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.
75
70%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./config/claude/skills/ios-simulator-skill/SKILL.mdQuality
Discovery
67%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 strong in specificity and distinctiveness, clearly identifying a niche around iOS app testing and automation with concrete capabilities listed. Its main weaknesses are the lack of an explicit 'Use when...' clause and missing some natural trigger terms users might use (e.g., 'Xcode', 'iPhone', 'Swift'). The phrase 'Optimized for AI agents with minimal token output' describes an implementation detail rather than helping with skill selection.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to test, build, or automate iOS apps, manage simulators, or run accessibility checks.'
Include additional natural trigger terms users would say, such as 'Xcode', 'iPhone', 'iPad', 'Swift', 'xcodebuild', '.ipa', or 'App Store submission'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management.' Also mentions '21 production-ready scripts' and 'iOS app testing, building, and automation,' which are concrete and specific. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the domain (iOS app development). Per rubric guidelines, missing 'Use when...' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'iOS', 'testing', 'building', 'automation', 'simulator', 'accessibility testing', and 'UI navigation.' However, it misses common user-facing variations like 'Xcode', 'iPhone', 'iPad', 'xcrun', 'xcodebuild', '.ipa', 'App Store', or 'Swift' that users would naturally mention. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of iOS-specific terminology, simulator management, semantic UI navigation, and the mention of '21 production-ready scripts' creates a very distinct niche. Unlikely to conflict with other skills given the specificity to iOS app development tooling and AI agent optimization. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
72%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 skill that provides actionable, executable commands and good progressive disclosure through external references and --help flags. Its main weaknesses are verbosity in the script catalog (listing every sub-feature for all 21 scripts) and missing validation/error-recovery steps in workflows, especially for destructive operations like device deletion and erasure.
Suggestions
Condense the 21-script catalog to a brief table (script name, one-line description, key flags) and let --help handle the details—this would significantly reduce token usage.
Add explicit validation checkpoints and error recovery steps to the Typical Workflow, especially after build/interaction steps (e.g., 'If screen_mapper shows unexpected state, capture debug snapshot before proceeding').
Remove the 'Key Design Principles' section or reduce it to a single line—these are implementation details Claude doesn't need to follow the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary content. The detailed enumeration of all 21 scripts with their sub-features is verbose—Claude could discover options via --help. The 'Key Design Principles' section explains concepts Claude already understands. However, the quick start and common patterns sections are lean. | 2 / 3 |
Actionability | The quick start provides fully executable, copy-paste-ready commands. Each script lists concrete CLI options with flags. The typical workflow gives specific commands that can be run immediately without modification (aside from bundle IDs). | 3 / 3 |
Workflow Clarity | The 'Typical Workflow' section provides a clear sequence of steps, but lacks validation checkpoints and error recovery. For destructive operations like simctl_delete and simctl_erase, there are no explicit feedback loops or verification steps documented in the workflow. The safety confirmation mention for delete is good but insufficient for a complete workflow. | 2 / 3 |
Progressive Disclosure | The skill has a clear quick start, then progressively reveals detail through script categories. It references external documentation (README.md, CLAUDE.md, references/, examples/) with clear one-level-deep navigation. All scripts support --help for deeper discovery. | 3 / 3 |
Total | 10 / 12 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- freekmurze/dotfiles
- Commit
05d40bb
- 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.