Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
87
81%
Does it follow best practices?
Impact
96%
3.42xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%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 is a solid, concise description that clearly identifies its niche (Apple platform development via XcodeBuildMCP CLI) and includes an explicit 'Use when' clause with good trigger terms. Its main weakness is that the capability list is somewhat abbreviated — the parenthetical shorthand (build, test, run, debug, log, UI automation) could be expanded into more descriptive action phrases to improve specificity.
Suggestions
Expand the parenthetical action list into more descriptive phrases, e.g., 'Builds Xcode projects, runs tests, launches simulators, captures device logs, and automates UI interactions.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Xcode/Apple platform development) and lists several actions (build, test, run, debug, log, UI automation), but these are presented as a parenthetical shorthand list rather than fully described concrete actions. It's more than vague but not as detailed as 'Extract text and tables from PDF files, fill forms, merge documents.' | 2 / 3 |
Completeness | The description explicitly answers both 'what' (XcodeBuildMCP CLI skill for build, test, run, debug, log, UI automation) and 'when' ('Use when doing iOS/macOS/watchOS/tvOS/visionOS work'). The 'Use when...' clause is present and explicit. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users would actually say: iOS, macOS, watchOS, tvOS, visionOS, build, test, run, debug, log, UI automation, and Xcode. These cover the major Apple platforms and common development actions comprehensively. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly distinctive — it targets a very specific tool (XcodeBuildMCP CLI) and a clear niche (Apple platform development). The combination of platform names and Xcode-specific terminology makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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, concise skill that effectively teaches Claude to use the XcodeBuildMCP CLI wrapper instead of raw xcodebuild commands. Its main weakness is that it relies heavily on `--help` discovery rather than providing concrete usage examples for common workflows, which reduces actionability. Adding a few representative command examples and error-handling guidance would significantly improve it.
Suggestions
Add 2-3 concrete executable examples of common workflows (e.g., `xcodebuildmcp build --project MyApp.xcodeproj --scheme MyApp --destination 'platform=iOS Simulator,name=iPhone 16'`) so Claude has copy-paste-ready patterns rather than relying entirely on --help discovery.
Add a brief error handling/validation section covering common failure modes (e.g., no simulators booted, scheme not found, build errors) with recovery steps to improve workflow clarity for the actual task execution phase.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Xcode, simulators, or CLI tools are. Every section serves a purpose and there's no padding or unnecessary context. The capability overview is a brief bullet list rather than verbose descriptions. | 3 / 3 |
Actionability | Installation commands and help discovery commands are concrete and copy-paste ready, but the actual usage guidance is abstract — it tells Claude to use `--help` discovery rather than providing concrete examples of common workflows (e.g., building a project, running on a simulator). The 'help-first discovery' approach delegates actionability to the CLI itself rather than providing executable examples. | 2 / 3 |
Workflow Clarity | The three-step sequence (verify CLI → discover commands → execute minimally) is clear, and the exit criteria section is a nice touch. However, there are no validation checkpoints for actual build/test/run operations — no guidance on what to do when builds fail, tests fail, or simulators aren't available. The workflow covers setup but not the actual task execution loop. | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines with no bundle files, the content is well-organized into clear sections with logical progression. The skill appropriately keeps everything in one file since there's no complex reference material that would benefit from splitting. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
a9305e8
Table of Contents
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.