CtrlK
BlogDocsLog inGet started
Tessl Logo

anti-ui-slop

Stop coding agents from shipping generic UI. Use UIZZE's 800,000+ real web and iOS screens to build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate. Use for web or iOS UI design, implementation, redesign, critique, and pre-ship review in Codex, Claude Code, Cursor, Copilot, and other coding agents.

67

Quality

81%

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

78%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 compact, well-structured instruction-only skill: the five-step workflow is clearly sequenced with a finish-gate check, guidance is directive and specific, and external material is appropriately deferred to one-level-deep links. Its only real weakness is a small amount of promotional framing and a verification step that is conditional rather than an explicit validate-fix-retry loop.

Suggestions

Make the step-5 finish gate an explicit validate → fix → re-check loop (e.g., "render, fix breakage, render again until clean") rather than a conditional instruction, to close the workflow-clarity gap.

Trim the promotional framing ("free anti-ui-slop workflow", the three trailing links) to the single install command and canonical source, freeing tokens for the workflow itself.

Add one or two concrete before/after or state-coverage micro-examples in the Example section to make the guidance fully copy-paste actionable.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no explanations of concepts Claude already knows — but the "Canonical Package and More Examples" section with its three promotional links and the "free anti-ui-slop workflow" framing are tokens that could be trimmed, matching anchor 4's minor over-explanation rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Concrete, executable elements are present: a copy-paste install command (`npx skills add https://uizze.com --skill anti-ui-slop`), a worked example prompt, named MCP tools with usage limits, and specific directives like "Implement the required loading, empty, error, success, disabled, and permission states"; the five workflow steps remain directives rather than fully concrete operations, so it sits at anchor 4 rather than anchor 5's fully-executable coverage of common cases.

4 / 5

Workflow Clarity

The five numbered steps form a clear sequence (read context → reuse system → real content → states → render and check) with a finish gate in step 5 ("render the result and fix observable clipping... Run the project's relevant checks"), but the verification step is conditional ("When the environment supports it") and lacks an explicit fix-and-revalidate loop, matching anchor 4's minor validation gaps rather than anchor 5.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the skill is a short, single-purpose workflow under 50 lines, so per the simple-skill exception it scores on organization alone: clean, well-labeled sections (When to Use, How to Use, Example, Optional References, Canonical Package) with one-level-deep, clearly signaled external links — matching anchor 5's well-organized standard.

5 / 5

Total

17

/

20

Passed

Description

83%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 description that clearly states concrete capabilities and gives explicit, natural trigger guidance covering the full lifecycle (design, implementation, redesign, critique, pre-ship review). It is only a synonym or two short of fully comprehensive trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — "build product-specific interfaces", "define a design contract", "cover required states", "run a hard finish gate" — with only minor gaps; "hard finish gate" is slightly jargon-adjacent, keeping it below the comprehensive anchor 5 and well above anchor 3's 1-2 actions.

4 / 5

Completeness

Explicitly answers both what ("build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate") and when ("Use for web or iOS UI design, implementation, redesign, critique, and pre-ship review") with concrete trigger phrases, matching the anchor-5 example pattern exactly.

5 / 5

Trigger Term Quality

Good natural-phrase coverage: "web or iOS UI design, implementation, redesign, critique, and pre-ship review" plus agent names (Codex, Claude Code, Cursor, Copilot); common synonyms like "mockup", "wireframe", "frontend", or "dashboard" are missing, so it falls just under anchor 5 but clearly above anchor 3.

4 / 5

Distinctiveness Conflict Risk

A clear niche (product-specific UI in coding agents, backed by UIZZE's 800,000+ screens) with distinct triggers, but "UI design, implementation, redesign" is broad enough to overlap with general frontend/design skills — mostly distinct with minor overlap risk, matching anchor 4 rather than anchor 5's minimal-conflict bar.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
davepoon/buildwithclaude
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.