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 ./.trae/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-written routing and operations manual: concise, actionable, with a clear setup sequence and an explicit bounded verification loop. Its one real defect is that the progressive-disclosure layer it depends on — the reference/ directory of per-command playbooks, craft-floor, native, and routing files cited throughout the body and scripts — is not present in the bundle, breaking navigation in practice.

Suggestions

Ship the missing reference/ directory: the body cites 31 reference/*.md files (craft-floor.md, new-work.md, routing.md, operate.md, every per-command playbook, and the .native.md variants) but no reference/ or references/ directory exists in the bundle, so every 'See reference/X.md' link is broken and the skill's actual execution guidance is unavailable.

Verify referenced paths resolve at runtime: context.mjs loads reference/<platform>.md via SKILL_REFERENCE_DIR (safeRead silently returns null on missing files), so with the directory absent the native-platform guidance for ios/android/adaptive silently no-ops rather than failing loudly.

Trim the motivational intro paragraph ('Whereas before, your design work would have been safe, timid and measured...') to lift conciseness — it is rhetorical framing rather than operational guidance Claude needs.

Dimension	Reasoning	Score
Conciseness	The body is dense operational prose that does not explain concepts Claude already knows (no 'what is a landing page' padding) and packs a lot of routing guidance per line. It is not a 5 because the rhetorical intro ('Whereas before, your design work would have been safe, timid and measured, you now approach every design task as a award-winning design director...') and a few wordy sentences are motivational padding that could be trimmed.	4 / 5
Actionability	Concrete, executable commands are present ('node <skill-base-dir>/scripts/context.mjs', 'node .trae/skills/impeccable/scripts/pin.mjs <pin\|unpin> <command>', '/impeccable hooks <on\|off\|status\|...>', '/impeccable doctor') and the Commands table maps each verb to a reference. As an instruction-only skill the absence of code blocks is not penalized; it stops short of 5 because copy-paste-ready depth for each command is delegated to the reference files rather than carried inline.	4 / 5
Workflow Clarity	Setup is a clean 3-step sequence and the body carries an explicit bounded verification loop ('Build fully, inspect once with a batched round (desktop and mobile together...), fix everything it shows in one batch, confirm with at most one more round, and stop polishing'), so validation is present rather than absent. It does not reach 5 because the detailed per-command checklists and feedback loops live in the reference files, so the body's own workflow detail is routing-level.	4 / 5
Progressive Disclosure	The body is well structured as an overview pointing one level deep to reference/.md files via a Commands table and inline links, with clearly signaled (not buried) navigation — which alone would read as a 4-5. But scored against the actual bundle structure per the rubric guideline, the referenced disclosure layer is missing: there is no reference/ directory, and none of the 31 cited reference/.md playbooks exist in the bundle, so every navigation link is dangling and the disclosed content the skill needs to function is absent.	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 strong, explicit trigger description: it states both what the skill does and when to use it with concrete action verbs and natural trigger phrases, plus a clear negative boundary. Its only soft spots are trigger-term breadth (a few casual phrasings absent) and minor overlap risk from the wide frontend scope.

Dimension	Reasoning	Score
Specificity	The description lists many concrete action verbs ('design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract') plus concrete surfaces and concerns, giving comprehensive rather than minor-gap coverage. It sits clearly above the 'several specific actions; minor gaps' (4) anchor.	5 / 5
Completeness	It opens with an explicit 'Use when the user wants to...' trigger and states what the skill does (improve frontend interfaces across named surfaces and concerns), then adds 'Also use for...' triggers and a 'Not for backend-only or non-UI tasks' boundary. Both what and when are explicit with concrete trigger phrases, matching the 5 anchor; the 'Use when' clause is present so no 3-cap applies.	5 / 5
Trigger Term Quality	Natural phrasings users would say are well covered ('bland designs that need to become bolder', 'loud designs that should become quieter', 'live browser iteration', 'frontend interface'), with good synonym breadth across the command verbs. It falls short of the 5 anchor, whose model is a focused tool with synonyms plus file extensions; common casual phrasings like 'make it pretty', 'modernize', or 'rebrand' are not all captured.	4 / 5
Distinctiveness Conflict Risk	It carves a clear frontend-design niche and adds an explicit negative boundary ('Not for backend-only or non-UI tasks'), which is more distinct than the 'could still overlap' (3) anchor. It does not reach 5 because the scope is very broad within frontend/UI work and could overlap with general web-dev, accessibility, or performance 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/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.