agent-app-store

Agent skill for app-store - invoke with $agent-app-store

2.85x

Quality

28%

Does it follow best practices?

Impact

97%

2.85x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-app-store/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a competent agent-role definition with a practical MCP toolkit, but it leans on strategic prose Claude already understands and offers no operational workflow with validation, nor any file-based progressive disclosure. It lands squarely at the mid-level across all dimensions.

Suggestions

Trim concept-explaining prose (ecosystem/community/monetization narrative) to keep only the toolkit and task-specific guidance, improving token efficiency.

Replace placeholder parameters (app_id: "app_id", source_code: sourceCode) with concrete, complete examples so the code is copy-paste ready.

Add an operational workflow with validation checkpoints for publish and deploy operations, and move the long category/feature lists into a reference file for clearer progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body provides a useful code toolkit but surrounds it with prose describing marketplace/developer-ecosystem concepts Claude already knows (e.g. "foster a vibrant ecosystem", "thriving developer ecosystem"), so it is mostly efficient yet padded, matching the score-2 anchor.	2 / 3
Actionability	Concrete MCP tool calls with realistic parameters are provided, but placeholders like app_id: "app_id" and source_code: sourceCode are not fully complete or copy-paste ready, fitting the score-2 anchor of some concrete but incomplete guidance.	2 / 3
Workflow Clarity	The numbered "marketplace management approach" is strategic rather than an operational sequence, and publishing/deploying operations lack validation checkpoints; per the rubric, missing validation in destructive/batch operations caps this at 2.	2 / 3
Progressive Disclosure	Content is organized into labeled sections (giving some structure) but is monolithic with no bundle files or external references, and inline material such as the long category list and toolkit could be split out, matching the score-2 anchor.	2 / 3
	Total	8 / 12 Passed

Description

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 a bare domain label plus an invocation hint, with no concrete capabilities and no natural use-trigger guidance, placing it near the bottom of the rubric. It is only mildly rescued by naming a specific marketplace niche.

Suggestions

Replace the placeholder with concrete actions, e.g. "Publish, search, deploy, and analyze apps and templates in the Flow Nexus marketplace."

Add an explicit "Use when..." trigger clause listing natural terms users would say, such as app store, marketplace, publish an app, or deploy a template.

Drop the technical "$agent-app-store" invocation syntax in favor of user-facing trigger language to improve trigger term quality.

Dimension	Reasoning	Score
Specificity	The description "Agent skill for app-store - invoke with $agent-app-store" names only a domain and offers no concrete actions, matching the score-1 anchor for vague/abstract language rather than score 2 which requires naming some actions.	1 / 3
Completeness	It does not state what the skill concretely does beyond a domain label and lacks any "Use when..." trigger guidance, leaving both what and when weak or missing per the score-1 anchor.	1 / 3
Trigger Term Quality	The phrase "invoke with $agent-app-store" is a technical invocation mechanism rather than natural keywords a user would say, and no common variations are present, so it matches the score-1 anchor.	1 / 3
Distinctiveness Conflict Risk	"app-store" names a somewhat specific niche, but the surrounding wording is generic enough that it could still overlap with related skills, fitting the score-2 anchor better than the fully generic score 1.	2 / 3
	Total	5 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/agent-app-store/SKILL.md
Commit: 26c35b5

Reviewed: about 5 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.