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.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%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-organized routing overview with strong validation discipline and concrete launcher commands. Its main weakness is progressive disclosure: the many 'reference/*.md' links it depends on are not present in the bundle, so the one-level-deep structure it advertises cannot actually be navigated.

Suggestions

Ship the referenced reference/*.md files (new-work.md, craft-floor.md, routing.md, operate.md, and the per-command references) in a references/ or reference/ bundle so the advertised progressive-disclosure structure actually resolves.

Trim the rhetorical opening paragraph ('Whereas before, your design work would have been safe, timid and measured…') to a one-line intent statement to raise conciseness to a lean score-5 level.

Inline one or two concrete executable snippets (e.g., example 'impeccable context' invocation with a sample --target) so actionability does not depend entirely on loading external references.

DimensionReasoningScore

Conciseness

The body is dense and mostly assumes Claude's competence (routing tables, terse command specs), but the opening paragraph ('Whereas before, your design work would have been safe, timid and measured…') is rhetorical padding that could be trimmed — efficient with minor instances of over-explanation, matching the score-4 anchor rather than the lean score-5 anchor.

4 / 5

Actionability

It gives concrete executable commands ('<skill-base-dir>/scripts/impeccable context', 'impeccable pin <pin|unpin> <command>', '/impeccable doctor') and a routing table, but much guidance is 'load [reference/X.md] and follow it' rather than inlined executable steps — mostly executable guidance with minor gaps, matching score 4 and not the fully copy-paste score-5 anchor.

4 / 5

Workflow Clarity

Setup is a numbered sequence with explicit validation discipline ('Verify in bounded passes, not a loop… fix everything it shows in one batch, confirm with at most one more round, and stop') and a launcher-failure fallback with its own ordered steps, providing clear sequencing with explicit validation checkpoints and feedback loops — matching the score-5 anchor.

5 / 5

Progressive Disclosure

Structure is good with a Commands table and one-level-deep '[reference/X.md]' links, but the referenced reference/*.md files (new-work.md, craft-floor.md, routing.md, etc.) are not present in the bundle — references are signaled but the destination files are missing, leaving it at 'some structure, references present but not clearly deliverable' rather than the score-4/5 anchors whose references resolve.

3 / 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.

The description is comprehensive, concrete, and well-scoped: it enumerates many specific actions, surfaces, and natural trigger phrases while explicitly bounding the skill's scope with an exclusion clause. Third-person voice is maintained throughout, satisfying the rubric's voice requirement.

DimensionReasoningScore

Specificity

The description lists a long, concrete inventory of actions ('design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract') plus enumerated domains (websites, dashboards, components, forms, settings, onboarding, empty states) — comprehensive coverage, matching the score-5 anchor of multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers 'what' ('design… improve a frontend interface') and 'when' via the 'Use when the user wants to…' clause plus concrete trigger surfaces, and adds a 'Not for backend-only or non-UI tasks' boundary — clearly and explicitly both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

It includes natural phrases users actually say ('make it bolder', 'quieter', 'polish', 'audit') alongside synonyms and surface types (landing pages, dashboards, empty states), giving comprehensive coverage of natural terms including common variations.

5 / 5

Distinctiveness Conflict Risk

The niche is clearly scoped to frontend/interface design and the explicit 'Not for backend-only or non-UI tasks' exclusion minimizes conflict risk with unrelated skills, matching the score-5 clear-niche anchor.

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: 34 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.