swiftui-design

SwiftUI 前端设计 skill — anti AI-slop rules, design direction advisor, brand asset protocol, and five-dimension review. Works with Claude Code, Cursor, Codex, and OpenCode.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/swiftui-design/SKILL.md

Quality

Content

72%

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 lean, well-organized catalogue/pointer entry that defers the real workflow to an upstream repository. Conciseness and structure are strong, but actionability and workflow clarity suffer because no substantive, executable SwiftUI design guidance is actually present in the file.

Suggestions

Inline at least a minimal actionable quick-start (e.g., a short SwiftUI anti-slop checklist or a sample view snippet) so the skill is usable without leaving the file.

Make the install workflow concrete with exact paths/commands (e.g., the target skills directory and a copy/clone command) rather than directing the reader to inspect the upstream README.

Add an explicit validation step (e.g., 'After install, confirm the skill appears via <command>') so the multi-step install→invoke flow has a checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is short and unpadded, assuming Claude's competence without explaining concepts it already knows; the only minor redundancy is the verbatim repeat of the description under 'What it does', but overall every token earns its place.	3 / 3
Actionability	It offers one concrete command (`open https://github.com/wholiver/swiftui-design-skill`) and a clear invocation instruction, but the actual SwiftUI design guidance is entirely deferred to the upstream repo, so the executable guidance is incomplete for the skill's stated purpose.	2 / 3
Workflow Clarity	A loose sequence is implied (install the upstream bundle, then invoke by name or trigger phrase), but there are no explicit steps, exact install paths, or validation checkpoints, so the workflow is present but informal.	2 / 3
Progressive Disclosure	At under 50 lines with no local bundle files, the content is cleanly organized into well-signaled sections (What it does, Source, How to use) and points to one clearly labeled external upstream reference, satisfying the simple-skill allowance for a top score.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 domain-specific and names several components, but it reads as a feature list rather than concrete actions and lacks an explicit 'Use when...' trigger clause. It is competent but sits at the middle anchor across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger situations (e.g., 'Use when building SwiftUI views that risk generic AI-slop styling, choosing a design direction, or applying brand assets').

Replace feature-label phrasing with concrete actions (e.g., 'Reviews SwiftUI views across five dimensions, advises design direction, and applies brand color/typography assets') to lift specificity.

Fold one or two natural trigger variations (e.g., 'iOS design', 'native UI design') into the description so trigger coverage does not depend solely on the separate triggers block.

Dimension	Reasoning	Score
Specificity	The description names the domain ("SwiftUI 前端设计 skill") and lists component features ("anti AI-slop rules, design direction advisor, brand asset protocol, and five-dimension review"), but these are feature labels rather than multiple concrete actions, so it is not a comprehensive level-3 list.	2 / 3
Completeness	It clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance in the description, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	It includes some natural terms a user might say ("SwiftUI", "design", "anti AI-slop") but the description itself omits common variations like "iOS design" or "native UI" that appear only in the separate triggers block, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The SwiftUI-specific niche and anti-AI-slop framing make it reasonably distinct, but as a general design skill it could still overlap with other design-system skills, so it is not a clear level-3 niche.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/swiftui-design/SKILL.md
Commit: a2ba3ee

Reviewed: 4 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.