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.
52
58%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.roo/skills/polish/SKILL.mdQuality
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 purpose and trigger conditions. Its main strengths are the explicit 'Use when...' clause with natural user language and good coverage of trigger phrases. The primary weakness is that the capability actions could be more concrete and the domain could be narrower to reduce potential overlap with related skills like code review or design review.
| 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' (performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios). | 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 'polish' and 'finishing touches' is reasonably distinct, but terms like 'consistency' and 'something looks off' could overlap with code review, design review, or linting skills. The scope (alignment, spacing, micro-details) is somewhat broad and could conflict with CSS/layout or code formatting skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
35%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 UI polish checklist but suffers from significant verbosity—most of its content covers standard frontend best practices that Claude already knows (WCAG, semantic HTML, touch targets, font loading). The structure is logical with a clear progression from assessment to systematic polish to verification, but the sheer volume of inline content undermines token efficiency. It would be much stronger as a concise overview with references to detailed sub-files for each polish dimension.
Suggestions
Cut content by 60-70%: Remove explanations of concepts Claude already knows (what hover states are, what WCAG is, what layout shift means) and keep only project-specific guidance, non-obvious tips (like tinted neutrals, optical centering), and the specific values/thresholds.
Extract the 12 polish dimensions into a separate POLISH-CHECKLIST.md reference file, keeping only the top-level categories and non-obvious tips inline in SKILL.md.
Add concrete code examples for key actions—e.g., a CSS snippet for reduced-motion handling, a script to check for console.logs, or a command to audit contrast ratios.
Add explicit validation checkpoints between major polish phases (e.g., 'After fixing spacing, do a visual diff at all breakpoints before moving to typography') to create feedback loops that prevent regressions.
| 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). The checklist largely repeats the sections above it. Significant token waste with explanations of basic concepts like what hover/focus/active states are. | 1 / 3 |
Actionability | Provides specific guidance (e.g., '150-300ms transitions', '44x44px touch targets', 'ease-out-quart/quint/expo') and a concrete checklist, but lacks executable code examples or specific commands. Most items are descriptive checklists rather than copy-paste-ready instructions. The 'Check' sub-section under alignment mentions 'enable grid overlay' but doesn't show how. | 2 / 3 |
Workflow Clarity | Has a clear sequence (Pre-Polish Assessment → Systematic Polish → Checklist → Final Verification) and the 'CRITICAL: Polish is the last step' guard is good. However, there are no explicit validation checkpoints between polish dimensions, no feedback loops for catching regressions introduced during polish, and no 'fix and re-verify' steps despite the destructive potential of broad UI changes. | 2 / 3 |
Progressive Disclosure | References /frontend-design and /teach-impeccable as prerequisites, which is good. However, the massive inline content (12+ subsections with detailed bullet lists) would benefit greatly from being split into separate reference files. The checklist duplicates the section content and could be a separate file. No links to deeper references for individual topics. | 2 / 3 |
Total | 7 / 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
- onesixeight/IronMarket
- Commit
d8f6cf2
- 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.