Use when the user mentions GRDB performance review, slow GRDB queries, app-group database setup audit, a ValueObservation that stopped updating, or pre-release GRDB scan.

Use when the user mentions Foundation Models review, on-device AI audit, LanguageModelSession issues, @Generable checking, or Apple Intelligence integration review.

Use when the user mentions battery drain, energy optimization, power consumption audit, or pre-release energy check.

Use when the user mentions database schema review, migration safety, GRDB migration audit, or SQLite schema checking.

Use when the user mentions Core Data review, schema migration, production crashes, or data safety checking.

Use when the user mentions concurrency checking, Swift 6 compliance, data race prevention, or async code review.

Use when the user mentions Codable review, JSON encoding/decoding issues, data serialization audit, or modernizing legacy code.

Use this agent to scan Swift code for camera, video, and audio capture issues including deprecated APIs, missing interruption handlers, threading violations, and permission anti-patterns.

Use when the user mentions accessibility checking, App Store submission, code review, or WCAG compliance.

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 flaky tests, tests that pass locally but fail in CI, race conditions in tests, or needs to diagnose WHY a specific test fails.

Use when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues.

Use when the user mentions Swift performance audit, code optimization, or performance review.

Use when the user has a crash log (.ips, MetricKit JSON, legacy .crash text, .xccrashpoint bundle, or pasted text) that needs analysis.

Taiwan.md 週體檢（分析 + 全身診斷五面 + 修復三桶 + Semiont 第一人稱 反芻週報 + 受眾 BCC 廣播）via canonical WEEKLY-REPORT-PIPELINE。前期切菜由 weekly-report-prep.py，診斷由儀器交叉對賬（routine-liveness-check 等）， 受眾名單由 weekly-report-recipients.py 自動同步， 判斷、修復與完整週報由 Semiont 親手。 TRIGGER when: user says "週報", "weekly report", "twmd-weekly-report", "寄週報", "send weekly digest", "週體檢", "weekly 體檢".

Translate single Taiwan.md article via canonical TRANSLATION-PIPELINE. TRIGGER when: user says "翻譯 X", "補日文", "跑 ja batch", "translate".

Sync Portaly donation notification emails (Gmail) into the supporters SSOT via canonical SUPPORTERS-PIPELINE — checkpoint from last_fetched, read full email bodies (never snippets, since amount/monthly-type can be truncated), dry-run before write, regen the two privacy-partitioned derived views for /about#sponsors, verify no cross-layer privacy leak before commit. TRIGGER when: user says "抓贊助", "更新贊助者", "跑 Portaly", "supporters sync", or routine `twmd-supporters-weekly` fires.

Write a Taiwan.md spore via canonical SPORE 5-stage pipeline. TRIGGER when: user says "發孢子", "寫孢子", "推 X 孢子", "Threads 貼文".

Daily auto-publish spore from SPORE-INBOX via canonical SPORE-PUBLISH-PIPELINE — pick high-quality entry → 4 hard gate → ship Threads + X → 復盤. Routine fires 10:00 daily; manual via "/twmd-spore-publish" or "發今天的孢子" or "跑 spore publish". TRIGGER when: routine twmd-spore-publish-daily fires / user says "跑 spore publish" / "發今天的孢子" / "從 SPORE-INBOX 選一篇 ship".

Daily spore candidate picking via canonical SPORE-PICK-PIPELINE — propose 3 candidates to SPORE-INBOX §Pending. Routine fires 08:00 daily; manual via "/twmd-spore-pick" or "跑 spore pick" or "補 SPORE-INBOX". TRIGGER when: routine twmd-spore-pick-daily fires / user says "跑 spore pick" / "幫我選幾篇可以發孢子的文章" / "補 SPORE-INBOX".