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 is an extremely weak description that provides virtually no useful information for skill selection. It reads as a placeholder or auto-generated stub, containing only an invocation command and the skill's internal name. Claude would have no reliable basis for choosing this skill over any other.
Suggestions
Add a clear 'what' clause describing concrete actions, e.g., 'Generates mobile app specifications for React Native projects, including component architecture, navigation flows, and platform-specific requirements.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about React Native app specs, mobile app architecture, React Native project planning, or mobile UI specifications.'
Remove the invocation syntax from the description (it's metadata, not a capability description) and replace with domain-specific language that distinguishes this from general React Native coding skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It only names itself ('spec-mobile-react-native') and mentions invocation syntax, with no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command with no explanation of purpose or trigger conditions. | 1 / 3 |
Trigger Term Quality | The only potentially relevant terms are 'mobile' and 'react-native' embedded in the skill name, but these are not presented as natural trigger keywords. A user asking about React Native mobile development would not naturally use the phrase 'agent-spec-mobile-react-native'. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish it from any other mobile or React Native related skill. The word 'spec' is ambiguous—it could mean specification writing, testing, or something else entirely. | 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 non-functional YAML frontmatter (hooks, triggers, optimization settings) that have no effect in Claude Code, consuming significant token budget. The body content is generic and superficial—listing best practices Claude already knows without providing the specific, actionable guidance needed for complex React Native development tasks. It lacks structured workflows, validation steps, and progressive disclosure to supporting materials.
Suggestions
Remove or drastically reduce the YAML frontmatter to only fields Claude Code actually uses (name, description); the hooks, triggers, optimization, and integration sections are non-functional and waste tokens.
Replace the generic 'Best practices' bullet list with concrete, executable workflows—e.g., step-by-step instructions for setting up navigation with React Navigation, including specific commands and validation steps.
Add explicit multi-step workflows with validation checkpoints for complex tasks like native module integration (e.g., 1. Create bridge file → 2. Register module → 3. Verify with `npx react-native run-ios` → 4. If error, check linking).
Create separate reference files for platform-specific patterns (iOS.md, Android.md), navigation setup, and state management, with clear one-level-deep links from the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is bloated with an enormous YAML frontmatter that Claude cannot act on (triggers, hooks, optimization settings, integration configs are not real Claude Code features). 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 unique value. | 1 / 3 |
Actionability | The component pattern code example is executable and copy-paste ready, which is good. However, the 'Key responsibilities' and 'Best practices' sections are vague directives rather than concrete, actionable instructions. There are no specific commands for project setup, no concrete navigation implementation, and no real guidance on native module integration. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow defined. The 'Key responsibilities' are listed as a numbered list but lack sequencing, validation checkpoints, or any feedback loops. For a complex skill involving cross-platform development with native modules and platform-specific code, the absence of any structured workflow (e.g., create component → test on iOS → test on Android → validate) is a significant gap. | 1 / 3 |
Progressive Disclosure | The content is a monolithic file with no references to supporting documents. Platform-specific considerations, navigation patterns, state management, and native module integration are all topics that warrant separate detailed files but are instead given one-line bullet points. There is no bundle structure to support deeper exploration. | 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/claude-flow
- Commit
9d4a9ea
- 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.