CtrlK
BlogDocsLog inGet started
Tessl Logo

hig-inputs

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

46

Quality

48%

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-inputs/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 well-organized overview of Apple HIG input principles with excellent progressive disclosure through a verified reference index. Its main weakness is workflow clarity: the design-output process lacks explicit validation or sequencing checkpoints.

DimensionReasoningScore

Conciseness

The 15 principles are tight one-line bullets that assume platform knowledge ('Tap to activate, swipe to scroll/navigate, pinch to zoom'); there is minimal padding, though the breadth of input types makes it longer than strictly necessary.

4 / 5

Actionability

For an instruction-only design skill it gives concrete directives ('On iPadOS, support both touch and pointer', 'Use keyboard-avoidance APIs', 'Map to extended gamepad profile') plus a defined Output Format, with only minor gaps in specificity.

4 / 5

Workflow Clarity

A light sequence exists (check context -> ask uncovered questions -> produce the four Output Format deliverables) but there are no explicit validation checkpoints; the 'Questions to Ask' and 'When to Use' sections are loosely ordered rather than a checked workflow.

3 / 5

Progressive Disclosure

A Reference Index table maps each input topic to a one-level-deep reference file with a key-content summary, and all 13 referenced files (gestures.md, keyboards.md, eyes.md, etc.) exist on disk, giving clear, well-signaled navigation.

5 / 5

Total

16

/

20

Passed

Description

25%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 mischaracterizes the skill as a question-asking process rather than Apple HIG input-method design guidance, omitting any capability statement or 'Use when' trigger. It is concrete in phrasing but fails to convey what the skill does or when to invoke it.

Suggestions

Rewrite the description to state the skill's actual capability, e.g. 'Provides Apple Human Interface Guidelines for input methods across platforms...'.

Add an explicit 'Use when...' clause with natural triggers like 'Apple HIG inputs', 'gestures', 'Apple Pencil', 'keyboard shortcuts', or 'visionOS eye interaction'.

Keep the 'check .claude/apple-design-context.md first' instruction in the body rather than occupying the description field.

DimensionReasoningScore

Specificity

The description states two concrete actions ('Check for .claude/apple-design-context.md', 'ask for information not already covered') but these describe a meta-process rather than the skill's actual input-design capabilities, leaving the real domain unnamed.

2 / 5

Completeness

It offers a vague and misplaced 'what' (a behavioral instruction) with no 'when' / 'Use when' clause; per the guideline, a missing explicit trigger caps completeness, and the what itself does not describe the skill's capability.

2 / 5

Trigger Term Quality

Only generic words like 'context', 'questions', and 'information' appear; none of the natural trigger phrases a user would say for this skill (e.g. 'Apple HIG inputs', 'gestures', 'keyboard shortcuts', 'Apple Pencil') are present.

2 / 5

Distinctiveness Conflict Risk

The 'check a context file before asking' framing is generic and would overlap with many skills; although the apple-design-context.md filename hints at the Apple niche, nothing distinguishes this from the sibling hig-* skills.

2 / 5

Total

8

/

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.