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

48%

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

43%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 a lean, well-sectioned catalogue stub that cleanly signals its upstream source, but it contains almost none of the actual skill content — no rules, no design guidance, no review procedure — and no local bundle files exist to back the advertised capabilities. As a standalone SKILL.md it cannot guide the advertised SwiftUI design workflow beyond pointing at an external GitHub repository.

Suggestions

Bundle the upstream material locally (references/ for the anti-slop rules and review dimensions, scripts/ for any tooling) and reference those files by path from the body, so the skill functions without network access.

Replace the vague 'install the upstream bundle into your active agent's skills directory' with a concrete, executable install command and a numbered sequence (install → verify → invoke) with a verification checkpoint.

Inline a minimal quick-start (e.g., the five review dimensions and when to apply them) instead of repeating the frontmatter description verbatim in 'What it does'.

Dimension	Reasoning	Score
Conciseness	The body is short and free of padded explanation, but "What it does" repeats the frontmatter description verbatim and the meta commentary about the catalogue entry adds little, fitting anchor 4 ('Efficient; minor instances of over-explanation that could be trimmed') rather than anchor 5.	4 / 5
Actionability	The only executable command is `open https://github.com/wholiver/swiftui-design-skill`; the actual workflow (slop rules, design advisor, brand asset protocol, five-dimension review) is never specified, matching anchor 2 ('Minimal concrete guidance; high-level hints but missing the specific steps to execute').	2 / 5
Workflow Clarity	A rough prose sequence exists (open the repo, inspect the README, install the bundle, invoke by name or trigger), but the install step is undefined with no concrete command and there are no checkpoints, matching anchor 2 ('Rough sequence present but many gaps; steps poorly defined').	2 / 5
Progressive Disclosure	Sections are clearly organized (What it does / Source / How to use) and the upstream URL is clearly signaled, but the entire payload — rules, advisor, protocol, and review material that should live in bundled references/scripts — is absent locally and deferred to an external repo, fitting anchor 3's deficient content organization.	3 / 5
	Total	11 / 20 Passed

Description

53%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 enumerates its components, but the components are stated as feature labels rather than concrete actions, and there is no 'when to use' guidance. Adding an explicit 'Use when...' clause with natural trigger phrases would raise both completeness and trigger term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when building or restyling SwiftUI views, iOS app interfaces, or when the user mentions SwiftUI design, iOS UI, or AI-slop in Apple frontend code.'

Convert component labels into concrete actions, e.g. 'Applies anti AI-slop rules to SwiftUI code, advises design direction, loads brand assets, and reviews interfaces across five dimensions.'

Include natural trigger synonyms and variations users would actually say (SwiftUI views, iOS app UI, Apple design guidelines) rather than relying on the separate triggers frontmatter.

Dimension	Reasoning	Score
Specificity	The description names the domain ("SwiftUI 前端设计") and lists several components ("anti AI-slop rules, design direction advisor, brand asset protocol, and five-dimension review"), but these are feature labels rather than concrete actions the skill performs, matching anchor 3 rather than anchor 4's 'several specific actions'.	3 / 5
Completeness	There is a clear 'what' (the listed skill components) but no 'Use when...' clause or equivalent explicit trigger guidance — "Works with Claude Code, Cursor, Codex, and OpenCode" states agent compatibility, not when to use the skill — so completeness is capped at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"SwiftUI 前端设计" and "design" provide some relevant keywords users would say, but common variations and synonyms (e.g., iOS app UI, Swift UI, SwiftUI views, .swift) are missing, matching anchor 3 ('Some relevant keywords but missing common variations or synonyms').	3 / 5
Distinctiveness Conflict Risk	"SwiftUI" pins a distinct Apple-native niche with minimal conflict risk against non-SwiftUI skills, though generic phrases like "design direction advisor" leave minor overlap risk with broader design/web-design skills, matching anchor 4.	4 / 5
	Total	13 / 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: 1b47e60

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.