Coding standards, component defaults, and best practices for the UCD Mobile app (Expo, React Native, NativeWind, Expo Router).
46
48%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/assistant-ucd-mobile/SKILL.mdQuality
Discovery
40%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 benefits from strong distinctiveness due to its project-specific naming and explicit tech stack, but it falls short on completeness by lacking any 'Use when...' guidance. The capabilities listed are high-level categories rather than concrete actions, and trigger terms could be expanded to cover more natural user language around mobile development tasks.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when working on the UCD Mobile app, writing React Native components, configuring navigation, or asking about coding conventions for this project.'
List more specific concrete actions, e.g., 'Defines component structure, enforces naming conventions, configures NativeWind styling patterns, and sets up Expo Router navigation defaults.'
Include additional natural trigger terms like 'mobile development', 'styling', 'navigation', 'components', 'code style', or 'app conventions' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (UCD Mobile app) and mentions high-level categories ('coding standards, component defaults, best practices') but does not list specific concrete actions like 'enforce naming conventions', 'configure NativeWind themes', or 'set up Expo Router navigation patterns'. | 2 / 3 |
Completeness | Describes 'what' at a high level (coding standards, component defaults, best practices) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also quite vague, warranting a score of 1. | 1 / 3 |
Trigger Term Quality | Includes relevant technology keywords (Expo, React Native, NativeWind, Expo Router) and the app name (UCD Mobile), which users might naturally mention. However, it lacks common variation terms like 'styling', 'navigation', 'mobile development', 'components', or 'code style'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to a specific app ('UCD Mobile app') with a specific tech stack (Expo, React Native, NativeWind, Expo Router), making it highly unlikely to conflict with other skills. The project-specific naming creates a clear niche. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured coding standards reference with excellent executable examples covering the full stack. Its main weakness is its monolithic size — at ~500 lines with no bundle files, it consumes significant context window space and would benefit greatly from splitting detailed reference material (error codes, result containers, platform defaults) into separate files. The content is mostly efficient but includes some explanations of patterns Claude already understands.
Suggestions
Extract the error code → UI behavior table, result container class definitions, and platform defaults into separate reference files (e.g., ERROR_CODES.md, RESULT_TYPES.md, PLATFORM_DEFAULTS.md) and link to them from the main skill.
Add a brief 'Adding a new feature' workflow section with numbered steps and validation checkpoints (e.g., 1. Create service function → 2. Add hook → 3. Build screen → 4. Verify TypeScript strict compliance → 5. Test accessibility).
Trim explanations of standard patterns Claude already knows (e.g., what React Context is, what Platform.select does) and focus only on project-specific deviations from standard practice.
Consider splitting into a concise SKILL.md overview (~100 lines) with quick-reference tables and links to detailed topic files for styling, data layer, accessibility, and navigation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive and mostly efficient, but some sections explain things Claude already knows (e.g., what Platform.select does, basic React Context patterns, what accessibility roles are). The error code table and full result container class definitions are quite lengthy and could be extracted to a reference file. However, most content is project-specific and earns its place. | 2 / 3 |
Actionability | Nearly every section includes fully executable, copy-paste-ready code examples with correct imports and realistic usage patterns. The component template, data fetching hook, context pattern, bottom sheet setup, and layered error handling all provide concrete, complete code that Claude can directly apply. | 3 / 3 |
Workflow Clarity | The skill is primarily a reference/standards document rather than a multi-step workflow, so explicit sequencing is less critical. However, the data propagation section (Section 17) describes a multi-layer flow (DB → Service → API → UI) with clear layer responsibilities and conversion rules, which serves as an implicit workflow. It lacks explicit validation checkpoints or feedback loops for common development tasks like adding a new feature or screen. | 2 / 3 |
Progressive Disclosure | This is a monolithic ~500-line document with no references to supporting files (except one mention of an accessibility skill). The error code table, full result container class definitions, platform defaults table, and detailed data propagation examples could all be extracted to separate reference files. The single-file approach makes this a wall of text that competes heavily for context window space. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (737 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
c0b2e4b
Table of Contents
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.