菜单
Benchmarking and performance auditing for the Wax repo. Use when running or interpreting Wax benchmarks, diagnosing CPU, memory, or I/O bottlenecks, or investigating Swift 6.2 concurrency issues such as Sendable, actor isolation, `@unchecked Sendable`, task-group fan-out, and data races.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/christopherkarani/Wax --skill wax-performance-audit命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Swift framework guidance for Wax on-device memory/RAG. Use when writing Swift code with the public Memory facade, embedding providers, retrieval modes, or hybrid search. For agent operators using the Wax MCP server tools, use the separate wax-mcp skill instead.
Maintain the Wax memory store used by the Hermes wax-memory provider.
Operator playbook for the Wax MCP memory server. Use whenever Wax MCP tools are available (remember, recall, search, handoff, session_start/end, structured memory), when installing or configuring waxmcp, or when an agent should keep durable cross-session memory. Prefer this skill over the Swift framework skill unless the task is writing Wax Swift code.
正在显示 SKILL.md
基于 SOC 职业分类
| name | wax-performance-audit |
| description | Benchmarking and performance auditing for the Wax repo. Use when running or interpreting Wax benchmarks, diagnosing CPU, memory, or I/O bottlenecks, or investigating Swift 6.2 concurrency issues such as Sendable, actor isolation, `@unchecked Sendable`, task-group fan-out, and data races. |
Use this skill to benchmark Wax changes, isolate the hottest code path, and separate real regressions from noisy samples.
The repo builds with Swift 6.1 and StrictConcurrency enabled, so audit for Swift 6.2 concurrency risks without assuming 6.2-only language mode.
Use references/benchmark-workflow.md for the command matrix, environment flags, and benchmark map.
Prefer these repo entry points when they match the symptom:
Tests/WaxIntegrationTests/RAGBenchmarkSupport.swiftTests/WaxIntegrationTests/RememberDedupBenchmarks.swiftTests/WaxIntegrationTests/StoreBloatBenchmarks.swiftTests/WaxIntegrationTests/RAGBenchmarks.swiftTests/WaxIntegrationTests/RAGBenchmarksMiniLM.swiftTests/WaxIntegrationTests/BatchEmbeddingBenchmark.swiftTests/WaxIntegrationTests/SessionRuntimeStatsBenchmarks.swiftTests/WaxIntegrationTests/WALCompactionBenchmarks.swiftTests/WaxIntegrationTests/HandoffLookupBenchmarks.swiftTests/WaxIntegrationTests/PayloadLivenessBenchmarks.swiftTests/WaxIntegrationTests/SurrogateSourceBenchmarks.swiftTests/WaxIntegrationTests/AccessStatsBootstrapBenchmarks.swiftTests/WaxIntegrationTests/ConcurrencyStressTests.swiftTests/WaxIntegrationTests/MemoryOrchestratorTests.swiftTests/WaxArcticTests/ArcticPerformanceBenchmark.swiftTests/WaxCoreTests/ReadWriteLockTests.swiftTests/WaxCoreTests/AsyncMutexTests.swiftmeasureAsync in RAGBenchmarkSupport.swift uses DispatchSemaphore plus Task because XCTest measurement is synchronous; do not confuse that with production concurrency.ANECompilerService or similar background work is active.Use references/concurrency-checklist.md when the change touches actors, task groups, Sendable, or @unchecked Sendable.
Default checks:
@Sendable closures that capture immutable values.@unchecked Sendable as a deliberate exception, not a default.@MainActor crossings in UI-adjacent or Photos code.@preconcurrency interop and @unchecked Sendable around CoreML, GRDB, Photos, and tokenizer internals as review hotspots, not automatic bugs.When you finish, state: