CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hig-patterns

Apple Human Interface Guidelines interaction and UX patterns.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hig-patterns/SKILL.md

The canonical home for this skill is hig-patterns in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured overview skill: excellent progressive disclosure (verified, one-level-deep reference index) and concrete, actionable pattern guidance with a useful goal-to-pattern selection table. Weakest on conciseness due to a redundant Key Principles summary that duplicates reference content, a meaningless boilerplate "When to Use" section, and an attribution footer.

Suggestions

Delete the boilerplate "When to Use" section ("This skill is applicable to execute the workflow or actions described in the overview") and the vendor attribution footer — neither adds guidance value.

Trim or cut the Key Principles section: most of its one-liners duplicate content in the reference files, so letting the reference index carry that detail would save tokens without losing information.

Add one short worked example (a user request → selected pattern → condensed output) to make the Output Format template concrete and executable.

DimensionReasoningScore

Conciseness

The body is mostly lean one-line principles, but the 8 Key Principles largely restate HIG guidance that is duplicated in the reference files, and it includes unnecessary padding: the vacuous "This skill is applicable to execute the workflow or actions described in the overview" boilerplate section and the vendor attribution footer. Matches anchor 3 (some unnecessary explanation that could be tightened), not 4.

3 / 5

Actionability

Concrete, actionable guidance throughout: "Three screens max", "Activity indicators for indeterminate waits, progress bars for determinate", and a Pattern Selection Guide mapping user goals to recommended patterns and anti-patterns. It is an instruction-only skill, so absence of code is not penalized; the minor gap is no worked example grounding the Output Format template. Anchor 4.

4 / 5

Workflow Clarity

A coherent implied workflow exists — check `.claude/apple-design-context.md` before asking, gather context via the 4 "Questions to Ask", then produce the structured 4-part Output Format — but it is scattered across sections rather than presented as one sequenced process, and no checkpoints are needed for this advisory, non-destructive skill. Anchor 4 (clear sequence, minor gaps), not 5 (no explicit end-to-end process walkthrough).

4 / 5

Progressive Disclosure

The body is a clear overview with a 26-entry reference index table giving topic and key content per file; all referenced paths were verified to exist, references are exactly one level deep with no nested pointers between reference files, plus Related Skills for further navigation. Matches anchor 5.

5 / 5

Total

16

/

20

Passed

Description

40%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 identifies a distinct niche (Apple HIG interaction and UX patterns) but is a domain label rather than a capability statement: no actions, no "Use when..." trigger clause, and missing common synonyms like "HIG" or "iOS design". It functions as a topic pointer, not a trigger-optimized description.

Suggestions

Rewrite as an action statement in third person, e.g., "Applies Apple Human Interface Guidelines interaction and UX patterns when designing or reviewing iOS, iPadOS, macOS, watchOS, or visionOS app flows."

Add an explicit "Use when..." clause with concrete trigger phrases users would naturally say: "Use when the user mentions HIG, Apple design guidelines, iOS/macOS UI patterns, modality, onboarding, drag and drop, or haptic feedback."

Include natural synonyms and platform names (HIG, Apple design, iOS design, SwiftUI/UIKit) to improve trigger-term coverage.

DimensionReasoningScore

Specificity

"Apple Human Interface Guidelines interaction and UX patterns" names the domain but contains no action verbs at all — it is a bare noun phrase like "Processes PDF files". It does not reach anchor 3, which requires 1-2 concrete actions (e.g., "applies HIG patterns" or "evaluates designs against HIG").

2 / 5

Completeness

There is no "Use when..." clause or equivalent trigger guidance, so the score is capped. The "what" is a domain label with no stated function (no verb describing what the skill does), matching anchor 2's "vague 'what' and no 'when'" rather than anchor 3, whose example lists concrete actions.

2 / 5

Trigger Term Quality

"Apple", "Human Interface Guidelines", and "UX" are natural terms users would say, but common variations are missing: "HIG" abbreviation, "iOS/macOS design", "SwiftUI/UIKit", "design guidelines". Some relevant keywords, missing common synonyms — matches anchor 3 rather than 4's "only a few natural terms missing".

3 / 5

Distinctiveness Conflict Risk

"Apple Human Interface Guidelines" carves a clear niche with minimal conflict risk against unrelated skills, matching anchor 4. Not anchor 5 because it lacks explicit trigger phrases and could still overlap with generic UX/design-guideline requests.

4 / 5

Total

11

/

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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hig-patterns/SKILL.md

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.