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

80%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/impeccable/SKILL.md

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 well-structured, actionable routing skill with clear sequencing and an explicit bounded-verification loop. Its main weakness is that the extensive reference/*.md navigation it depends on points to files not present in the bundle, undermining the progressive-disclosure design.

Suggestions

Ship the reference/*.md files (craft-floor.md, new-work.md, routing.md, and one per command) in a references/ bundle so the body's navigation links actually resolve.

Trim the motivational opening paragraph ('out-of-distribution craft', 'award-winning design director') to operational essentials to tighten conciseness.

Inline a one-line summary of the most critical reference (e.g. craft-floor.md's absolute bans) so the quality floor is not entirely gated behind a missing file.

Dimension	Reasoning	Score
Conciseness	The body is overwhelmingly operational and lean (Setup steps, Modes, Commands table, Routing), with only a minor trim-able motivational opening ('design that earns to be called out-of-distribution craft... award-winning design director'); no concept-teaching padding.	4 / 5
Actionability	Concrete executable guidance throughout — specific commands (impeccable context, impeccable pin, /impeccable hooks, /impeccable doctor), a full command-to-reference table, and explicit file paths — with minor gaps because the executable detail lives in the referenced (and here, absent) reference files.	4 / 5
Workflow Clarity	Clear sequenced Setup (once-per-session context, then craft-floor before any edit) with an explicit bounded-verify feedback loop ('inspect once with a batched round... fix everything... confirm with at most one more round, and stop') and a launcher-failure recovery fallback; minor validation detail is delegated to referenced docs.	4 / 5
Progressive Disclosure	Structure and signaling are excellent — a clear overview/router with a Commands table pointing to one-level-deep reference files — but the referenced reference/*.md files (craft-floor.md, new-work.md, routing.md, one per command) are absent from the bundle (only scripts/ exists), so the disclosure is broken in practice.	3 / 5
	Total	15 / 20 Passed

Description

88%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 highly specific, comprehensive description with explicit trigger guidance and a useful negative boundary. It is slightly diluted by skill-command jargon mixed into the trigger terms and a broad action list that risks minor overlap with adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions (design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract) plus exhaustive surface and aspect coverage — comprehensive, not just 1-2 actions.	5 / 5
Completeness	Explicitly answers both 'what' (improve frontend interfaces across named surfaces and aspects) and 'when' (multiple 'Use when...'/'Also use for...' triggers) with a concrete negative boundary ('Not for backend-only or non-UI tasks').	5 / 5
Trigger Term Quality	Strong natural terms (design, redesign, dashboard, landing pages, forms, typography, responsive, accessibility) with synonyms (design/redesign/shape, bolder/delight, quieter), but several verbs (distill, harden, shape, overdrive) are skill-command jargon rather than phrases a user would naturally say.	4 / 5
Distinctiveness Conflict Risk	Clear frontend-UI niche with an explicit negative scope that reduces conflict, but the very broad action list (optimize, adapt, harden, audit) creates minor overlap risk with performance- or accessibility-specific skills.	4 / 5
	Total	18 / 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: .claude/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.