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.

39

Quality

38%

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 ./skills/hig-inputs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

64%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 well-structured Apple HIG reference skill for input methods with excellent progressive disclosure through its reference index table. Its main weaknesses are the lack of concrete, executable guidance (no code examples for implementing the principles) and the absence of an explicit workflow with validation steps. The content is reasonably concise but could trim some descriptions that restate obvious platform behaviors.

Suggestions

Add concrete SwiftUI/UIKit code examples for at least the most common input patterns (e.g., gesture recognizer setup, keyboard shortcut registration, keyboard avoidance).

Define an explicit workflow sequence: e.g., 1) Check context file, 2) Identify target platforms, 3) Audit input methods against checklist, 4) Validate accessibility alternatives exist, 5) Produce output.

Remove the generic 'When to Use' section at the bottom, which adds no value.

DimensionReasoningScore

Conciseness

The content is fairly efficient, presenting principles as numbered rules without excessive explanation. Minor verbosity exists in some descriptions (e.g., listing out specific gesture types that Claude would already know), and the 'When to Use' section at the bottom is generic filler. The 'Questions to Ask' and 'Output Format' sections are lean and useful.

4 / 5

Actionability

The skill provides design guidance principles and output format expectations, but lacks concrete, executable examples. There are no code snippets, no specific API calls, no SwiftUI/UIKit examples for implementing gesture recognizers or keyboard shortcuts. The guidance is specific enough to be useful for design review but not copy-paste actionable for implementation.

3 / 5

Workflow Clarity

The skill is structured as a reference/checklist rather than a multi-step workflow. The implicit workflow is: check context file → ask questions → apply principles → produce output. The Output Format section defines deliverables, and the Questions section provides a discovery step, but there's no explicit sequencing, validation, or feedback loop for the design review process.

3 / 5

Progressive Disclosure

Excellent progressive disclosure with a clear overview of 15 principles in the main file and a well-organized Reference Index table pointing to 13 separate reference files, each clearly labeled by topic with key content descriptions. References are one level deep and clearly signaled with a navigable table format.

5 / 5

Total

15

/

20

Passed

Description

11%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.

This description fails as a skill description because it reads as an internal behavioral instruction rather than describing what the skill does or when it should be selected. It provides no information about the skill's capabilities, domain, or use cases, making it nearly impossible for Claude to correctly select this skill from a list of alternatives.

Suggestions

Add a clear 'what' clause describing the skill's actual purpose, e.g., 'Provides Apple Human Interface Guidelines and design patterns for building iOS/macOS applications.'

Add a 'Use when...' clause with natural trigger terms like 'Apple design', 'iOS UI', 'macOS interface', 'HIG', 'SwiftUI layout', etc.

Move the file-checking instruction into the skill body rather than the description, as it is an implementation detail, not a selection criterion.

DimensionReasoningScore

Specificity

The description contains no concrete actions or capabilities. It only describes a procedural instruction about checking a file and avoiding redundant questions, with no indication of what the skill actually does.

1 / 5

Completeness

Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an internal behavioral instruction without explaining the skill's purpose or trigger conditions.

1 / 5

Trigger Term Quality

The only potentially useful trigger terms are 'apple-design-context' and the file path, but these are internal references rather than natural user language. A user would never say 'check for .claude/apple-design-context.md'.

2 / 5

Distinctiveness Conflict Risk

While the specific file path '.claude/apple-design-context.md' is unique, the description is so vague about what the skill does that it could overlap with any Apple-related or design-related skill. The lack of defined purpose creates ambiguity.

2 / 5

Total

6

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

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.