Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
76
70%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 reasonably effective skill description that clearly identifies its niche (Apple platform development via Xcode) and includes an explicit 'Use when' clause with good trigger terms. Its main weakness is that the capability descriptions are terse keyword lists rather than fully articulated actions, which slightly reduces specificity. Overall it would perform well in skill selection scenarios.
Suggestions
Expand the action keywords into slightly more descriptive phrases, e.g., 'Build and compile Xcode projects, run tests, launch simulators, inspect debug logs, and automate UI interactions' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Apple platform development) and lists some actions (build, test, run, debug, log, UI automation), but these are brief keywords rather than fully described concrete actions. It doesn't explain what the tool specifically does with these actions. | 2 / 3 |
Completeness | The description answers both 'what' (XcodeBuildMCP for building, testing, running, debugging, logging, UI automation) and 'when' with an explicit 'Use when' clause specifying the trigger conditions (iOS/macOS/watchOS/tvOS/visionOS work). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: iOS, macOS, watchOS, tvOS, visionOS, build, test, run, debug, log, UI automation, and Xcode. These cover the major platform names and common development actions users would mention. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Apple platform development via Xcode, which is a distinct niche. The combination of platform names (iOS, macOS, etc.) and XcodeBuildMCP makes it very 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 solid structural overview of XcodeBuildMCP with clear behavioral rules (e.g., don't run discovery speculatively, prefer combined build-and-run). However, it lacks concrete examples of tool invocations with parameters and expected outputs, which limits actionability. The workflow steps would benefit from explicit validation checkpoints, especially around build failures and session context verification.
Suggestions
Add concrete tool call examples with parameters and expected outputs (e.g., show a sample `session_show_defaults` call and its response, then a build-and-run call).
Add explicit validation checkpoints in the workflow—e.g., 'After calling session_show_defaults, verify that project, scheme, and simulator are all populated before proceeding to build.'
Include a brief error-handling feedback loop: 'If build fails → read error output → fix issue → rebuild' with specific tool calls for each step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The capabilities list is somewhat verbose and could be tightened—Claude doesn't need a full feature catalog to use MCP tools. However, the step-by-step instructions are reasonably lean and the overall content isn't padded with explanations of basic concepts. | 2 / 3 |
Actionability | The skill provides specific tool names (e.g., `session_show_defaults`, `discover_projs`) and clear behavioral rules, but lacks concrete executable examples—no sample tool calls, no example parameters, no expected outputs. It tells Claude what to do conceptually but not with copy-paste specificity. | 2 / 3 |
Workflow Clarity | Steps 1-3 provide a reasonable sequence, but there are no validation checkpoints or feedback loops. For example, after setting session defaults or building, there's no explicit 'verify success before proceeding' step. The workflow for handling missing tools (Step 2) mentions checking config but doesn't provide a clear validate-fix-retry loop. | 2 / 3 |
Progressive Disclosure | The skill references an external URL for configuration docs, which is appropriate, but there are no bundle files for deeper reference material. The capabilities list is inline and could benefit from being split out if it were longer. For a standalone skill with no bundle, the structure is acceptable but not exemplary. | 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.
1d9bfc0
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.