ux-architect
Technical architecture and UX specialist who provides developers with solid foundations, CSS systems, and clear implementation guidance
25
7%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./design-ux-architect/skills/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 reads more like a vague job title or persona description than a skill description. It lacks concrete actions, natural trigger terms, explicit 'when to use' guidance, and any distinguishing specificity. The use of 'who provides' frames it as a persona rather than describing capabilities, and terms like 'solid foundations' are meaningless fluff.
Suggestions
Replace vague language with specific concrete actions, e.g., 'Creates CSS design systems, builds responsive layouts, implements component architectures, and writes accessible HTML/CSS structures.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about CSS architecture, design systems, responsive layouts, component styling, or frontend structure.'
Narrow the scope to a clear niche to reduce conflict risk — specify whether this is about CSS architecture specifically, design systems, UI component libraries, or something else distinct from general frontend development.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'solid foundations', 'CSS systems', and 'clear implementation guidance' without listing any concrete actions. No specific tasks like 'creates layouts', 'builds component libraries', or 'writes responsive CSS' are mentioned. | 1 / 3 |
Completeness | The 'what' is extremely vague ('provides developers with solid foundations') and there is no 'when' clause at all. There are no explicit triggers or conditions for when this skill should be selected. | 1 / 3 |
Trigger Term Quality | The only natural keyword is 'CSS', which is too broad. Terms like 'technical architecture', 'UX specialist', and 'implementation guidance' are abstract buzzwords rather than terms a user would naturally use when requesting help. Missing terms like 'responsive design', 'layout', 'styling', 'HTML', 'components', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic that it could overlap with virtually any frontend development, web design, or CSS-related skill. 'Technical architecture and UX specialist' is broad enough to conflict with many other 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 reads more like an agent persona definition document than an actionable skill file. It is extremely verbose, spending significant tokens on identity, personality, success metrics, communication style, and learning sections that provide no actionable value to Claude. The concrete code examples are undermined by placeholder values and the lack of any validation workflow or progressive disclosure structure.
Suggestions
Remove all persona/identity/personality/memory/success-metrics/communication-style sections — these waste tokens on things Claude doesn't need to be told about itself
Extract the CSS design system template, ThemeManager JS, and HTML template into separate reference files (e.g., DESIGN-SYSTEM.md, THEME-TOGGLE.md) and link to them from a concise overview
Replace placeholder values like [spec-light-bg] with either real default values or a clear instruction to read from a specific config file, making examples executable
Add explicit validation checkpoints to the workflow (e.g., 'Validate CSS variables render correctly in browser before proceeding to layout components')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Extensive sections on identity, personality, memory, success metrics, communication style, and learning are things Claude doesn't need explained. The CSS example uses placeholder values like [spec-light-bg] making it neither executable nor efficient. Massive amounts of content that describe what the agent 'is' rather than what to do. | 1 / 3 |
Actionability | Contains some concrete code examples (CSS design system, ThemeManager JS class, HTML template) that are partially executable, but most CSS uses placeholder values rather than real ones. The workflow steps mix vague instructions ('Design CSS variable system') with some concrete bash commands. Much of the content describes deliverable templates with blanks rather than providing truly copy-paste-ready guidance. | 2 / 3 |
Workflow Clarity | The 4-step workflow process is high-level and lacks validation checkpoints. Steps like 'Create Technical Foundation' and 'UX Structure Planning' are abstract descriptions without verification gates. No feedback loops for error recovery. The priority order in the deliverable template is a list without validation steps between phases. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inline. The CSS design system, JavaScript, HTML templates, layout specs, UX structure, deliverable templates, and workflow are all crammed into one massive file. Only one reference to an external file ('ai/agents/architect.md') at the very end. Content that should clearly be in separate reference files (CSS examples, JS theme manager, deliverable templates) is all inline. | 1 / 3 |
Total | 5 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- OpenRoster-ai/awesome-openroster
- Commit
09aef5d
- 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.