agent-app-store
Agent skill for app-store - invoke with $agent-app-store
40
7%
Does it follow best practices?
Impact
97%
2.85xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-app-store/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It provides no information about what the skill does, when it should be used, or what domain it operates in. The only content is a generic label ('app-store') and an invocation command, which is insufficient for Claude to make informed skill selection decisions.
Suggestions
Add concrete actions describing what this skill does (e.g., 'Searches app store listings, retrieves app metadata, checks app availability and pricing').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks about finding apps, checking app reviews, app store listings, or mobile application information').
Specify which app store(s) this covers (iOS App Store, Google Play, etc.) to reduce ambiguity and conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for app-store' is entirely vague and does not describe what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an 'agent skill' and how to invoke it, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'app-store' which is ambiguous and not a natural phrase users would say when requesting a specific task. No natural trigger terms are present. | 1 / 3 |
Distinctiveness Conflict Risk | 'App-store' is vague and could refer to many things (iOS App Store, Google Play, internal app catalogs, etc.). There is no specificity to distinguish this from other potential skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with descriptive content about marketplace philosophy, categories, and features that don't provide actionable guidance. While the MCP tool call examples are a strength, the skill lacks concrete workflows for common tasks (e.g., how to publish an app end-to-end, how to handle failed deployments) and wastes significant token budget on lists Claude doesn't need memorized.
Suggestions
Remove the extensive category lists, quality standards bullets, and marketplace feature descriptions—these are reference material that either belong in a separate file or can be omitted since Claude can infer them.
Add concrete step-by-step workflows for key operations like 'publish an app' and 'deploy a template' with validation checkpoints (e.g., verify app exists after publishing, check deployment status).
Trim the role-playing preamble and responsibility lists to a 1-2 sentence purpose statement, focusing the body on executable tool usage patterns.
Split detailed reference content (categories, quality standards) into a separate REFERENCE.md file and link to it from a concise overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive lists of categories, quality standards, and marketplace features that Claude already understands conceptually. The role-playing preamble, bullet-point lists of responsibilities, and feature descriptions add significant token bloat without actionable value. | 1 / 3 |
Actionability | The JavaScript code examples for MCP tool calls are concrete and show actual function signatures with parameters, which is useful. However, much of the content is descriptive rather than instructive—listing categories, quality standards, and features without telling Claude exactly what to do in specific scenarios. | 2 / 3 |
Workflow Clarity | There are no clear multi-step workflows with sequencing or validation checkpoints. The numbered 'marketplace management approach' list describes abstract responsibilities, not actionable steps. Publishing, deploying, and managing apps are all potentially multi-step processes that lack defined sequences and error handling. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files or structured navigation. All categories, standards, and features are inlined despite being reference material that could be split out or omitted entirely. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/ruflo
- Commit
398f7c2
- Reviewed
Table of Contents
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.