flow-nexus-platform

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

2.04x

Quality

50%

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

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's strength is comprehensive, concrete, parameter-complete tool-call documentation across every platform domain, organized with a useful table of contents and a five-step quick start. It is undermined by monolithic length with no external reference files, generic best-practices padding, pervasive slash-character corruption that breaks path/URL examples, and the absence of validation checkpoints around destructive operations.

Suggestions

Split the per-domain API references (authentication, sandboxes, app store, payments, challenges, storage) into separate reference files and keep SKILL.md as a concise overview with clearly signaled links, which would also fix the broken <details> progressive-disclosure section.

Fix the systematic character corruption where "$" replaces "/" in file paths and URLs (e.g., "$app$config$database.json", "https:/$api.example.com$data") so examples are actually executable.

Delete the generic knowledge sections ("Publishing Best Practices", "Tips for Success", "Best Practices", subscription marketing copy) and add explicit validation/confirmation steps before destructive operations like sandbox_delete and storage_delete.

Dimension	Reasoning	Score
Conciseness	At ~1150 lines the body is heavily padded with material Claude already knows: "Use semantic versioning (MAJOR.MINOR.PATCH)", "Never hardcode API keys - use environment variables", "Start Simple: Begin with beginner challenges to build confidence", plus marketing-style subscription-tier and revenue-sharing copy. This is noticeably verbose bordering on the severely padded anchor 1, but the bulk is at least concrete tool documentation rather than tutorial prose.	2 / 5
Actionability	Nearly every tool is documented with a concrete, fully-parameterized call covering the common cases, which alone would merit a 4-5. However, pervasive character corruption — "$app$config$database.json" instead of "$app/config/database.json", "https:/$api.example.com$data", "postgres:/$user:pass@host:5432$db" — renders a large share of path and URL examples non-executable as written, which exceeds the "minor gaps" of anchor 4.	3 / 5
Workflow Clarity	The Quick Start Guide provides a coherent five-step sequence (register, configure billing, create sandbox, deploy app, complete challenge), but workflows involving destructive and batch operations (sandbox_delete, storage_delete, chunked uploads) include no validation or verification steps, which per the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	The skill is a monolithic ~1150-line API dump with no bundle files (no references/, scripts/, or assets/ exist); the per-domain API references clearly belong in separate files. The one nod to disclosure — a "Progressive Disclosure" section using <details> blocks — contains corrupted closing tags ("<$summary>", "<$details>") and would not render, so the structure is effectively inlined-only, matching anchor 2.	2 / 5
	Total	10 / 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 communicates a distinct platform niche with a clear capability list, but it reads as a feature inventory rather than usage guidance: the only verb is generic ("management"), there is no "when to use" trigger clause, and "Comprehensive" is filler. It is serviceable but below the quality of the good examples, which pair concrete actions with explicit trigger phrases.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user mentions Flow Nexus, rUv credits, sandbox execution, or deploying apps to the Flow Nexus platform."

Replace the generic "management" with concrete actions, e.g., "Create and execute code in cloud sandboxes, deploy apps from the template store, purchase and monitor credits, and submit coding challenge solutions."

Trim the filler word "Comprehensive" and surface omitted capability areas (storage, real-time subscriptions, credit billing) so the trigger terms cover what the skill actually does.

Dimension	Reasoning	Score
Specificity	The description enumerates five concrete capability areas ("authentication, sandboxes, app deployment, payments, and challenges") but the only action verb is the generic "management", and "Comprehensive" is padding. It names the domain and functional areas without concrete operations, landing between anchor 2 (generic actions) and anchor 3 (1-2 concrete actions).	3 / 5
Completeness	The "what" is reasonably clear (platform management across five areas), but there is no "Use when..." clause or any equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like "authentication", "sandboxes", "app deployment", "payments", and "challenges" are natural phrases a user might say, but common variations and synonyms are missing (e.g., "credits", "billing", "storage", "deploy"), matching anchor 3 rather than the fuller coverage of anchor 4.	3 / 5
Distinctiveness Conflict Risk	Naming the specific proprietary platform ("Flow Nexus") establishes a clear niche with minimal conflict risk against unrelated skills. It is not a 5 because generic terms like "authentication" and "payments" could overlap with other platform/account-management skills.	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 (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/ruflo
Path: .agents/skills/flow-nexus-platform/SKILL.md
Commit: b14c79e

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.