Name: bencium-impact-designer
Rating: 51.2 (1 reviews)
Author: bencium

bencium-impact-designer

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics. Based on Anthropic's Frontend Designer Skill

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

47%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body has a strong, well-sequenced design workflow with explicit validation and checklists, and includes some real executable tooling examples. Its main weaknesses are severe verbosity from restating generic design knowledge, and a monolithic structure whose referenced progressive-disclosure files are missing with their content inlined instead.

Suggestions

Cut generic design-knowledge sections Claude already knows (UX principles, accessibility basics, color/typography theory) and remove duplicated prohibition lists and the oversized tone-options list to recover the token budget.

Actually create the referenced bundle files (ACCESSIBILITY.md, MOTION-SPEC.md, RESPONSIVE-DESIGN.md) and move the corresponding inline content into them so the progressive-disclosure pointers resolve instead of dangling.

Replace abstract design-direction prose with more concrete, copy-paste-ready code and templates so guidance is uniformly actionable.

Dimension	Reasoning	Score
Conciseness	The ~983-line body is verbose and explains concepts Claude already knows (typography and color theory, UX principles like direct manipulation/feedback/forgiveness, WCAG accessibility basics), and is padded with repetition such as the "NEVER use these fonts/colors" list stated three times and a 50+ item tone-options list, matching the level-1 anchor.	1 / 3
Actionability	It provides real executable guidance (shadcn/phosphor/sonner imports, Tailwind responsive classes, CSS clamp, a rem typographic scale, box-shadow examples), but this is mixed with substantial abstract design-direction prose, so it is not uniformly copy-paste-ready as required for level 3.	2 / 3
Workflow Clarity	It gives a clear sequence (Design Thinking Protocol, then Design Workflow: understand context → explore options → implement iteratively → validate) with an explicit validate step (playwright MCP, test at each stage, verify accessibility) plus multiple checklists (Design Decision Checklist, Testing Checklist, rule-breaking checklist), matching the level-3 anchor.	3 / 3
Progressive Disclosure	It has section structure and a signaled References section listing ACCESSIBILITY.md, MOTION-SPEC.md, and RESPONSIVE-DESIGN.md, but those referenced files do not exist in the bundle and the corresponding accessibility/responsive/motion content is inline in this monolithic file, fitting the level-2 "content that should be separate is inline" anchor.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 well-formed with an explicit "Use this skill when..." trigger giving strong completeness, and it uses correct third-person voice. It is held back by somewhat overlapping/vague actions and a broad trigger that risks overlapping with general web-dev skills.

Suggestions

Add more granular, distinct concrete actions to raise specificity (e.g., "design landing pages, dashboards, marketing sites, and component libraries") instead of the overlapping "build components, pages, or applications".

Broaden trigger terms to natural phrasings users actually say, such as "design a UI", "make a landing page/website", "redesign a page", or "create a dashboard".

Sharpen distinctiveness by narrowing or qualifying the trigger so it clearly targets distinctive aesthetic design rather than generic web development.

Dimension	Reasoning	Score
Specificity	It names the frontend domain and several actions ("Create...frontend interfaces", "build web components, pages, or applications", "Generates creative, polished code"), but the actions largely overlap and are padded with vague adjectives like "production-grade" and "high design quality", so it is not the comprehensive, granular action list of level 3.	2 / 3
Completeness	It clearly answers both what ("Create distinctive, production-grade frontend interfaces...") and when via the explicit trigger "Use this skill when the user asks to build web components, pages, or applications.", matching the level-3 anchor.	3 / 3
Trigger Term Quality	It includes relevant terms users say ("frontend", "web components, pages, or applications"), but misses common natural variations such as "design a UI", "landing page", "website", or "dashboard", keeping it below the broad coverage of level 3.	2 / 3
Distinctiveness Conflict Risk	The anti-generic-aesthetic niche gives some distinctiveness, but the trigger "build web components, pages, or applications" is broad and would overlap with general web-development or coding skills, so it is not the clear, conflict-free niche of level 3.	2 / 3
	Total	9 / 12 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
skill_md_line_count	SKILL.md is long (989 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: bencium/bencium-marketplace
Commit: 9db3236

Reviewed: 5 days 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.