ios-debugger-agent
Use XcodeBuildMCP to build, run, launch, and debug the current iOS project on a booted simulator. Trigger when asked to run an iOS app, interact with the simulator UI, inspect on-screen state, capture logs/console output, or diagnose runtime behavior using XcodeBuildMCP tools.
Install with Tessl CLI
npx tessl i github:Dimillian/Skills --skill ios-debugger-agent95
Does it follow best practices?
Validation for skill structure
Discovery
100%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 well-crafted skill description that excels across all dimensions. It clearly specifies concrete actions (build, run, debug), includes natural trigger terms iOS developers would use, explicitly states both what the skill does and when to use it, and has a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'build, run, launch, and debug' iOS projects, 'interact with the simulator UI', 'inspect on-screen state', 'capture logs/console output', 'diagnose runtime behavior'. | 3 / 3 |
Completeness | Clearly answers both what ('build, run, launch, and debug iOS project on simulator') AND when ('Trigger when asked to run an iOS app, interact with the simulator UI, inspect on-screen state, capture logs/console output, or diagnose runtime behavior'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'run an iOS app', 'simulator', 'logs', 'console output', 'debug', 'runtime behavior'. These are terms developers naturally use when working with iOS development. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific niche: iOS development, Xcode, simulator, XcodeBuildMCP tools. The combination of iOS-specific terminology and the named tool (XcodeBuildMCP) makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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, actionable skill that efficiently guides Claude through iOS simulator debugging workflows. The content is appropriately concise and provides specific tool names with parameters. The main weakness is the lack of explicit validation steps after build/launch operations to confirm success before proceeding.
Suggestions
Add explicit validation after build_run_sim (e.g., 'Verify app launched by calling describe_ui or screenshot before proceeding')
Include a feedback loop for build failures: check error output, suggest specific fixes, then retry with validation
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude's competence with Xcode and iOS development. No unnecessary explanations of what simulators are or how MCP works—just direct instructions. | 3 / 3 |
Actionability | Provides specific MCP tool names with exact parameters (e.g., `projectPath`, `scheme`, `simulatorId`). Each step names the concrete tool to call and what arguments to pass. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (1-3) with logical flow, but lacks explicit validation checkpoints. No feedback loop for build failures beyond 'ask whether to retry'—missing verification that the app actually launched successfully. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections (Core Workflow, UI Interaction, Logs, Troubleshooting). Content is appropriately sized for a single file with no need for external references. Easy to navigate. | 3 / 3 |
Total | 11 / 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.
- Reviewed
Table of Contents
Is this your skill?
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.