ux-copy
Write or review UX copy — microcopy, error messages, empty states, CTAs. Trigger with "write copy for", "what should this button say?", "review this error message", or when naming a CTA, wording a confirmation dialog, filling an empty state, or writing onboarding text.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 a strong skill description that clearly defines its scope (UX copy writing and review), lists specific content types it handles, and provides rich, natural trigger terms that users would actually say. It uses proper third-person voice and effectively distinguishes itself from general copywriting or content skills by focusing on UI-specific copy types.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Write or review UX copy — microcopy, error messages, empty states, CTAs.' These are distinct, well-defined content types that clearly communicate what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (write or review UX copy including microcopy, error messages, empty states, CTAs) and 'when' (explicit trigger phrases and scenarios like naming a CTA, wording a confirmation dialog, etc.). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'write copy for', 'what should this button say?', 'review this error message', 'naming a CTA', 'wording a confirmation dialog', 'filling an empty state', 'writing onboarding text'. These are highly natural phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly occupies a distinct niche — UX copy and microcopy — with specific triggers like 'button say', 'error message', 'empty state', 'CTA', and 'confirmation dialog' that are unlikely to conflict with general writing or coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid UX copy skill with strong actionability through concrete examples and a well-structured output template. Its main weakness is including principles Claude already knows (clear, concise, human writing) and having some underdeveloped pattern sections (tooltips, loading states, onboarding) that add little value in their current form. The copy patterns for CTAs, errors, empty states, and confirmation dialogs are the strongest parts and provide genuinely useful, specific guidance.
Suggestions
Remove or significantly trim the 'Principles' section — Claude already knows these UX writing fundamentals; focus tokens on the specific patterns and examples that add unique value.
Flesh out the stub patterns (Tooltips, Loading States, Onboarding) with concrete examples like the other patterns, or remove them to save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some content Claude already knows well (UX writing principles like 'clear', 'concise', 'human' are basic knowledge). The 'What I Need From You' section and tips are useful but the principles section is largely unnecessary for Claude. | 2 / 3 |
Actionability | The copy patterns section provides concrete, specific examples for each UX copy type (CTAs, error messages, empty states, confirmation dialogs). The output template is fully structured with a clear markdown format including alternatives table and rationale sections, making it immediately usable. | 3 / 3 |
Workflow Clarity | For a single-task skill (writing/reviewing UX copy), the workflow is clear and unambiguous: gather context → apply patterns → produce structured output. The output template serves as an implicit checklist ensuring completeness (recommended copy, alternatives, rationale, localization notes). No destructive operations require validation loops. | 3 / 3 |
Progressive Disclosure | The skill has reasonable structure with clear sections, but some patterns (tooltips, loading states, onboarding) are stub-like with only a few words each — they should either be fleshed out inline or linked to a separate reference. The connector references are well-handled, but the content is somewhat monolithic for its length. | 2 / 3 |
Total | 10 / 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
- anthropics/knowledge-work-plugins
- Commit
f55b539
- 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.