CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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, mostly lean overview that routes each command to a one-level-deep reference, gives concrete runnable commands, and states an explicit bounded-pass verification discipline. The main weaknesses are motivational padding in the intro/principles and delegation of executable detail to reference files that are not present in the provided bundle.

Suggestions

Trim the rhetorical opening paragraph and 'Dream big and bold' principle to directive statements; the motivational framing costs tokens without adding actionable guidance.

Inline one or two short concrete examples (e.g., a minimal context.mjs invocation with expected output) so the body is self-sufficient for the common case without requiring a reference load.

Ensure the referenced reference/*.md files ship in the bundle so the one-level-deep progressive-disclosure structure is verifiable and navigable rather than only signaled.

DimensionReasoningScore

Conciseness

Mostly efficient and information-dense assuming Claude's competence, but the opening paragraph ('earns to be called out-of-distribution craft', 'award-winning design director with impeccable understanding') and core-principle lines like 'Dream big and bold. Distinct, beautiful, outstanding and highly inspiring work' are motivational rhetoric rather than actionable instruction. Not a 5 due to this rhetorical padding; not a 3 because the bulk is tight, directive, and free of explaining concepts Claude already knows.

4 / 5

Actionability

Concrete executable commands appear throughout ('node <skill-base-dir>/scripts/context.mjs', '--target <path>', 'node .gemini/skills/impeccable/scripts/pin.mjs <pin|unpin> <command>', '/impeccable hooks ...') and the Commands table maps each verb to a reference. Not a 5 because the body delegates the copy-paste-ready executable detail to reference files rather than presenting specific examples covering common cases inline; not a 3 because the guidance given is concrete and runnable, not pseudocode.

4 / 5

Workflow Clarity

A clear 3-step Setup sequence, explicit routing decision rules, and a stated verification discipline ('Build fully, inspect once with a batched round... fix everything in one batch, confirm with at most one more round, and stop polishing') provide checkpoints. Not a 5 because the verification is expressed as philosophy rather than a single explicit validate→fix→retry checklist tied to the main flow; not a 3 because sequence and checkpoints are clearly present.

4 / 5

Progressive Disclosure

The body is a clear overview with well-signaled one-level-deep references (the Commands table plus inline links to reference/*.md) and content appropriately split per command — a textbook disclosure structure. Not a 5 because the referenced reference/*.md files are not present in the bundle (only scripts/ exists), so the one-level-deep, non-nested property cannot be verified against the actual bundle structure as the rubric directs.

4 / 5

Total

16

/

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.

An exemplary description: it names many concrete actions and surfaces, includes comprehensive natural trigger terms with synonyms, explicitly answers both what and when, and draws a clear negative boundary to avoid mis-triggering. It is concise relative to its breadth and free of vague fluff.

DimensionReasoningScore

Specificity

Lists many concrete actions (design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract) plus concrete surfaces (websites, landing pages, dashboards, forms, settings, onboarding, empty states) and concrete concerns (visual hierarchy, IA, a11y, perf, responsive, theming, typography) — comprehensive coverage matching the score-5 anchor. Not a 4 because coverage is broad and specific rather than having minor gaps.

5 / 5

Completeness

Explicitly answers both what ('Covers...', 'Handles UX review, visual hierarchy...') and when ('Use when the user wants to...', 'Also use for...', 'Not for backend-only or non-UI tasks') with concrete trigger phrases. Matches the score-5 anchor precisely; not a 4 because both what and when are concrete and explicit.

5 / 5

Trigger Term Quality

Comprehensive natural terms users actually say — 'design', 'redesign', 'polish', 'critique', 'audit', 'animate', 'colorize', 'bolder', 'quieter', 'landing pages', 'dashboards', 'empty states' — including synonyms (bolder/louder, quieter) and the negative boundary trigger. Not a 4 because it covers synonyms and natural phrasings comprehensively; file extensions are N/A for this frontend-design niche.

5 / 5

Distinctiveness Conflict Risk

Clear niche (frontend interface design) with distinct triggers and an explicit negative boundary ('Not for backend-only or non-UI tasks') minimizing conflict risk. Matches the score-5 anchor; not a 4 because overlap risk is minimal given the explicit scope and exclusion.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.