Name: hig-components-controls
Rating: 41.6 (1 reviews)
Author: administrakt0r

hig-components-controls

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

Quality

41%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/hig-components-controls/SKILL.md

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

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 a well-structured advisory skill: clear control-selection heuristics, a defined output shape, and an excellent one-level reference index. Its main weaknesses are mild over-explanation of HIG basics and a generic 'When to Use' section that adds no workflow clarity.

Suggestions

Trim rationale sentences that restate HIG fundamentals Claude already knows (e.g., the consistency/accessibility justification in principle 2) to keep only decision-relevant guidance.

Replace the generic 'When to Use' section with concrete trigger conditions for this skill specifically.

Add an explicit selection workflow, e.g. answer the four 'Questions to Ask' -> map data type/option count/platform to a control -> output the 4-part recommendation, to lift workflow clarity above a rough sequence.

Dimension	Reasoning	Score
Conciseness	The numbered principles are organized as tight bullets, but several restate HIG knowledge Claude already has ('Built-in controls provide consistency and accessibility') and the closing 'When to Use' line is generic filler ('applicable to execute the workflow or actions described in the overview').	3 / 5
Actionability	Concrete decision heuristics ('Segmented controls for 2-5 items', 'Sliders for continuous values', keyboard types email/URL/number) plus a defined 4-part Output Format and an elicitation question list give mostly executable guidance for an instruction-only skill.	4 / 5
Workflow Clarity	A rough sequence exists (Questions to Ask -> recommend control per Output Format) but there are no explicit checkpoints or validation steps; the generic 'When to Use' section does not clarify the process.	3 / 5
Progressive Disclosure	The body is a concise overview and the Reference Index table signals 14 real one-level-deep reference files (all present in references/) with topic and key-content columns, making navigation easy.	5 / 5
	Total	15 / 20 Passed

Description

17%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 describes an internal process behavior rather than the skill's capability or trigger conditions, so it does not communicate what the skill does or when to use it. It is essentially indistinguishable from any context-gathering skill.

Suggestions

Rewrite the description to state the capability in third person, e.g. 'Recommends Apple HIG selection and input controls (toggles, segmented controls, sliders, pickers, steppers, text fields, combo boxes, token fields) with state, validation, and accessibility guidance.'

Add an explicit 'Use when...' clause with natural trigger terms users would say: 'Use when choosing iOS/macOS input controls, designing forms, or selecting between toggles, segmented controls, sliders, and pickers.'

Remove the context-file housekeeping instruction from the description; it belongs in the body, not the trigger surface.

Dimension	Reasoning	Score
Specificity	The phrase 'Check for .claude/apple-design-context.md before asking questions' names a concrete process action but never states the skill's actual domain (Apple HIG selection/input controls); actions are minimal and not about the skill's capability.	2 / 5
Completeness	It offers a vague 'what' (check a context file, ask only uncovered questions) and no 'when' / 'Use when...' clause, so it fails to explain when Claude should invoke the skill.	2 / 5
Trigger Term Quality	It contains only technical jargon ('apple-design-context.md') and generic process language ('ask for information'); there are no natural keywords a user would say when they need HIG control recommendations.	1 / 5
Distinctiveness Conflict Risk	The 'check for a context file before asking questions' pattern is generic and would overlap with any context-file-driven skill, with no signal that ties it to HIG controls.	2 / 5
	Total	7 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/hig-components-controls/SKILL.md
Commit: 57c135b

Reviewed: 4 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.