impeccable

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

63%Weight 40%Scale 1-5

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

A well-organized dispatcher body with concrete commands, a clear command/routing table, and an explicit verification philosophy. It is held back by motivational padding in the opening and by progressive-disclosure links that point to reference files not present in the bundle.

Suggestions

Trim the motivational opening paragraph and rhetorical Core principles lines ('award-winning design director', 'Dream big and bold') so the body assumes Claude's competence and starts with actionable direction.

Restore or include the reference/*.md files referenced by the Commands table and inline links (new-work.md, craft-floor.md, shape.md, routing.md, etc.) so progressive-disclosure navigation resolves to real files.

Add explicit per-command validation/feedback-loop checkpoints inline (or confirm they exist in each reference) so batch and destructive operations like hooks and drift repair have visible validate-fix-retry steps.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and instruction-dense, but the opening motivational paragraph ('earns to be called out-of-distribution craft', 'award-winning design director', 'Dream big and bold') and rhetorical Core principles lines pad concepts Claude does not need explained.	3 / 5
Actionability	Provides concrete executable commands ('node <skill-base-dir>/scripts/context.mjs', 'node .cursor/skills/impeccable/scripts/pin.mjs <pin\|unpin> <command>') and a full Commands table mapping each command to a reference, with minor gaps because the detailed design guidance is deferred to references.	4 / 5
Workflow Clarity	Clear numbered Setup sequence and an explicit bounded-pass verification model ('Build fully, inspect once with a batched round... confirm with at most one more round, and stop polishing'), with explicit gating on destructive drift repair; minor gaps come from per-command workflows living in references.	4 / 5
Progressive Disclosure	The in-body structure is excellent and well-signaled (Setup, Modes, Commands table, Routing) with one-level-deep reference links, but the referenced reference/*.md files (~25 of them) are absent from the bundle — navigation resolves to missing files, which is more than a minor organization gap.	3 / 5
	Total	14 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, comprehensive description that explicitly covers what the skill does, when to use it with natural trigger terms, and an explicit out-of-scope boundary. It is long but every clause adds concrete trigger coverage rather than padding.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ('design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract') across concrete domains ('websites, landing pages, dashboards, product UI, app shells'), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (improve frontend interfaces across listed surfaces) and 'when' via an explicit 'Use when...' clause with concrete trigger phrases, plus an explicit negative boundary ('Not for backend-only or non-UI tasks').	5 / 5
Trigger Term Quality	Comprehensive natural terms with synonyms a user would actually say ('design', 'redesign', 'polish', 'critique', 'audit', 'bolder', 'quieter', 'animate', 'colorize'), including common variations like 'bland designs that need to become bolder'.	5 / 5
Distinctiveness Conflict Risk	Clear frontend-interface-design niche with distinct triggers and an explicit exclusion ('Not for backend-only or non-UI tasks') that minimizes conflict risk with unrelated skills.	5 / 5
	Total	20 / 20 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: 32 missing	Warning

	Total	14 / 16 Passed

Repository: pbakaus/impeccable
Path: .cursor/skills/impeccable/SKILL.md
Commit: 78b50aa

Reviewed: 4 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.