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 provides explicit trigger guidance. Its main weakness is that the capabilities are listed as a brief parenthetical rather than described as full concrete actions, which slightly reduces specificity. Overall it would perform well in skill selection among a large set of skills.
Suggestions
Expand the parenthetical actions into more descriptive capability phrases, e.g., 'Builds, tests, and runs Xcode projects; captures device logs; performs UI automation and debugging for iOS/macOS/watchOS/tvOS/visionOS apps.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists several actions (build, test, run, debug, log, UI automation) but they are parenthetical and terse rather than described as concrete capabilities. It names the domain and some actions but isn't comprehensive about what each action entails. | 2 / 3 |
Completeness | Explicitly answers both 'what' (XcodeBuildMCP CLI 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 clear. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: iOS, macOS, watchOS, tvOS, visionOS, build, test, run, debug, log, UI automation, and XcodeBuildMCP. These are terms users would naturally use when requesting Apple platform development tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific tool (XcodeBuildMCP CLI) and specific Apple platforms. Unlikely to conflict with generic coding or document skills; the platform names and Xcode reference create a clear niche. | 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 a help-first discovery pattern for the XcodeBuildMCP CLI. Its main weakness is the lack of concrete usage examples—while the discovery approach is sound, at least one complete executable example (e.g., building and running an iOS app on a simulator) would significantly improve actionability. The workflow also lacks validation/error-handling guidance for build operations.
Suggestions
Add at least one concrete, end-to-end example showing a real command invocation (e.g., `xcodebuildmcp build-and-run --project MyApp.xcodeproj --simulator 'iPhone 16'`) so Claude has a copy-paste-ready reference.
Add a brief error-handling/validation section: what does a failed build look like, how to interpret errors, and what recovery steps to take (e.g., check session defaults, clean build, re-run with verbose logging).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Xcode, simulators, or build systems are. Every section serves a clear purpose and there's no padding or unnecessary context. | 3 / 3 |
Actionability | Installation commands and help discovery commands are concrete and executable. However, the actual usage of the tool relies entirely on self-discovery via --help rather than providing any concrete workflow examples (e.g., a build-and-run command with real arguments). The 'Capability Overview' is a vague bullet list rather than actionable guidance. | 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 if a build fails, how to verify success, or feedback loops for common errors. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~50 lines), the content is well-organized into clear sections with logical progression. The help-first discovery approach effectively delegates detailed reference to the CLI itself, which is an appropriate form of progressive disclosure for a CLI wrapper tool. | 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.
200ac9c
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.