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

90%

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

81%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 well-organized, highly actionable routing document with clear sequenced workflows and concrete commands. Its one serious defect is that the entire reference/*.md layer it points to is missing from the bundle, breaking progressive disclosure against the actual file structure.

Suggestions

Ship the reference/*.md files the body cites (new-work.md, craft-floor.md, shape.md, routing.md, and every command reference in the Commands table) so the one-level-deep references resolve.

If any referenced references are intentionally external/optional, mark them clearly and inline the minimum needed guidance so the skill is not dependent on missing files.

Trim the launcher-unavailable and routing-prose paragraphs to the essential directives to lift conciseness from 4 toward 5.

Dimension	Reasoning	Score
Conciseness	The body is dense but largely earns its tokens for a multi-command routing skill, with no padding of concepts Claude already knows; it is only slightly over-written in a few clauses (e.g. the launcher-unavailable paragraph), keeping it just below the lean-and-efficient anchor.	4 / 5
Actionability	It gives fully executable, copy-paste-ready commands ('${CLAUDE_SKILL_DIR}/scripts/impeccable context', 'pin <pin\|unpin> <command>', '/impeccable hooks <on\|off\|status...>') plus a complete Commands table with syntax, category, and per-command reference, covering the common cases concretely.	5 / 5
Workflow Clarity	Setup is a clear numbered sequence with an explicit verification philosophy ('build fully, inspect once... confirm with at most one more round, and stop') and a launcher-failure recovery fallback, providing explicit checkpoints and a feedback loop for the workflow.	5 / 5
Progressive Disclosure	The body is structured as an overview that signals ~25 one-level-deep reference/*.md files in a clean Commands table, but the reference/ directory is absent from the actual bundle, so every reference is dangling and the detailed content is unreachable — measured against the real file listing, navigation to the separated material is broken.	2 / 5
	Total	16 / 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.

An exceptionally strong description: it pairs comprehensive concrete actions with natural user trigger phrases, answers both what and when explicitly, and draws a clear boundary against non-UI work. No meaningful gaps for the description rubric.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete actions ('design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract') and a comprehensive list of surface types (websites, dashboards, product UI, components, forms, settings, onboarding, empty states), matching the comprehensive-coverage anchor.	5 / 5
Completeness	It explicitly answers both 'what' (improve frontend interfaces; the covered surface types) and 'when' ('Use when the user wants to...'), with concrete trigger phrases and an explicit exclusion ('Not for backend-only or non-UI tasks').	5 / 5
Trigger Term Quality	It leads with 'Use when the user wants to...' and packs in natural phrases users say ('design', 'critique', 'audit', 'polish', 'bolder', 'quieter', 'colorize') plus synonyms and surface terms, giving comprehensive natural-term coverage.	5 / 5
Distinctiveness Conflict Risk	The frontend-UI-design niche is sharply defined with distinct triggers and an explicit 'Not for backend-only or non-UI tasks' boundary, minimizing conflict risk with other 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: 34 missing	Warning

	Total	14 / 16 Passed

Repository: pbakaus/impeccable
Path: plugin/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.