Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
79
70%
Does it follow best practices?
Impact
91%
1.97xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/xcodebuildmcp/SKILL.mdQuality
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) and provides explicit 'Use when' guidance with good trigger terms. Its main weakness is that the capability actions are listed as brief keywords in parentheses rather than described as concrete operations, which slightly reduces specificity. Overall it would perform well in skill selection among a large set of skills.
Suggestions
Expand the parenthetical action keywords into slightly more descriptive phrases, e.g., 'Build and run Xcode projects, execute test suites, stream device logs, perform UI automation' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists some actions in parenthetical form (build, test, run, debug, log, UI automation) but these are brief keywords rather than fully described concrete actions. It names the domain (Xcode/Apple platforms) and some actions but isn't comprehensive about what specifically the skill does with each. | 2 / 3 |
Completeness | Explicitly answers both 'what' (iOS/macOS/watchOS/tvOS/visionOS work including build, test, run, debug, log, UI automation) and 'when' ('Use when doing iOS/macOS/watchOS/tvOS/visionOS work'). The 'Use when' clause is explicitly present with clear trigger conditions. | 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 XcodeBuildMCP. These cover the major Apple platform keywords and common development actions users would mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of XcodeBuildMCP, specific Apple platform names (iOS, macOS, watchOS, tvOS, visionOS), and Xcode-specific actions creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable behavioral framework for using XcodeBuildMCP tools with clear sequencing and specific tool names, but falls short on actionability by lacking concrete examples (e.g., sample tool calls, example config YAML). The capabilities list is informative but somewhat verbose, and the workflow lacks explicit validation checkpoints for error recovery.
Suggestions
Add concrete example tool calls showing a typical workflow (e.g., `session_show_defaults` → `build_and_run_on_simulator` with sample parameters)
Include a minimal example of `.xcodebuildmcp/config.yaml` for enabling additional workflows instead of just linking to external docs
Add a validation/feedback loop in Step 2: e.g., 'After updating config.yaml, call session_show_defaults again to confirm the new workflows are active'
Trim the capabilities bullet list to focus on non-obvious behaviors and constraints rather than listing every feature category
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but the capabilities list is somewhat verbose and partially redundant with tool discovery. The bullet list of capabilities reads like marketing copy rather than actionable reference. However, it doesn't over-explain concepts Claude already knows. | 2 / 3 |
Actionability | Provides clear behavioral directives (e.g., 'Call session_show_defaults before the first build/run/test action') and names specific tools, but lacks concrete executable examples—no code snippets, no example tool calls, no sample config YAML. Guidance is specific but not copy-paste ready. | 2 / 3 |
Workflow Clarity | Steps are numbered and sequenced (establish context → understand tool availability → report context), but there are no validation checkpoints or feedback loops. Step 2 mentions checking enabled workflows but doesn't provide a concrete validation command or error-recovery sequence. The workflow for handling missing tools is vague ('check enabled workflows first'). | 2 / 3 |
Progressive Disclosure | References external configuration docs via URL, which is good, but the capabilities list is inlined when it could be a separate reference. The skill is reasonably short but the structure could better separate quick-start behavior from the full capabilities overview. Only one external reference is provided. | 2 / 3 |
Total | 8 / 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.