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.

68

Quality

83%

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

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.

The body is well-organized, operationally dense, and gives concrete commands with a clear sequenced workflow and validation principle. Its main weakness is progressive disclosure: it defers heavily to a reference/ directory that is absent from the bundle, leaving most per-command detail and several mandatory pre-edit reads pointing at missing files.

Suggestions

Ship the referenced reference/*.md files (new-work.md, craft-floor.md, and the ~24 Commands-table targets) or remove/inline the dead links, so the body's navigation resolves against the actual bundle — this is the lowest-scoring dimension.

Add one concrete, copy-paste example for the common case (e.g. `impeccable context` → edit → bounded-verify sequence) in the body so it stays executable when the per-command references are unavailable.

Replace the abstract "bounded passes" validation principle with a concrete verify step or command, since the per-command validation detail currently lives only in the missing references.

DimensionReasoningScore

Conciseness

Dense and operational throughout — it assumes Claude's competence and never pads with basics Claude already knows — but several run-on sentences (Setup step 1's base-dir/Windows fallback, the routing bullets) pack edge-case detail that could be tightened, so it is efficient rather than maximally lean.

4 / 5

Actionability

Gives concrete, executable commands ("scripts/impeccable context", ".kiro/skills/impeccable/scripts/impeccable pin <pin|unpin> <command>", "/impeccable hooks <on|off|status|...>") and a full syntax table, but the per-command executable detail and common-case examples live in reference files rather than the body, leaving minor gaps.

4 / 5

Workflow Clarity

Setup is a clear 3-step sequence with a launcher-failure fallback, and validation checkpoints exist (the bounded "inspect once → fix in one batch → confirm once → stop" rule, doctor, CONTEXT_STALE reporting); it stops short of 5 because the validation is stated as an abstract principle rather than a concrete per-edit verify step.

4 / 5

Progressive Disclosure

The body is well-structured with clearly signaled one-level-deep references (Setup links, the 24-row Commands table, reference/craft-floor.md), but scored against the actual bundle those referenced paths do not exist — no reference/ directory ships, so navigation leads to ~25 dead links, which breaks the "easy navigation" the higher anchors require.

3 / 5

Total

15

/

20

Passed

Description

96%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 description with a clear "Use when" trigger, comprehensive concrete action verbs, and a useful negative boundary. Its only weakness is that the covered surface is so wide that it is mostly-distinct rather than tightly niched.

DimensionReasoningScore

Specificity

Lists many concrete action verbs — "design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract" — each tied to a real command, giving comprehensive coverage of concrete actions rather than vague language.

5 / 5

Completeness

Explicitly answers both: what ("improve a frontend interface", with enumerated surfaces and handled concerns) and when ("Use when the user wants to...", "Also use for..."), plus a negative boundary ("Not for backend-only or non-UI tasks").

5 / 5

Trigger Term Quality

Natural user-facing phrases abound ("design", "polish", "critique", "make it bolder", "loud designs that should become quieter", "live browser iteration"), with synonym coverage across the refine/enhance verbs a user would actually say.

5 / 5

Distinctiveness Conflict Risk

The "frontend interface" niche and the "Not for backend-only or non-UI tasks" exclusion make it mostly distinct, but the scope is extremely broad (all frontend design) so it carries minor overlap risk with general web-dev or styling skills rather than the tight, minimal-conflict niche of the 5 anchor.

4 / 5

Total

19

/

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.