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

78%

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 ./.agents/skills/impeccable/SKILL.md

The canonical home for this skill is impeccable in pbakaus/impeccable

Quality

Content

56%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-structured orchestration skill with concrete commands and a clear sequenced workflow, but it carries motivational padding in its opening and Core principles, and its primary progressive-disclosure layer is undermined because the 29 referenced reference/*.md files are absent from the bundle. Tightening the prose and shipping the reference playbooks would lift the weakest dimensions.

Suggestions

Trim the opening paragraph and inspirational Core principles ("Go all out," "Dream big and bold") to concrete directives so every token earns its place, lifting conciseness.

Include the missing reference/*.md playbooks (29 are linked but none exist in the bundle) so the one-level-deep progressive-disclosure layer actually resolves.

Add an explicit validate/confirm-then-act loop for the risky operations (hooks on/off/reset, pin, doctor repair) so workflow_clarity reaches a 5.

Dimension	Reasoning	Score
Conciseness	The bulk is lean routing guidance, but the opening paragraph ("design that earns to be called out-of-distribution craft," "award-winning design director with impeccable understanding," "peak creativity, a clear POV") and parts of Core principles ("Go all out," "Dream big and bold") are motivational padding that assumes less of Claude than warranted; this is more than the minor trim of a 4 but not the several padded sections of a 2.	3 / 5
Actionability	Gives concrete executable commands and scripts (context.mjs with --target, pin.mjs <pin\|unpin>, $impeccable hooks <on\|off\|status\|...>, $impeccable doctor) plus a full command table with arguments and specific routing rules, so guidance is mostly executable with only minor gaps where commands defer to references; not the copy-paste-complete profile of a 5.	4 / 5
Workflow Clarity	Setup is a clear ordered 3-step sequence with checkpoints ("once per session," "Before acting... inspect the target... before editing," "After analysis and direction are resolved") and routing gives explicit decision branches with a gate ("ask once if two commands fit"), but risky ops like hooks/doctor lack an explicit validate-fix-retry loop, so it sits above a 3 and below a 5.	4 / 5
Progressive Disclosure	Structure and one-level-deep signaling are strong (clear sections plus a command table routing to reference playbooks), but the 29 referenced reference/*.md files do not exist in the bundle — only scripts/ is present — so a large share of the reference layer is broken, which is a bigger organization gap than the minor issues allowed at a 4 and above the minimal/buried profile of a 2.	3 / 5
	Total	14 / 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.

The description is exemplary: it lists comprehensive concrete actions and domains, supplies natural trigger terms with synonyms, explicitly answers both what and when, and carves out a distinct niche with a clear negative boundary. Its only weakness is verbosity, which the rubric flags but does not penalize on these dimensions.

Dimension	Reasoning	Score
Specificity	Names many concrete actions ("design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve") alongside concrete domains (websites, landing pages, dashboards, app shells, components, forms, settings, onboarding, empty states), giving comprehensive coverage rather than the several-with-gaps profile of a 4.	5 / 5
Completeness	Opens with an explicit "Use when..." trigger clause, reinforces with "Also use for...", and states a negative boundary ("Not for backend-only or non-UI tasks"), explicitly answering both what it does and when to invoke it with concrete trigger phrases, exactly the score-5 pattern.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers users would actually say ("design," "critique," "audit," "polish," "bolder," "quieter," "live browser iteration," "landing pages," "dashboards," "forms") plus synonyms (bland/loud, bolder/quieter), matching the comprehensive-coverage-with-synonyms anchor; not the few-terms-missing profile of a 4.	5 / 5
Distinctiveness Conflict Risk	Scoped tightly to frontend UI work with an explicit exclusion ("Not for backend-only or non-UI tasks"), establishing a clear niche with distinct triggers and minimal conflict risk, matching the score-5 anchor rather than the minor-overlap profile of a 4.	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: 32 missing	Warning

	Total	14 / 16 Passed

Repository: getlarge/themoltnet
Path: .agents/skills/impeccable/SKILL.md
Commit: 5daa9ca

Reviewed: ~13 hours 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.