DengNaichen

Use when fixing or auditing ANY accessibility issue — VoiceOver, Dynamic Type, color contrast, touch targets, WCAG compliance, App Store accessibility review.

Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature. Covers Foundation Models, @Generable, LanguageModelSession, Tool protocol, eval suites, model-as-judge scoring, SpeechTranscriber, CoreML.

Use when the user wants to triage a CORPUS of production crashes/hangs from an aggregator (Sentry, App Store Connect) — grouped, counted issues — rather than a single crash file.

Use when the user mentions file storage issues, data loss, backup bloat, or asks to audit storage usage.

Use when the user wants to audit test quality, find flaky test patterns, speed up test execution, or prepare for Swift Testing migration.

Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code. Covers build failures, compilation errors, dependency conflicts, simulator problems, environment-first diagnostics.

Use when writing ANY async code, actors, threads, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.

Use when working with ANY data persistence, database, storage, CloudKit, migration, or serialization. Covers SwiftData, Core Data, GRDB, SQLite, CloudKit sync, file storage, Codable, migrations.

从 .harnesskit/facts.md 和已核对的仓库证据填充或刷新 docs/practices/*.md。用于 scan-facts 之后更新 coding、product sense、security、reliability 等判断指导，而不是把每条建议都升级成 RULES.md 规则。

在 harnesskit init 之后编排 Context Harness 初始化。用于通过 scan-facts、fill-agents、fill-architecture、fill-practices、fill-rules、fill-skills 和最终一致性检查来启动或刷新 generated harness。

从已核对证据扫描仓库事实并写入 .harnesskit/facts.md。用于填充 AGENTS.md、ARCHITECTURE.md、RULES.md 或项目特定 skill section 前，启动或刷新 Context Harness facts。

从已核对证据扫描仓库事实并写入 .harnesskit/facts.md。用于填充 AGENTS.md、ARCHITECTURE.md、RULES.md 或项目特定 skill section 前，启动或刷新 Context Harness facts。

从 .harnesskit/facts.md 和已核对的仓库证据填充或刷新 docs/practices/*.md。用于 scan-facts 之后更新 coding、product sense、security、reliability 等判断指导，而不是把每条建议都升级成 RULES.md 规则。

从 .harnesskit/facts.md 和已核对的仓库证据填充或刷新 RULES.md 短规则索引。用于 scan-facts 之后更新可执行规则；validation context、检查方式和 runner bindings 应进入对应验证 artifact 或 runner。

从 .harnesskit/facts.md 和已核对的仓库证据填充或刷新 AGENTS.md，使其保持为简洁的 agent 启动入口。用于 scan-facts 之后更新操作关键事实、上下文路由、skill 触发点、验证入口、漂移处理，或同步 root/template AGENTS.md 的结构意图。

从 .harnesskit/facts.md 和已核对的仓库证据填充或刷新 AGENTS.md，使其保持为简洁的 agent 启动入口。用于 scan-facts 之后更新操作关键事实、上下文路由、skill 触发点、验证入口、漂移处理，或同步 root/template AGENTS.md 的结构意图。

Domain expertise for evaluating job-candidate fit for Backend, ML, and AI Engineering roles. Provides rubrics, quality standards, and decision frameworks—no workflow orchestration.