Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
60
70%
Does it follow best practices?
Impact
—
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 solid, concise description that clearly identifies its niche (Apple platform development via XcodeBuildMCP) 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 action list into more descriptive capability statements, 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 (XcodeBuildMCP, Apple platforms) and some actions but lacks detail on what each action entails. | 2 / 3 |
Completeness | Explicitly answers both 'what' (build, test, run, debug, log, UI automation for Apple platforms) and 'when' with a clear '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 (via XcodeBuildMCP). These cover the main platform and action keywords a developer would use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Xcode and Apple platform development with specific platform names and development actions. The mention of XcodeBuildMCP and five specific Apple platforms makes it highly distinctive and 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.
The skill provides a reasonable high-level guide for using XcodeBuildMCP tools with clear behavioral rules (e.g., don't chain build-only then build-and-run). However, it lacks concrete executable examples of tool calls, validation checkpoints in workflows, and deeper references for the many capabilities it lists. The capabilities enumeration is informational but adds token cost without proportional actionability.
Suggestions
Add concrete tool call examples with parameters and expected responses for the most common workflows (e.g., session_show_defaults → inspect output → build-and-run).
Include explicit validation checkpoints: what to verify after session_show_defaults, how to confirm a build succeeded before proceeding, and error recovery steps for common failures.
Trim the capabilities list to a brief summary or move it to a separate reference file, keeping only what's needed to guide tool selection decisions.
Add example snippets showing how to handle the 'tool not available' case, including the exact config.yaml change needed to enable a workflow.
| 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 content avoids explaining basic concepts. | 2 / 3 |
Actionability | The skill provides specific tool names (e.g., `session_show_defaults`, `discover_projs`) and behavioral rules, but lacks concrete executable examples—no actual tool call syntax, parameter examples, or expected output formats are shown. Guidance is directional rather than copy-paste ready. | 2 / 3 |
Workflow Clarity | Steps are numbered and sequenced, but there are no validation checkpoints or feedback loops. For example, Step 1 says to call `session_show_defaults` but doesn't specify what to check in the response or how to handle unexpected results beyond a vague 'use discover_projs' fallback. No error recovery patterns are defined. | 2 / 3 |
Progressive Disclosure | There is one external reference (the configuration docs URL), and the content is organized into sections. However, with no bundle files and no references to detailed guides for advanced workflows (debugging, UI automation, device workflows), the skill tries to cover many capabilities inline without pointing to deeper resources. | 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.
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.