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

52%

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

46%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.

This is a catalogue/advertisement entry pointing to an upstream bundle rather than a self-contained executable skill, so the body offers little concrete, copy-paste guidance for the skill's actual function. Structure and brevity are acceptable, but actionability is the weakest dimension.

Suggestions

Replace the external-pointer hand-off with concrete first-run guidance (exact install path/command and a minimal invocation example) so the skill is actionable without reading the upstream README.

Remove the verbatim duplication of the frontmatter description and upstream URL from the body to tighten token efficiency.

Add an explicit verify step (e.g. confirm the upstream skill is installed and resolves by name) after the install instruction to give the workflow a checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is reasonably lean, but the 'What it does' section repeats the frontmatter description verbatim and the 'Source' section restates the upstream URL, so there is some unnecessary redundancy that could be tightened.	3 / 5
Actionability	The only concrete commands are `open https://github.com/...` and 'ask the agent to invoke this skill by name'; the skill's actual capabilities (anti-slop rules, review) are described rather than instructed, with execution deferred to an external repo README.	2 / 5
Workflow Clarity	A rough sequence exists (install the upstream bundle, then invoke by name or trigger), but the install step is hand-wavy ('Inspect the upstream README for exact paths') and there are no validation checkpoints.	3 / 5
Progressive Disclosure	The body is a short, well-sectioned overview (What it does / Source / How to use) with one clearly signaled external reference; no bundle files exist, and the structure is easy to navigate, with only minor organization gaps.	4 / 5
	Total	12 / 20 Passed

Description

58%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 names a distinct niche and several capability areas but is missing an explicit 'when to use' clause and keeps its best trigger terms in the frontmatter rather than the description body. Specificity and distinctiveness are strong; completeness and trigger-term coverage are the limiting dimensions.

Suggestions

Add an explicit 'Use when ...' clause naming concrete trigger scenarios (e.g. building SwiftUI views, applying brand assets, reviewing UI for AI-slop).

Surface natural user phrases and synonyms directly in the description (e.g. 'SwiftUI views', 'iOS UI design', 'native Apple UI') instead of relying on the frontmatter triggers list.

Clarify what the 'five-dimension review' covers so the named capability is concrete rather than abstract jargon.

Dimension	Reasoning	Score
Specificity	Names the SwiftUI design domain and lists several concrete capability areas ('anti AI-slop rules', 'design direction advisor', 'brand asset protocol', 'five-dimension review'), though terms like 'AI-slop' and 'five-dimension review' are somewhat abstract without defining the dimensions.	4 / 5
Completeness	The 'what' is clear, but there is no 'Use when...' clause or equivalent explicit trigger guidance inside the description, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	The description text surfaces 'SwiftUI' and 'design' but few natural user phrases; the richer trigger set lives in the frontmatter rather than the description string, so common variations/synonyms are underrepresented in the description itself.	3 / 5
Distinctiveness Conflict Risk	'SwiftUI 前端设计' is a clearly distinct niche with specific triggers like 'apple frontend' and 'swiftui slop', leaving only minor overlap risk with general design skills.	4 / 5
	Total	14 / 20 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: d4138ea

Reviewed: 3 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.