agent-spec-mobile-react-native
Agent skill for spec-mobile-react-native - invoke with $agent-spec-mobile-react-native
40
7%
Does it follow best practices?
Impact
99%
1.16xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-spec-mobile-react-native/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 essentially a placeholder that provides no useful information for skill selection. It fails on every dimension: no concrete actions, no trigger terms, no 'what' or 'when' guidance, and no distinguishing characteristics. Claude would have no basis for selecting this skill over any other mobile or React Native related skill.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Generates mobile app specifications for React Native projects, defines component architecture, and creates screen navigation flows.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to create or review mobile app specifications, React Native project plans, or mobile UI/UX documentation.'
Include common keyword variations users might say, such as 'mobile app', 'React Native', 'RN', 'iOS', 'Android', 'app spec', 'mobile specification', '.tsx', 'cross-platform'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It only names itself and provides an invocation command, with no indication of what the skill actually does beyond a vague reference to 'spec-mobile-react-native'. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The only potentially useful keywords are 'mobile' and 'react-native' buried in the skill name, but these are not presented as natural trigger terms. No user-facing keywords like 'app', 'iOS', 'Android', 'specification', or 'mobile development' are included. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it could conflict with any React Native, mobile development, or specification-related skill. There are no distinct triggers or clear niche defined. | 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 an oversized YAML frontmatter full of fields that don't translate to actionable Claude behavior, while the actual body content is thin and generic. The best practices and responsibilities listed are things Claude already knows, and the single component example, while executable, is basic boilerplate. The skill lacks concrete workflows, validation steps, and any progressive disclosure structure.
Suggestions
Remove or drastically reduce the YAML frontmatter to only essential fields, and move the actual instructional content into the body with concrete, specific guidance (e.g., exact commands for setting up navigation, specific patterns for handling platform differences).
Add multi-step workflows with validation checkpoints for common tasks like 'creating a new screen', 'adding a native module', or 'setting up navigation', including explicit verification steps (e.g., 'run npx react-native run-ios to verify the screen renders correctly').
Replace generic best practices bullets with specific, actionable patterns - e.g., show the exact FlatList optimization pattern, the specific SafeAreaView usage for iOS, or the BackHandler pattern for Android.
Create separate reference files for platform-specific guides (iOS setup, Android setup, navigation patterns) and link to them from a concise overview in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is bloated with an enormous YAML frontmatter that includes many fields Claude doesn't use (hooks, triggers, optimization, communication style, etc.). The body itself lists generic best practices Claude already knows ('use functional components with hooks', 'test on both iOS and Android') and the component example is a basic boilerplate that adds little value. | 1 / 3 |
Actionability | The component pattern example is executable and copy-paste ready, which is good. However, the 'Key responsibilities' and 'Best practices' sections are vague bullet points ('Handle platform differences appropriately', 'Optimize images and assets') without concrete commands, specific techniques, or actionable guidance. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow defined. The skill lists responsibilities and best practices as unordered bullets without sequencing, validation checkpoints, or feedback loops. For a complex skill involving native modules, platform-specific code, and build processes, the absence of any workflow structure is a significant gap. | 1 / 3 |
Progressive Disclosure | The content is a monolithic file with no references to supporting documents. The massive YAML frontmatter dominates the file, and the body content mixes high-level responsibilities with inline code examples without any structured navigation or separation of concerns. No bundle files are provided or referenced. | 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
844f68d
- 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.