polish

Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.

Quality

54%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/polish/SKILL.md

Quality

Discovery

82%

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 solid description that clearly communicates both what the skill does and when to use it, with natural trigger terms that users would realistically say. Its main weakness is that the capability descriptions are somewhat categorical rather than deeply specific, and there's moderate overlap risk with general styling or design review skills. Overall it performs well as a skill description.

Dimension	Reasoning	Score
Specificity	Names the domain (quality pass) and some actions (fixing alignment, spacing, consistency, micro-detail issues), but these are somewhat general categories rather than highly concrete actions like 'adjust padding values' or 'normalize font sizes'.	2 / 3
Completeness	Clearly answers both what ('final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping') and when ('Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great').	3 / 3
Trigger Term Quality	Includes strong natural trigger terms users would actually say: 'polish', 'finishing touches', 'pre-launch review', 'something looks off', 'good to great'. These cover a good range of how users naturally express the need for this skill.	3 / 3
Distinctiveness Conflict Risk	The concept of 'fixing alignment, spacing, consistency' could overlap with general CSS/styling skills or design review skills. However, the specific framing as a 'final quality pass before shipping' and triggers like 'finishing touches' and 'good to great' help narrow the niche somewhat.	2 / 3
	Total	10 / 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.

This skill is a comprehensive but overly verbose UI polish checklist that reads more like a general frontend quality handbook than a targeted skill for Claude. Most of the content covers well-known best practices (WCAG, touch targets, semantic HTML, no console.logs) that Claude already understands, wasting significant token budget. The lack of executable code examples, concrete fix patterns, and proper content splitting into sub-files significantly reduces its effectiveness.

Suggestions

Cut content by 60-70%: Remove items Claude already knows (WCAG basics, semantic HTML, removing console.logs) and focus only on non-obvious polish patterns, specific fix recipes, and project-specific conventions.

Add executable code examples for common polish fixes (e.g., a CSS snippet for optical icon centering, a transition mixin with the recommended easing, a script to audit spacing token usage).

Split the 12 polish dimensions into a separate POLISH-CHECKLIST.md reference file, keeping only the top-level workflow and 2-3 most critical dimensions inline in SKILL.md.

Add concrete validation steps: e.g., 'Run `npx lighthouse --only-categories=accessibility` and verify score ≥ 95' or 'Check CLS with `web-vitals` library — must be < 0.1'.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~200+ lines. Many items are general UI/UX best practices Claude already knows (WCAG contrast, semantic HTML, no console.logs, 44px touch targets, FOUT/FOIT). The exhaustive checklists read like a textbook rather than adding novel, project-specific knowledge. Significant token waste.	1 / 3
Actionability	Provides concrete checklists and specific values (150-300ms, 44x44px, 45-75 chars), which is somewhat actionable. However, there are no executable code snippets, no specific commands to run, and guidance like 'enable grid overlay and verify alignment' is vague. It describes what to check rather than how to fix things.	2 / 3
Workflow Clarity	There is a clear sequence (pre-assessment → systematic polish → checklist → final verification), and the 'CRITICAL: Polish is the last step' constraint is good. However, there are no explicit validation checkpoints between polish dimensions, no feedback loops for error recovery, and the verification step is vague ('use it yourself') without concrete validation commands or criteria.	2 / 3
Progressive Disclosure	Monolithic wall of text with all content inline. The 12+ subsections with extensive bullet lists should be split into separate reference files. The only external reference is to /frontend-design, but the skill itself dumps everything into one massive document with no navigation structure or links to detailed sub-guides.	1 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 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: about 5 hours 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.