CtrlK
BlogDocsLog inGet started
Tessl Logo

hig-components-menus

Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.

37

Quality

35%

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/skills/hig-components-menus/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%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 well-structured as an overview that points to a complete set of one-level-deep reference files, with concise principles and clear navigation. Its main weakness is actionability: the in-body guidance is abstract, leaning on the references for concrete detail, and the workflow is implied rather than explicitly sequenced.

Suggestions

Add a brief "Process" section that explicitly sequences the steps: check apple-design-context.md → ask the clarifying questions → consult the relevant reference file(s) → produce the Output Format.

Tighten each Key Principle with one concrete rule (e.g. name the standard button styles or the canonical menu ordering) so the body is actionable without always opening a reference.

Replace the vague "When to Use" line with the concrete trigger conditions (platforms, menu/button design tasks) that currently live only in the questions list.

DimensionReasoningScore

Conciseness

The body is mostly lean: one-line principles, a compact reference table, and short output/question lists, with only minor trimmable redundancy (the description directive is restated and the generic "When to Use" line adds little).

4 / 5

Actionability

Guidance is high-level HIG advice ("Use standard button styles", "Toolbars for frequent actions") with concrete specifics deferred to the reference files; as an instruction-only skill it has structure but lacks specific, directly-applicable rules in the body itself.

3 / 5

Workflow Clarity

A loose process is implied (consult context, ask the clarifying questions, produce the four-part Output Format) but it is not explicitly sequenced and has no validation checkpoints, though the skill is non-destructive so the destructive cap does not apply.

3 / 5

Progressive Disclosure

The body is a clear overview with a well-signaled Reference Index table linking one level deep to 11 real files in references/ (all listed paths exist), each with topic and key-content columns for easy navigation.

5 / 5

Total

15

/

20

Passed

Description

5%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 is a procedural meta-instruction about consulting a context file rather than a statement of the skill's purpose; it omits the domain (Apple HIG menus/buttons), trigger terms, and use-when guidance entirely. It reads as a behavioral directive that would not help a user discover or distinguish this skill.

Suggestions

Rewrite the description to state the capability first, e.g. "Recommends Apple HIG menu and button types (menus, toolbars, pop-up/pull-down buttons, disclosure controls) with platform-specific placement and shortcuts."

Add an explicit trigger clause: "Use when designing menus, toolbars, or buttons for iOS/iPadOS/macOS/visionOS, or when the user mentions HIG, menu bar, context menus, or toolbar layout."

Move the ".claude/apple-design-context.md" check instruction into the body's workflow rather than the frontmatter description, so the description stays a concise what+when statement.

DimensionReasoningScore

Specificity

The description names a concrete action ("Check for .claude/apple-design-context.md before asking questions") but never names the skill's actual domain (Apple HIG menus/buttons), so the actions relate to a meta-procedure rather than the skill's capability.

2 / 5

Completeness

It answers neither "what does this skill do" (the menus/buttons purpose is absent) nor "when should Claude use it" (no "Use when..." clause or trigger guidance), and the guideline caps completeness at 3 for missing triggers — here both are missing.

1 / 5

Trigger Term Quality

There are no natural trigger terms a user would say when needing menu/button design help (no "menus", "buttons", "HIG", "toolbar"); the only keyword is the technical file path ".claude/apple-design-context.md".

1 / 5

Distinctiveness Conflict Risk

The directive to check a context file and only ask uncovered questions is entirely generic and could apply to any context-file-driven skill, creating conflict with virtually any other skill.

1 / 5

Total

5

/

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.

Validation15 / 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
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.