Diagnose data races, convert callback-based code to async/await, implement actor isolation patterns, resolve Sendable conformance issues, and guide Swift 6 migration. Use when developers mention: (1) Swift Concurrency, async/await, actors, or tasks, (2) "use Swift Concurrency" or "modern concurrency patterns", (3) migrating to Swift 6, (4) data races or thread safety issues, (5) refactoring closures to async/await, (6) @MainActor, Sendable, or actor isolation, (7) concurrent code architecture or performance optimization, (8) concurrency-related linter warnings (SwiftLint or similar; e.g. async_without_await, Sendable/actor isolation/MainActor lint).
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 an excellent skill description that clearly articulates specific capabilities, provides comprehensive trigger terms covering natural developer language, and explicitly separates 'what' from 'when'. The numbered trigger list is thorough and covers both common and edge-case scenarios (like linter warnings), making it highly effective for skill selection among many options.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: diagnose data races, convert callback-based code to async/await, implement actor isolation patterns, resolve Sendable conformance issues, and guide Swift 6 migration. | 3 / 3 |
Completeness | Clearly answers both 'what does this do' (diagnose data races, convert callbacks, implement actor isolation, resolve Sendable issues, guide Swift 6 migration) AND 'when should Claude use it' with an explicit numbered 'Use when...' clause covering 8 distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Swift Concurrency', 'async/await', 'actors', 'data races', 'thread safety', 'Swift 6', '@MainActor', 'Sendable', 'actor isolation', 'closures to async/await', and even linter-specific terms like 'async_without_await'. These are terms developers would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on Swift Concurrency patterns and Swift 6 migration. The triggers are domain-specific enough (actors, Sendable, @MainActor, async/await in Swift context) that they are unlikely to conflict with general coding skills or other language-specific skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that provides actionable, well-structured guidance for Swift Concurrency issues. Its strengths are the diagnostic table mapping errors to fixes, the clear migration validation loop with explicit checkpoints, and the well-organized reference router. The only notable weakness is minor verbosity in some sections that could be tightened without losing clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and avoids explaining basic concepts Claude already knows, but some sections are somewhat verbose — e.g., the 'Concurrency Tool Selection' table repeats guidance that's fairly obvious to Claude, and the Swift 6 migration section restates well-known changes. The guardrails and diagnostic table earn their tokens, but overall it could be tightened. | 2 / 3 |
Actionability | The skill provides concrete, executable code examples (network request with UI update, task group processing), specific diagnostic-to-fix mappings, exact build settings to check with their SwiftPM/Xcode equivalents, and clear decision criteria for Quick Fix Mode. The guidance is highly specific and copy-paste ready. | 3 / 3 |
Workflow Clarity | The Migration Validation Loop provides an explicit numbered sequence with validation checkpoints (build → fix → rebuild → test → only proceed when clean). The Fast Path section establishes a clear diagnostic workflow. The 'When Quick Fixes Fail' section provides an escalation path. Feedback loops are explicitly present for destructive/batch migration operations. | 3 / 3 |
Progressive Disclosure | The Reference Router section is excellently organized with clear one-level-deep references to specific topic files, grouped by category (Foundations, Streams, Applied topics, Migration/tooling, Glossary). The main skill serves as a concise overview with actionable quick-reference content, deferring detailed material to well-signaled reference files. | 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.
eba0d55
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.