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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and highly actionable, with concrete copy patterns, examples, and a clear output template that make the single-task workflow unambiguous. Its main weakness is mild redundancy and generic writing advice in the Principles and Tips sections that a competent model already knows.

Suggestions

Trim the 'Principles' section (Clear/Concise/Consistent/Useful/Human) to only non-obvious guidance, since these are writing fundamentals Claude already applies.

Remove or merge the 'Tips' section, which restates 'What I Need From You' and 'Voice and Tone' rather than adding new information.

Fix the malformed markdown in 'If Connectors Available' (the '~~knowledge base**' and '~~design tool**' mix strikethrough and bold) so the connector conditions render correctly.

Dimension	Reasoning	Score
Conciseness	The copy patterns, output template, and voice/tone sections are lean and useful, but the 'Principles' section states generic writing wisdom Claude already knows and 'Tips' partly duplicates 'What I Need From You' and 'Voice and Tone', so it could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance — named structures ('What happened + Why + How to fix') with specific examples ('Payment declined. Your card was declined by your bank...', 'Delete 3 files?' not 'Are you sure?') and a fill-in output scaffold.	3 / 3
Workflow Clarity	As a single-purpose skill the flow is unambiguous — gather context, apply the copy patterns, and produce the templated output — and no destructive or batch operations require validation checkpoints.	3 / 3
Progressive Disclosure	No bundle files exist, so the self-contained body is scored on organization; it is split into clear, well-labeled sections with only a one-level pointer to CONNECTORS.md and no nested references.	3 / 3
	Total	11 / 12 Passed

Description

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.

The description is specific, trigger-rich, and complete, naming concrete copy tasks alongside natural user phrases and an explicit 'Trigger with' clause. It uses the imperative voice consistent with the strong reference examples and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'microcopy, error messages, empty states, CTAs' and 'naming a CTA, wording a confirmation dialog, filling an empty state, or writing onboarding text' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Write or review UX copy — microcopy, error messages...') and when ('Trigger with...' plus 'or when naming a CTA...'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Includes natural phrases a user would actually say — 'write copy for', 'what should this button say?', 'review this error message' — giving good coverage of likely trigger phrasings.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear UX-copy niche with distinct triggers focused on wording and interface text, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: anthropics/knowledge-work-plugins
Commit: f96c57c

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.