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.

The body is a well-organized, actionable overview with a strong command/routing structure and explicit verification cadence, though some prose is dense and could be tightened. Its main defect is progressive disclosure: nearly all reference/*.md paths it points to are missing from the bundle, breaking the navigation it promises.

Suggestions

Ship the reference/ directory (new-work.md, craft-floor.md, routing.md, operate.md, and the ~25 command references) so the well-signaled links actually resolve; dangling references are the body's biggest gap.

Tighten the longest compound sentences (Setup step 1 and the Modes definitions) into shorter clauses to reduce density without losing the operational detail.

Move or mark the few abstract directives ("Dream big and bold," "let the artifact lead") as framing rather than steps, so actionable instructions stay clearly separable from motivational guidance.

Dimension	Reasoning	Score
Conciseness	Information-dense and free of basic-concept padding, but several sentences are overlong and could be trimmed (e.g. the Setup step-1 launcher sentence and the compound sentences in Modes), keeping it just below the lean ideal.	4 / 5
Actionability	Provides concrete, executable guidance via the Commands table, exact setup invocation ("<skill-base-dir>/scripts/impeccable context"), and explicit routing branches, but mixes in some abstract directives ("Dream big and bold," "let the artifact lead") that aren't directly executable.	4 / 5
Workflow Clarity	The Setup section is a clear numbered 1-2-3 sequence and verification cadence is explicit ("Verify in bounded passes... fix everything... confirm with at most one more round, and stop"), though detailed per-task workflows live in the referenced files rather than the body.	4 / 5
Progressive Disclosure	The body is well-structured as an overview with clearly signaled one-level-deep references (a Commands table linking 30 reference/*.md files), but the reference/ directory is absent from the bundle, so most referenced paths dangle and navigation does not resolve.	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 strong, comprehensive description that concretely enumerates actions, surfaces, and trigger phrases while drawing a clear scope boundary. It answers what, when, and distinctiveness without padding or vague language.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ("design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract") plus specific surfaces ("websites, landing pages, dashboards, product UI, app shells, components, forms"), giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both what (frontend interface improvement covering named surfaces and aspects) and when ("Use when the user wants to..." plus "Also use for bland designs..." and "Not for backend-only or non-UI tasks"), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural keywords users would say ("design," "redesign," "critique," "audit," "polish," "animate," "colorize") plus synonyms and intent phrases ("bland designs that need to become bolder," "loud designs that should become quieter," "live browser iteration"), matching the anchor's expectation of broad synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Clear frontend-UI-design niche with an explicit out-of-scope boundary ("Not for backend-only or non-UI tasks"), minimizing conflict 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: 34 missing	Warning

	Total	14 / 16 Passed

Repository: pbakaus/impeccable
Path: .gemini/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.