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

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.trae-cn/skills/impeccable/SKILL.md

Quality

Content

63%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-organized, directive overview with real executable scripts and an explicit bounded-verification loop. Its main weakness is a missing references/ directory: the 30 reference/*.md files the body depends on for per-command detail are absent from the bundle, breaking progressive disclosure and leaving execution detail unresolved.

Suggestions

Ship the references/ directory with the 30 reference/*.md files the Commands table and routing rules link to, or inline the missing detail for the most common commands so the skill is self-contained.

Replace the opening manifesto ('award-winning design director…', 'Dream big and bold…') with a one-line purpose statement; keep the directive principles but cut the inspirational rhetoric.

De-duplicate the command list between the frontmatter argument-hint and the Commands table to recover tokens.

Dimension	Reasoning	Score
Conciseness	The bulk (Setup, Modes, Commands table, Routing) is dense and directive and assumes Claude's competence, but the opening manifesto ('award-winning design director with impeccable understanding', 'Dream big and bold… highly inspiring work') is rhetorical padding that does not earn its tokens.	3 / 5
Actionability	Gives concrete, executable commands with real backing scripts — 'node <skill-base-dir>/scripts/context.mjs --target <path>', 'node .trae-cn/skills/impeccable/scripts/pin.mjs <pin\|unpin> <command>', '/impeccable hooks <on\|off\|…>' — plus a specific command table, with only minor abstract directives like 'inspect the target'.	4 / 5
Workflow Clarity	Setup is a clear 1-2-3 sequence and the 'Verify in bounded passes… inspect once with a batched round, fix everything, confirm with at most one more round, and stop' discipline is an explicit checkpointed feedback loop, but per-command execution detail lives in reference files that are not present, leaving the full workflow only partially self-contained.	4 / 5
Progressive Disclosure	The body is well structured as an overview with a Commands table linking to one-level-deep reference/*.md files, but the bundle contains no references/ directory — all 30 referenced files are missing — so the signaled disclosure structure is only partially realized and navigation to detail fails.	3 / 5
	Total	14 / 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 dense, third-person description with explicit trigger guidance, concrete actions, and a clear exclusion boundary — strong on completeness and specificity. Slightly weakened by a long enumeration that mixes natural user phrasing with skill-command jargon.

Suggestions

Trim the enumerated verb list to the terms users actually say (design, redesign, critique, audit, polish, animate, improve) and move skill-command jargon (distill, harden, colorize, overdrive) into argument-hint rather than the trigger phrase.

Lead with the 'Use when…' trigger and the 'Not for…' boundary so the activation signal lands before the long capability enumeration.

Dimension	Reasoning	Score
Specificity	Lists many concrete design actions — 'design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract' — giving comprehensive coverage of the frontend-design domain rather than vague verbs.	5 / 5
Completeness	Explicitly answers both 'what' (improve frontend interfaces across listed surfaces and concerns) and 'when' via 'Use when the user wants to…', 'Also use for…', and an explicit 'Not for backend-only or non-UI tasks' boundary.	5 / 5
Trigger Term Quality	Strong natural terms (design, redesign, critique, audit, polish, improve, UX review, accessibility) with synonyms (bland→bolder, loud→quieter), but several enumerated verbs (distill, harden, colorize, shape, overdrive) are skill-command jargon users would not naturally say.	4 / 5
Distinctiveness Conflict Risk	Clear frontend-UI niche reinforced by an explicit exclusion clause, but the broad 'design / improve a frontend interface' verb set carries minor overlap risk with general web-development or styling 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: 32 missing	Warning

	Total	14 / 16 Passed

Repository: pbakaus/impeccable
Path: .trae-cn/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.