clarify
Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.
70
63%
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 ./source/skills/clarify/SKILL.mdQuality
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 improvement), lists specific content types it handles, and provides an explicit 'Use when' clause with natural trigger terms. It uses third person voice correctly and is concise without being vague. The description would effectively differentiate this skill from general writing or editing skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: improve unclear UX copy, error messages, microcopy, labels, and instructions. The goal is also concrete: 'make interfaces easier to understand.' | 3 / 3 |
Completeness | Clearly answers both 'what' (improve unclear UX copy, error messages, microcopy, labels, instructions) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'confusing text', 'unclear labels', 'bad error messages', 'hard-to-follow instructions', 'better UX writing', 'microcopy'. These cover a good range of natural phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Targets a clear niche—UX writing and interface copy improvement—with distinct triggers like 'microcopy', 'error messages', 'UX writing' that are unlikely to conflict with general writing or coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides comprehensive UX writing guidance with useful before/after examples across many interface text categories, which is its primary strength. However, it is far too verbose for a skill file—it reads more like a UX writing handbook than a concise instruction set for Claude, who already understands these principles. The monolithic structure with no progressive disclosure and the lack of concrete implementation workflows significantly reduce its effectiveness as a skill.
Suggestions
Reduce content by 60-70%: Remove principles Claude already knows (be specific, be concise, be active, etc.) and keep only the before/after examples as a quick reference pattern library.
Split the nine copy-type subsections (Error Messages, Form Labels, Buttons, etc.) into a separate COPY_PATTERNS.md reference file, keeping only a summary table in the main skill.
Add a concrete workflow with validation: e.g., '1. Identify all copy instances → 2. Categorize by type → 3. Draft improvements → 4. Review against checklist → 5. If inconsistencies found, revise and re-check'.
Remove the closing motivational paragraph ('Remember: You're a clarity expert...') and the 'CRITICAL' callout explaining why clear copy matters—these explain things Claude already understands.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~150+ lines, with extensive explanations of UX writing principles that Claude already knows well (e.g., 'be specific', 'be concise', 'be active'). The bad/good examples for every category are helpful but the sheer volume of them, combined with redundant principles sections and the closing motivational paragraph, makes this significantly bloated. | 1 / 3 |
Actionability | The before/after examples are concrete and useful, providing clear patterns to follow. However, the skill lacks executable implementation guidance—there are no code snippets, no specific file editing commands, and the 'Assess Current Copy' and 'Plan Copy Improvements' sections are more conceptual frameworks than actionable steps. The dependency on external commands (frontend-design, teach-impeccable) without explaining what they provide reduces standalone actionability. | 2 / 3 |
Workflow Clarity | There is a general sequence (gather context → assess → plan → improve → verify), but the verification step is a checklist of questions rather than concrete validation actions. The mandatory preparation step references external commands without clear fallback if they're unavailable. For a skill involving text changes across an interface, there's no feedback loop for iterating on improvements based on verification results. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with all content inline. The nine subsections (Error Messages, Form Labels, Buttons, Help Text, Empty States, Success Messages, Loading States, Confirmation Dialogs, Navigation) could easily be split into separate reference files, with SKILL.md serving as a concise overview. There are no references to external files for detailed guidance on specific copy types. | 1 / 3 |
Total | 6 / 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
- pbakaus/impeccable
- Commit
3a4fc70
- 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.