at 2. It is distinctive via the product name but generic feature terms create moderate conflict risk.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers, e.g. 'Use when the user asks to manage Flow Nexus sandboxes, deploy apps, handle credits/payments, or submit coding challenges.'

Convert capability categories into concrete verb-actions (e.g. 'create and run code sandboxes, deploy templates, manage credit balances, submit challenge solutions') to lift specificity from 2 to 3.

Lead with the distinctive Flow Nexus trigger terms and drop the marketing word 'Comprehensive' to reduce conflict risk and improve naturalness.

Dimension	Reasoning	Score
Specificity	Quotes 'Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges' name the domain and five sub-capability areas, but these are noun-categories rather than concrete verb-actions like the score-3 anchor ('Extract text and tables...'). It is above score 1 because it names a specific domain and multiple sub-areas rather than being vague.	2 / 3
Completeness	It clearly states what the skill does (platform management across five areas) but provides no 'when should Claude use it' trigger guidance; per the rubric, a missing 'Use when...' clause caps completeness at 2, so it is not score 3 despite a clear 'what'.	2 / 3
Trigger Term Quality	The product name 'Flow Nexus' plus feature terms 'sandboxes', 'app deployment', 'payments', 'challenges' are relevant keywords a user might say, but the framing ('Comprehensive...management') is marketing-style with no natural 'Use when...' trigger phrasing or common variations, matching the score-2 anchor 'Some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The 'Flow Nexus' qualifier gives it a recognizable niche, but generic capability terms ('authentication', 'payments', 'deployment') could overlap with other platform skills and, with no explicit trigger guidance, it might fire for the wrong skill — matching 'Somewhat specific but could still overlap'.	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 (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	14 / 16 Passed

Repository: ruvnet/claude-flow
Path: .agents/skills/flow-nexus-platform/SKILL.md
Commit: 26c35b5

Reviewed: about 4 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.