flutter-claude-skills

Automated UI verification loop: Marionette screenshot -> Figma reference -> pixel-diff -> difference list -> auto-fix iteration. Solves the false-positive verification problem flagged in insights reports (UI claimed fixed without actually being compared against the reference). Triggers (English): verify ui, ui compare, pixel diff, figma compare, automated ui verification, golden test fail. 自动 UI 验证：Marionette 截图 → Figma 参考图 → pixel-diff → 差异列表 → 自动修复循环。 触发关键字（中文）：verify ui、ui 对比、pixel diff、figma 对比、自动验证

Structured visual QA verdict for screenshot-to-reference comparisons

Operational rules for driving Codex CLI from scripts: success-signal contract, diff-feeding semantics, worktree -C flag, and stdin vs argv. Triggers when invoking `codex exec` programmatically (not interactively) — script wrappers, ralph loops, cron pipelines, multi-CLI fan-out. Surfaces silent failure modes that exit 0 but produce no useful output. Triggers (English): codex exec, codex cli, codex review, codex rescue, codex fallthrough, agent script invocation, programmatic codex.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Socratic deep interview with mathematical ambiguity gating before autonomous execution

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches code-reviewer subagent to review implementation against plan or requirements before proceeding

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization

Multi-layer verification flow after Flutter code changes: static analysis + tests + widget tree check + runtime error detection. Run after edits before claiming the change works. Triggers (English): verify changes, flutter verify, flutter analyze, widget tree check, runtime error detection, post-edit verification. 改完代碼後的多層驗證流程。靜態分析 + 跑測試 + widget tree 檢查 + runtime error 檢測。 觸發詞（中文）：verify、驗證、確認改動

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection

Apple App Store Connect API manager for iOS and macOS app management. Use this skill when managing iOS/macOS apps, in-app purchases, subscriptions, app metadata, TestFlight, app submissions, or adding macOS platform to existing iOS apps via the App Store Connect API. Triggers on keywords like "App Store Connect", "iOS products", "TestFlight", "app submission", "Apple IAP", "iOS subscription", "Mac App Store", "macOS deploy".

Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the Figma file context — e.g. create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills, bind variables to properties, or inspect file structure programmatically.

Kotlin Multiplatform fundamentals - use for project setup, expect/actual patterns, source sets, and platform-specific code

One-line summary of WHEN this skill should activate. Be specific. Triggers: comma-separated keywords / file-path patterns / user intents (e.g. `flutter test`, `*.golden.png`, `golden test fails`). Skip: conditions under which the skill should NOT activate (e.g. "not for unit tests", "not for non-Flutter projects").

Flutter/Dart API 契約測試與逆向工程 API 驗證。當需要對第三方 API 做整合測試、驗證 JSON 回應格式、建立 API 契約、快照回歸測試、或使用 api_contract/pact_dart/json_serializable 做契約驗證時使用。觸發關鍵字："API 契約", "contract test", "API 測試", "整合測試", "API 格式驗證", "逆向 API", "JSONP parse", "response validation", "API regression"。

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Port native Android/iOS code to Flutter (or any target language) using Contract-Based TDD. Guarantees zero missed features by extracting the complete API surface from the reference project first, writing contract tests, then implementing RED→GREEN. Use when porting Kotlin/Swift/Java to Dart, or any cross-language feature parity task.

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

Firebase AI Logic (formerly Vertex AI in Firebase) 設定與整合指南。當用戶需要在 Flutter App 中使用 Gemini AI（語音解析、OCR 解析、AI 分類等），或遇到 Firebase AI 相關錯誤時使用。包含 Token 優化、ThinkingConfig、System Instruction 最佳實踐。

Use when managing Firebase App Check via CLI. Covers enabling the API, registering Android/iOS attestation providers (Play Integrity, App Attest), managing SHA-256 fingerprints, enforcing services, and managing debug tokens. Triggers on keywords like "App Check", "Play Integrity", "App Attest", "debug token", "attestation", "enforce Firebase".

Reverse engineer Flutter/mobile app APIs using Frida dynamic instrumentation, BoringSSL traffic interception, crypto analysis, and standalone client creation. Use this skill when the user wants to: reverse engineer a mobile app's API, intercept HTTPS traffic from a Flutter app, extract auth tokens or crypto keys from Android apps, bypass API encryption/obfuscation layers, create a standalone Python API client from a mobile app, hook native libraries with Frida, analyze AES/Ed25519/X25519 crypto in stripped binaries, or dump SharedPreferences. Triggers on keywords like "逆向", "reverse engineer", "Frida", "intercept API", "hook", "ssl_write", "bypass encryption", "extract token", "API client from app", "BoringSSL", "libapp.so", "libflutter.so", "decompile APK".

Flutter background task configuration guide for iOS (background_fetch/BGTaskScheduler) and Android (WorkManager). Use when setting up periodic background tasks, debugging background execution failures, or auditing platform configuration for background work.

Comprehensive Flutter app CRUD testing on real devices/simulators using Mobile MCP + Dart MCP. Use when user asks to "test all pages", "verify all buttons", "run device CRUD test", "全頁面測試", "模擬器測試", "跑一遍所有按鈕". Triggers on keywords like "test all screens", "CRUD test", "device test", "tap every button", "full page test".

End-to-end Flutter project initialization with Firebase, AdMob, RevenueCat IAP, GA4 Analytics, Crashlytics, BYOK secure key management, Riverpod 3.0 state management, and pluggable engine architecture. This is the ONE skill to use when creating any new Flutter app from scratch. Triggers on keywords like 'new Flutter app', 'Flutter project', 'init Flutter', '建立新專案', '新專案', 'create Flutter', 'start project'. Also use when setting up Firebase, AdMob, IAP, or GA4 for an existing project that is missing these integrations. This skill supersedes flutter-project-standards for project creation — it contains the full executable workflow, not just a checklist.

Flutter ListView/CustomScrollView viewport recycling gotchas and debugging patterns. Use when debugging Flutter issues where widget state changes do not reflect in the UI, `didUpdateWidget` is never called, `ScrollController` has no clients, or selected items in horizontally scrollable lists are not visible. Triggers on keywords like "didUpdateWidget not called", "ListView recycling", "widget state lost", "scroll to selected", "chip not visible", "ScrollController hasClients false", "StatefulWidget disposed unexpectedly", "ConsumerStatefulWidget state lost".

Flutter 四工具联合测试：Marionette MCP（16 tools）+ Dart MCP（25 tools）+ Mobile MCP（21 tools）+ Codex CLI。 Marionette tap by text、热重载循环、widget tree 检查、录屏、截图存档、多语言测试。 触发关键字：marionette、mcp 测试、热重载、flutter driver、widget tree、录屏、截图对比

Flutter social login (Google + Apple Sign-In) with Firebase Auth. Use when setting up or debugging Google/Apple sign-in in Flutter apps, configuring OAuth client IDs, serverClientId, or handling platform-specific login flows. Triggers on keywords like "Google Sign-In", "Apple Sign-In", "social login", "serverClientId", "OAuth client", "sign_in_with_apple", "google_sign_in".

Automate testing of Flutter Windows desktop apps via Win32 API (user32.dll). Use when visually verifying Flutter desktop UI — clicking buttons, opening popups, navigating pages, taking screenshots. Triggers on keywords like "test Windows app", "UI test desktop", "click Flutter window", "Windows 桌面測試", "自動化測試", "截圖驗證", "visual verification desktop".

用 Playwright MCP 系統性抓取 Figma 設計稿（screenshot / design token / layer inventory）的完整工作流。 適用於：Figma MCP 限額耗盡 / 需要批量抓取多個 frame / 需要從 DOM 提取 token / 需要建立 frame-to-code 對照表。 觸發條件： - 用戶說「抓 Figma 設計稿」「批量截圖 Figma」「提 Figma token」 - Figma MCP 回報 "tool call limit" / "View seat" - 需要 Phase 對齊驗證（Figma vs 代碼實現） - 需要更新 design token 文件

Review all changed files, fix issues found, run tests, then commit. Use when finishing a feature or bugfix and want a clean commit.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

AdMob banner and native ad placement best practices for mobile apps. Use this skill when the user asks to add, review, or optimize AdMob ads to prevent account bans (accidental clicks) and improve UX.