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

94%

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

88%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.

The body is a dense, action-oriented overview: a sequenced setup, clear command/routing table, and an explicit bounded-verification discipline. Its main weaknesses are a slightly florid opening paragraph and reference links whose target files are absent from this bundle.

Suggestions

Trim the opening 'out-of-distribution craft / award-winning design director' mission statement to a single actionable sentence so the body leads with instruction, not framing.

Ensure the referenced reference/*.md files (new-work.md, craft-floor.md, routing.md, the per-command references) actually ship in the bundle, or note explicitly where they live, so the one-level-deep navigation resolves.

Consider collapsing the dense 'How to design' and 'Modes' prose into the command/reference layer to keep SKILL.md purely as a routing overview.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes competence ('The brief wins', 'Refinement preserves; redesign replaces'), but the opening mission statement ('tools and permission to create design that earns to be called out-of-distribution craft... award-winning design director with impeccable understanding...') is florid framing rather than actionable instruction — a minor padding hit that keeps it just below score 5.	4 / 5
Actionability	Concrete executable commands ('node <skill-base-dir>/scripts/context.mjs --target <path>'), a full command-routing table with explicit per-command references, and unambiguous routing rules give copy-ready guidance across common cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	Setup is a clearly sequenced 3-step flow with explicit preconditions, and verification is codified with feedback loops ('Verify in bounded passes... inspect once... fix everything it shows in one batch, confirm with at most one more round, and stop polishing'), matching the score-5 anchor.	5 / 5
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references (command table linking reference/*.md), but the referenced reference/ files are not present in the bundle — only scripts/ exists — so navigation resolves incompletely, leaving it just below the score-5 'easy navigation' anchor.	4 / 5
	Total	18 / 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.

The description is a strong, comprehensive trigger: it names many concrete actions and surfaces, uses natural user language with synonyms, and explicitly pairs a 'what' with multiple 'Use when' trigger clauses and an exclusion boundary. Voice is third-person ('the user wants') with no first/second-person instruction voice.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ('design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract') plus concrete surface types ('websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states') — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what ('design... improve a frontend interface' with enumerated capabilities) and when ('Use when the user wants to...', 'Also use for bland designs... loud designs...', 'Not for backend-only or non-UI tasks') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Natural user phrases are well covered ('design', 'redesign', 'polish', 'critique', 'audit', 'make bolder', 'quieter', 'live browser iteration') with synonyms and variations matching the score-5 anchor; not merely technical jargon.	5 / 5
Distinctiveness Conflict Risk	A clear frontend-design niche with explicit boundary exclusion ('Not for backend-only or non-UI tasks') and distinct verb triggers, giving minimal conflict risk per the score-5 anchor.	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: .github/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.