ios-simulator-skill

21 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./config/claude/skills/ios-simulator-skill/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable quick-start commands and a clear workflow, but full-flag verbosity, missing validation checkpoints around destructive/batch operations, and broken documentation references limit its top-end scores.

Suggestions

Add explicit validation/feedback-loop checkpoints to the workflow for destructive and batch operations (e.g., confirm UDID and verify state before simctl_delete/simctl_erase, verify shutdown before re-boot).

Fix or remove the dead Documentation links — either create README.md, CLAUDE.md, references/, and examples/ or drop those entries so navigation targets are real.

Move the per-script option-flag lists into a concise reference and keep SKILL.md to a tighter overview to improve conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference material with no concept over-explanation, but full option-flag dumps for all 21 scripts and the partly redundant 'Key Design Principles' section could be tightened.	2 / 3
Actionability	Quick Start gives fully executable, copy-paste-ready commands (e.g., 'python scripts/app_launcher.py --launch com.example.app') and each script lists concrete flags; referenced script paths are real files.	3 / 3
Workflow Clarity	The 'Typical Workflow' is a clear 6-step sequence, but the skill covers destructive/batch operations (simctl_delete, simctl_erase, privacy grant/revoke, --all) without explicit validation/feedback-loop checkpoints, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well organized with one-level-deep script references, but the 'Documentation' section cites README.md, CLAUDE.md, references/, and examples/ — none of which exist in the bundle — creating dead navigation links.	2 / 3
	Total	9 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 specific and occupies a clear, distinctive niche, but lacks explicit "when to use" trigger guidance and leans on internal/meta phrasing over natural user keywords.

Suggestions

Add an explicit 'Use when ...' clause naming natural triggers (e.g., 'Use when testing or building iOS apps in the Simulator, running UI/accessibility checks, or automating Xcode simulator workflows').

Replace meta phrasing like 'Optimized for AI agents with minimal token output' with concrete user-facing keywords (Xcode, Simulator, UI tests, tap/swipe interactions).

Lead with the trigger terms users actually say before listing internal capability categories.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete capabilities — "semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management" — matching the score-3 anchor of listing several specific actions.	3 / 3
Completeness	Clearly answers "what" with a capability list, but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Has natural terms users might say ("iOS app testing", "simulator"), but leans toward internal framing ("semantic UI navigation", "simulator lifecycle management", "Optimized for AI agents") and misses common variations like "Xcode", "UI test", or "tap".	2 / 3
Distinctiveness Conflict Risk	iOS simulator testing/building is a clear, narrow niche with distinct triggers unlikely to overlap with generic skills, matching the score-3 anchor.	3 / 3
	Total	10 / 12 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: freekmurze/dotfiles
Path: config/claude/skills/ios-simulator-skill/SKILL.md
Commit: 54dfd87

Reviewed: about 20 hours 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.