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

85%

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

71%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 tightly written, well-organized instruction skill with concrete commands and a clear verify loop. Its main weakness is progressive disclosure: the body routes depth to 'reference/*.md' files that are not present in the bundled package, breaking the navigation the SKILL.md advertises.

Suggestions

Bundle the 'reference/' directory (new-work.md, craft-floor.md, routing.md, operate.md, and the per-command references) so every link in the Commands table resolves; without them, most of the skill's depth is unreachable.

Split the long compound Setup step 1 into separate lines for base-dir resolution, the Windows fallback, and the --target flag, improving scannability without adding tokens.

Clarify the '<skill-base-dir>' placeholder once up front and use a short consistent token thereafter, so repeated command examples read as directly executable.

Dimension	Reasoning	Score
Conciseness	Lean, directive prose that assumes Claude's competence and never explains basic design concepts; a few compound sentences (e.g., Setup step 1) could be tightened, so it sits just below the anchor-5 'every token earns its place' bar.	4 / 5
Actionability	Concrete, executable guidance throughout — exact commands ('impeccable context', the Commands table with per-command references), specific file loads, and explicit routing rules; minor gaps come from unresolved placeholders like '<skill-base-dir>' and '--target <path>'.	4 / 5
Workflow Clarity	Clear sequenced Setup (1-2-3), a bounded-verify feedback loop ('inspect once... fix everything in one batch, confirm with at most one more round, and stop'), and explicit routing; not 5 because the workflow is routing/decision-heavy rather than a tight validate-fix-retry pipeline with checkpoints at every fragile step.	4 / 5
Progressive Disclosure	The body is well-structured with a clear Commands table and clearly signaled one-level-deep references, but the 32 referenced 'reference/*.md' files are absent from the actual bundle (only 'scripts/' is present), so the promised navigation does not resolve against the real bundle structure.	3 / 5
	Total	15 / 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 high-quality description: third-person, action-verb-rich, with an explicit 'Use when' trigger, broad-but-coherent frontend scope, and an explicit out-of-scope boundary. The only minor risk is sheer length, but every listed item is concrete rather than fluff.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ('design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract') plus concrete domains (websites, landing pages, dashboards, forms, empty states), giving comprehensive coverage matching the anchor-5 example.	5 / 5
Completeness	Explicitly answers both what (covers websites, dashboards, product UI; handles UX review, visual hierarchy, accessibility, etc.) and when ('Use when the user wants to... improve a frontend interface'), with concrete trigger phrases — a clear anchor-5 match.	5 / 5
Trigger Term Quality	Opens with 'Use when the user wants to design, redesign, shape, critique...' and adds natural phrases users say ('bland designs that need to become bolder', 'loud designs that should become quieter', 'live browser iteration'), covering synonyms and variations comprehensively.	5 / 5
Distinctiveness Conflict Risk	Carves a clear frontend-UI niche and adds an explicit negative boundary ('Not for backend-only or non-UI tasks'), giving distinct triggers with minimal conflict risk; not below 5 because the scope is coherently bounded to one domain.	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: 34 missing	Warning

	Total	14 / 16 Passed

Repository: pbakaus/impeccable
Path: .cursor/skills/impeccable/SKILL.md
Commit: 0a4e72a

Reviewed: 3 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.