@buivietphi/skill-mobile-mt 1.0.0

package/AGENTS.md

@@ -0,0 +1,392 @@
+# Skill Mobile MT — Agent Rules
+
+> Multi-agent compatibility layer for Claude Code, Codex, Gemini CLI, Kimi, Cursor, Copilot, Windsurf, Antigravity, and all Agent Skills-compatible tools.
+
+---
+
+## Agent Compatibility Matrix
+
+| Agent | Skill Path | Invocation | Think Block |
+|-------|-----------|------------|-------------|
+| Claude Code | `~/.claude/skills/skill-mobile-mt/` | `@skill-mobile-mt` or `@skill-mobile-mt project` | `<think>...</think>` |
+| Codex | `~/.codex/skills/skill-mobile-mt/` | `@skill-mobile-mt` or load as context | `<think>...</think>` |
+| Gemini CLI | `~/.gemini/skills/skill-mobile-mt/` | Load as context | `## Thinking:` block |
+| Kimi | `~/.kimi/skills/skill-mobile-mt/` | Load as context | `【思考】` or markdown |
+| Cursor | `~/.cursor/skills/skill-mobile-mt/` | Auto-loaded in Composer | Inline reasoning |
+| Copilot | `~/.copilot/skills/skill-mobile-mt/` | Loaded via workspace | `// PLAN:` comments |
+| Windsurf | `~/.windsurf/skills/skill-mobile-mt/` | Auto-loaded | Inline reasoning |
+| Antigravity | `~/.agents/skills/skill-mobile-mt/` | Loaded by orchestrator | Agent-native format |
+
+---
+
+## Full File Structure
+
+```
+skill-mobile-mt/
+├── SKILL.md                        ← Entry point. Always load first.
+├── AGENTS.md                       ← This file. Multi-agent config.
+│
+├── react-native/
+│   └── react-native.md             ← RN + Expo patterns (5,108 tokens)
+│
+├── flutter/
+│   └── flutter.md                  ← Flutter + Dart patterns (1,617 tokens)
+│
+├── ios/
+│   └── ios-native.md               ← Swift + UIKit/SwiftUI patterns (1,452 tokens)
+│
+├── android/
+│   └── android-native.md           ← Kotlin + Compose patterns (1,659 tokens)
+│
+└── shared/
+    │
+    ├── ── CORE (always load) ──────────────────────────────────
+    ├── code-review.md               ← Senior review checklist (865 tokens)
+    ├── bug-detection.md             ← Auto bug scanner (499 tokens)
+    ├── prompt-engineering.md        ← Auto-think + XML templates (3,927 tokens)
+    │
+    ├── ── ON-DEMAND (load by task) ────────────────────────────
+    ├── error-recovery.md            ← 16 build/runtime error fixes (2,435 tokens)
+    ├── document-analysis.md         ← Parse images/PDFs/DOCX → code (1,200 tokens)
+    ├── anti-patterns.md             ← PII, cardinality, payload detection (2,800 tokens)
+    ├── performance-prediction.md    ← Frame budget, FPS prediction (1,500 tokens)
+    ├── platform-excellence.md       ← iOS 18+ vs Android 15+ UX (1,500 tokens)
+    ├── version-management.md        ← SDK compat matrix + release testing (3,500 tokens)
+    ├── observability.md             ← Sessions as 4th pillar (3,000 tokens)
+    ├── common-pitfalls.md           ← Known issue patterns (1,160 tokens)
+    ├── release-checklist.md         ← App Store/Play Store checklist (587 tokens)
+    │
+    ├── ── TEMPLATES (copy to your project) ────────────────────
+    ├── claude-md-template.md        ← CLAUDE.md for Claude Code (copy to project root)
+    └── agent-rules-template.md      ← Rules for ALL agents: Cursor/.cursorrules, Windsurf/.windsurfrules, Copilot/.github/copilot-instructions.md, Codex/AGENTS.md, Gemini/GEMINI.md, Antigravity YAML
+```
+
+**Token totals:**
+- Smart load (1 platform + core shared): **~14,200 tokens** (11.1% of 128K)
+- Full load (all files): **~41,700 tokens** (32.6% of 128K)
+
+---
+
+## When Smart Load vs Full Load
+
+### Smart Load (default — always used)
+
+**Triggered by:** `@skill-mobile-mt` or `@skill-mobile-mt project`
+
+**Loads automatically:**
+```
+SKILL.md                           (6,100 tokens)
++ 1 platform file                  (~1,600–5,100 tokens depending on platform)
++ shared/code-review.md            (865 tokens)
++ shared/bug-detection.md          (499 tokens)
++ shared/prompt-engineering.md     (3,927 tokens)
+─────────────────────────────────────────────────
+≈ 14,200 tokens total
+```
+
+**Use case:** Regular coding, new features, code review. Covers 90% of daily work.
+
+---
+
+### On-Demand Load (triggered automatically by task type)
+
+The agent reads the task, then decides which extra file to load:
+
+| Task the user asks for | File loaded |
+|------------------------|-------------|
+| "Fix this crash / build error" | `shared/error-recovery.md` |
+| "Read this screenshot / PDF / DOCX" | `shared/document-analysis.md` |
+| "Add analytics / logging / crash tracking" | `shared/anti-patterns.md` + `shared/observability.md` |
+| "Build a FlatList / animation" | `shared/performance-prediction.md` |
+| "Make it feel native on iOS/Android" | `shared/platform-excellence.md` |
+| "Install this package / upgrade SDK" | `shared/version-management.md` |
+| "Prepare for App Store / Play Store" | `shared/release-checklist.md` |
+| "Weird issue, not sure why" | `shared/common-pitfalls.md` |
+
+**Load cost:** +500 to +3,500 tokens per on-demand file.
+
+---
+
+### Full Load (never automatic — AI reads all files)
+
+**No automatic trigger.** Full load happens when the AI reads every file without being selective — either because it's over-eager, or because the user explicitly asks for it.
+
+**Total:** ~41,700 tokens (32.6% of 128K, 20.9% of 200K)
+
+**How it actually works:**
+- `@skill-mobile-mt` only injects SKILL.md into context
+- From there, the AI uses the `Read` tool to open additional files
+- Smart load = AI reads selectively (only what the task needs)
+- Full load = AI reads every file in shared/ + all platform files
+
+**When full load makes sense:**
+- User says "load everything" or "give me a full audit"
+- New project setup where all patterns are relevant simultaneously
+- Cross-platform (iOS + Android + RN) with all shared patterns needed
+- Antigravity agent configured to load all files upfront
+
+**When it's wasteful:**
+- Single focused task ("fix this bug", "add this screen") — loads 3x more tokens than needed
+- Single-platform projects — loading all 4 platform files is waste
+
+---
+
+## Antigravity Configuration
+
+```yaml
+skill:
+  name: skill-mobile-mt
+  version: "1.0.0"
+  author: buivietphi
+  category: engineering
+  tags:
+    - mobile
+    - react-native
+    - flutter
+    - ios
+    - android
+    - clean-architecture
+    - code-review
+    - senior
+
+  modes:
+    default:
+      description: "Use pre-built production patterns from 18 real mobile apps"
+      loads:
+        # Core — always
+        - SKILL.md
+        - "{detected-platform}/{platform}.md"
+        - shared/code-review.md
+        - shared/bug-detection.md
+        - shared/prompt-engineering.md
+        # On-demand — add based on task
+        # - shared/error-recovery.md
+        # - shared/anti-patterns.md
+        # - shared/performance-prediction.md
+        # - shared/platform-excellence.md
+        # - shared/version-management.md
+        # - shared/observability.md
+        # - shared/document-analysis.md
+        # - shared/release-checklist.md
+        # - shared/common-pitfalls.md
+
+    project:
+      description: "Read current project, adapt to its framework and conventions"
+      argument: "project"
+      loads:
+        - SKILL.md (Section: Project Adaptation)
+        - "{detected-platform}/{platform}.md"
+        - shared/code-review.md
+        - shared/bug-detection.md
+        - shared/prompt-engineering.md
+
+  platform_detection:
+    react-native:
+      detect: "package.json contains 'react-native' or 'expo'"
+      load: "react-native/react-native.md"
+    flutter:
+      detect: "pubspec.yaml exists"
+      load: "flutter/flutter.md"
+    ios:
+      detect: "*.xcodeproj or *.xcworkspace exists (without pubspec.yaml)"
+      load: "ios/ios-native.md"
+    android:
+      detect: "build.gradle exists (without package.json or pubspec.yaml)"
+      load: "android/android-native.md"
+
+  language_detection:
+    typescript: ".tsx/.ts files in src/"
+    javascript: ".jsx/.js files in src/"
+    dart: ".dart files in lib/"
+    swift: ".swift files"
+    kotlin: ".kt files"
+    java: ".java files in app/src/"
+
+  context_budget:
+    max_tokens: 41700
+    smart_load_tokens: 14200
+    savings: "~66%"
+```
+
+---
+
+## File Loading Rules for All Agents
+
+### Smart Loading Protocol
+
+Every agent MUST follow this loading sequence:
+
+```
+1. ALWAYS load: SKILL.md (entry point, auto-detect, universal principles)
+
+2. AUTO-DETECT project:
+   - Framework (React Native / Flutter / iOS / Android)
+   - Language (TypeScript / JavaScript / Dart / Swift / Kotlin / Java)
+   - Package manager (yarn / npm / pnpm / bun / flutter pub / pod)
+   - State management
+   - Navigation
+
+3. LOAD the matching platform subfolder:
+   - react-native/react-native.md  (only if RN/Expo)
+   - flutter/flutter.md            (only if Flutter)
+   - ios/ios-native.md             (only if iOS native)
+   - android/android-native.md     (only if Android native)
+
+4. Cross-platform? Load multiple:
+   - Flutter → also load ios/ + android/ (native modules)
+   - React Native → also load ios/ + android/ (native modules)
+
+5. ALWAYS load shared/ (core):
+   - shared/code-review.md
+   - shared/bug-detection.md
+   - shared/prompt-engineering.md
+
+6. LOAD shared/ (on-demand, based on task):
+   - shared/error-recovery.md         (when debugging build/runtime errors)
+   - shared/document-analysis.md      (when reading images, PDFs, DOCX)
+   - shared/anti-patterns.md          (when reviewing or writing observability code)
+   - shared/performance-prediction.md (when building lists, animations, heavy screens)
+   - shared/platform-excellence.md    (when implementing platform-specific UX)
+   - shared/version-management.md     (when installing packages or upgrading SDK)
+   - shared/observability.md          (when adding logging, analytics, crash tracking)
+   - shared/common-pitfalls.md        (when encountering unfamiliar errors)
+   - shared/release-checklist.md      (when preparing for App Store/Play Store submission)
+
+7. SKIP non-matching platform subfolders (saves ~66% context)
+```
+
+### Loading Priority
+
+```
+Priority 1 (CRITICAL):  SKILL.md — Auto-detect, mode selection, principles
+Priority 2 (HIGH):      {platform}/{platform}.md — Framework-specific patterns
+Priority 3 (MEDIUM):    shared/code-review.md — Review checklist
+Priority 4 (MEDIUM):    shared/bug-detection.md — Auto-scanner
+Priority 5 (MEDIUM):    shared/prompt-engineering.md — Auto-think templates
+Priority 6 (ON-DEMAND): shared/error-recovery.md — Build/runtime error fixes
+Priority 6 (ON-DEMAND): shared/anti-patterns.md — PII, cardinality, payload detection
+Priority 6 (ON-DEMAND): shared/performance-prediction.md — Frame budget calculations
+Priority 6 (ON-DEMAND): shared/platform-excellence.md — iOS 18+ vs Android 15+ UX
+Priority 6 (ON-DEMAND): shared/version-management.md — SDK compatibility matrix
+Priority 6 (ON-DEMAND): shared/observability.md — Sessions as 4th pillar
+Priority 6 (ON-DEMAND): shared/document-analysis.md — Parse images/PDFs → code
+Priority 6 (ON-DEMAND): shared/release-checklist.md — Pre-release verification
+Priority 6 (ON-DEMAND): shared/common-pitfalls.md — Known issue patterns
+```
+
+---
+
+## Agent-Specific Behavior
+
+### Claude Code
+- Supports `$ARGUMENTS` — use `project` to trigger project mode
+- Can invoke sub-files via Read tool from subfolders
+- Full tool access for project scanning and auto-detect
+
+### Codex
+- Load SKILL.md as system context or prepend to conversation
+- Reference subfolder files with Read tool when needed
+- Use `project` keyword to trigger project adaptation mode
+
+### Gemini CLI
+- Load SKILL.md as system context
+- Parse mode from user prompt ("use project mode" or default)
+- Reference subfolder files as needed
+
+### Kimi
+- Load SKILL.md as knowledge base
+- Supports both Chinese and English prompts
+- Think blocks use `【思考】` format
+
+### Cursor / Copilot / Windsurf
+- Auto-loaded when skill directory detected in workspace
+- Mode determined by presence of project files in workspace
+- Think blocks embedded as comments before code
+
+### Antigravity
+- Orchestrator loads based on detected project type
+- Follows `platform_detection` rules above
+- Respects `context_budget` limits
+
+---
+
+## Project-Level Rules (Auto-Loaded Per Agent)
+
+Each agent reads a specific file from the **user's project root** every session.
+These are separate from the skill files — they go in the user's project, not in skill-mobile-mt/.
+
+| Agent | File | Location |
+|-------|------|----------|
+| Claude Code | `CLAUDE.md` | Project root |
+| Cursor | `.cursorrules` | Project root |
+| Windsurf | `.windsurfrules` | Project root |
+| GitHub Copilot | `.github/copilot-instructions.md` | `.github/` folder |
+| Codex | `AGENTS.md` | Project root |
+| Gemini CLI | `GEMINI.md` | Project root |
+| Kimi | No auto-load — paste as context | — |
+| Antigravity | YAML `context.rules` field | Antigravity config |
+
+**Templates for all agents:** `shared/agent-rules-template.md`
+Copy the relevant section to your project to enable auto-check rules in every session.
+
+```bash
+# After installing skill-mobile-mt, find the templates at:
+~/.claude/skills/skill-mobile-mt/shared/agent-rules-template.md
+~/.claude/skills/skill-mobile-mt/shared/claude-md-template.md
+```
+
+---
+
+## Installation Paths
+
+```bash
+# Claude Code (global)
+~/.claude/skills/skill-mobile-mt/
+
+# Claude Code (project-local)
+.claude/skills/skill-mobile-mt/
+
+# Codex
+~/.codex/skills/skill-mobile-mt/
+
+# Gemini CLI
+~/.gemini/skills/skill-mobile-mt/
+
+# Kimi
+~/.kimi/skills/skill-mobile-mt/
+
+# Cursor
+~/.cursor/skills/skill-mobile-mt/
+
+# Windsurf
+~/.windsurf/skills/skill-mobile-mt/
+
+# Copilot
+~/.copilot/skills/skill-mobile-mt/
+
+# Antigravity (shared agent directory)
+~/.agents/skills/skill-mobile-mt/
+
+# Custom path
+npx @buivietphi/skill-mobile-mt --path /your/custom/path
+```
+
+---
+
+## Metadata
+
+```json
+{
+  "id": "skill-mobile-mt",
+  "name": "skill-mobile-mt",
+  "version": "1.0.0",
+  "author": "buivietphi",
+  "category": "engineering",
+  "description": "Master Senior Mobile Engineer. Pre-built patterns from 18 production apps + project adaptation. Auto-detects language and framework. React Native, Flutter, iOS, Android.",
+  "risk": "low",
+  "source": "buivietphi (MIT)",
+  "platforms": ["react-native", "flutter", "ios", "android"],
+  "languages": ["typescript", "javascript", "dart", "swift", "kotlin", "java"],
+  "agents": ["claude-code", "codex", "gemini", "kimi", "cursor", "copilot", "windsurf", "antigravity"]
+}
+```

package/README.md

@@ -0,0 +1,224 @@
+# @buivietphi/skill-mobile-mt
+
+**Master Senior Mobile Engineer** — AI skill for Claude Code, Codex, Gemini CLI, Kimi, Cursor, Copilot, Windsurf, and Antigravity.
+
+Pre-built architecture patterns from **18 production mobile apps + 4 production open-source skills** + auto-adaptation to your current project.
+
+## Install
+
+```bash
+npx @buivietphi/skill-mobile-mt
+```
+
+Interactive mode — detects which AI agents are installed and prompts you.
+
+### Install to specific agents
+
+```bash
+npx @buivietphi/skill-mobile-mt --claude       # Claude Code only
+npx @buivietphi/skill-mobile-mt --codex        # Codex only
+npx @buivietphi/skill-mobile-mt --gemini       # Gemini CLI only
+npx @buivietphi/skill-mobile-mt --kimi         # Kimi only
+npx @buivietphi/skill-mobile-mt --antigravity  # Antigravity only
+npx @buivietphi/skill-mobile-mt --all          # All detected agents
+npx @buivietphi/skill-mobile-mt --path ./dir   # Custom directory
+```
+
+## Usage
+
+### Mode 1: Pre-Built Architecture (default)
+
+```
+@skill-mobile-mt
+```
+
+Uses battle-tested patterns extracted from real production apps:
+- **10 React Native apps** — Redux, MobX, Apollo/GraphQL, React Navigation
+- **3 Flutter apps** — Riverpod, Clean Architecture, Dio, GoRouter
+- **4 Android Native apps** — Multi-module Gradle, Hilt, Compose, Room
+- **1 iOS Native app** — Swift, MVVM, CocoaPods, Combine
+
+### Mode 2: Adapt to Your Project (project)
+
+```
+@skill-mobile-mt project
+```
+
+Reads your current project first, then follows **your** conventions:
+- Detects framework, language, package manager, state management, navigation
+- Matches your naming, imports, file structure, patterns
+- Never suggests migrations or imposes different architecture
+
+## Auto-Detect
+
+The skill automatically detects before any action:
+
+| What | How |
+|------|-----|
+| **Framework** | `pubspec.yaml` → Flutter, `package.json` with `react-native` → RN, `*.xcodeproj` → iOS, `build.gradle` → Android |
+| **Language** | `.dart` → Dart, `.tsx/.ts` → TypeScript, `.swift` → Swift, `.kt` → Kotlin |
+| **Package Manager** | `yarn.lock` → yarn, `pnpm-lock.yaml` → pnpm, `package-lock.json` → npm, `pubspec.lock` → flutter pub |
+| **State Management** | Redux / MobX / Zustand / Riverpod / BLoC / StateFlow / Combine |
+| **Navigation** | React Navigation / Expo Router / GoRouter / NavigationStack |
+
+## Smart Loading
+
+Only loads the relevant platform docs — saves **~60% context tokens**.
+
+```
+Flutter project?
+  → Load: flutter/flutter.md + ios/ + android/ + shared/
+  → Skip: react-native/
+
+React Native project?
+  → Load: react-native/react-native.md + ios/ + android/ + shared/
+  → Skip: flutter/
+
+iOS only?
+  → Load: ios/ios-native.md + shared/
+  → Skip: flutter/ + react-native/ + android/
+```
+
+## Context Cost
+
+| Scenario | Tokens | % of 128K | % of 200K |
+|----------|-------:|----------:|----------:|
+| SKILL.md only | ~6,100 | 4.8% | 3.1% |
+| + 1 platform + core shared/ | ~14,200 | 11.1% | 7.1% |
+| Cross-platform (RN/Flutter + iOS + Android) | ~18,200 | 14.2% | 9.1% |
+| All files loaded | ~41,700 | 32.6% | 20.9% |
+| **Smart load (recommended)** | **~14,200** | **11.1%** | **7.1%** |
+
+### Per-file token breakdown
+
+| File | Tokens |
+|------|-------:|
+| `SKILL.md` | 6,100 |
+| `AGENTS.md` | 1,541 |
+| `react-native/react-native.md` | 5,108 |
+| `flutter/flutter.md` | 1,617 |
+| `ios/ios-native.md` | 1,452 |
+| `android/android-native.md` | 1,659 |
+| `shared/code-review.md` | 865 |
+| `shared/bug-detection.md` | 499 |
+| `shared/prompt-engineering.md` | 3,927 |
+| `shared/common-pitfalls.md` | 1,160 |
+| `shared/error-recovery.md` | 2,435 |
+| `shared/document-analysis.md` | 1,200 |
+| `shared/release-checklist.md` | 587 |
+| `shared/anti-patterns.md` | 2,800 |
+| `shared/performance-prediction.md` | 1,500 |
+| `shared/platform-excellence.md` | 1,500 |
+| `shared/version-management.md` | 3,500 |
+| `shared/observability.md` | 3,000 |
+| **Total** | **~41,700** |
+
+## Installed Structure
+
+```
+~/.claude/skills/               (or ~/.gemini/skills/, ~/.agents/skills/, etc.)
+└── skill-mobile-mt/
+    ├── SKILL.md                    Entry point + auto-detect
+    ├── AGENTS.md                   Multi-agent compatibility
+    ├── react-native/
+    │   └── react-native.md         React Native patterns
+    ├── flutter/
+    │   └── flutter.md              Flutter patterns
+    ├── ios/
+    │   └── ios-native.md           iOS Swift patterns
+    ├── android/
+    │   └── android-native.md       Android Kotlin patterns
+    └── shared/
+        ├── code-review.md          Senior review checklist
+        ├── bug-detection.md        Auto bug scanner
+        ├── prompt-engineering.md   Intelligent prompt generation
+        ├── common-pitfalls.md      Problem → Symptoms → Solution
+        ├── error-recovery.md       Fix build/runtime errors
+        ├── document-analysis.md    Parse docs/images → code
+        ├── anti-patterns.md        PII, cardinality, payload detection
+        ├── performance-prediction.md  Predict FPS/memory BEFORE shipping
+        ├── platform-excellence.md  iOS 18+ vs Android 15+ guidelines
+        ├── version-management.md   SDK compatibility matrix + release testing
+        ├── observability.md        Sessions as 4th pillar, context-rich events
+        └── release-checklist.md    Pre-release verification
+```
+
+## What's Included
+
+### Clean Architecture & SOLID
+- Dependencies flow inward (UI → Domain → Data)
+- Single responsibility per file (max 300 lines)
+- Dependency injection, no hardcoded singletons
+
+### Code Review Protocol
+- Architecture, correctness, performance, security, platform checklists
+- Severity levels: Critical / High / Medium / Low
+- Auto-fail patterns (console.log in production, hardcoded secrets, empty catch blocks)
+
+### Bug Detection Scanner
+- Crash risks, memory leaks, race conditions
+- Security vulnerabilities, performance issues, UX problems
+- Platform-specific detection rules
+
+### Advanced AI Patterns (from Windsurf, Cursor, Devin, Cline)
+- **Status Update Pattern**: Brief progress notes before tool use (no monologues)
+- **Execution Modes**: Discovery → Implementation → Completion (prevents thrashing)
+- **Pre-Action Validation**: Think blocks verify parameters before acting
+- **Error Recovery Protocol**: Max 3 attempts with fallbacks, then ask user
+- **Mobile Context Capture**: Platform, SDK, device, native modules, permissions
+- **Build & Deploy Gates**: Platform-specific pre-completion checklists
+- **Mobile Anti-Patterns**: Common mistakes from AI tools (and how to avoid them)
+
+### Intelligent Prompt Engineering
+- XML tag structure for clarity (`<task>`, `<context>`, `<instructions>`, `<constraints>`)
+- Enhanced auto-think templates with pre-action validation
+- Progressive context loading (5 levels: overview → pattern → files → docs → expert)
+- Just-in-time file reading (grep first, read only needed)
+- Reference pattern system (clone existing instead of reading docs)
+- Multi-AI format support (Claude, Gemini, Kimi, Cursor, Copilot, Windsurf)
+
+### Document Analysis
+- Parse images (mockups, wireframes), PDFs (requirements), DOCX, XML, JSON
+- UI Analysis: extract layout, components, styling, states from screenshots
+- Requirements Extraction: user stories, screen flows, data models, business rules
+- Document → Code pipeline: read → extract → map features → scaffold
+
+### Production Patterns (from Senaiverse, Mhuxain, VoltAgent, Nexus)
+
+- **Anti-Pattern Detection** (`anti-patterns.md`): Detect PII leaks (CRITICAL), high cardinality tags, unbounded payloads, unstructured logs, sync telemetry on main thread — with auto-fix suggestions
+- **Performance Prediction** (`performance-prediction.md`): Calculate frame budget, FlatList bridge calls, and memory usage BEFORE writing code. Example: `50 items × 3 bridge calls × 0.3ms = 45ms/frame → 22 FPS ❌ JANK`
+- **Platform Excellence** (`platform-excellence.md`): iOS 18+ vs Android 15+ native UX standards — navigation patterns, typography, icons, gesture handling, performance targets (cold start < 1s iOS, < 1.5s Android)
+- **Version Management** (`version-management.md`): Full SDK compatibility matrix for RN 0.73-0.76, Expo 50-52, Flutter 3.22-3.27, iOS 16-18, Android 13-15. Check SDK compat BEFORE `npm install`. Release-mode testing protocol.
+- **Observability** (`observability.md`): Sessions as the 4th pillar (Metrics + Logs + Traces + **Sessions**). Session lifecycle, enrichment API, unified instrumentation stack, correlation queries. Every event carries `session_id` for full user journey reconstruction.
+
+### Error Recovery
+- 16 common build/runtime errors with concrete fixes
+- Platform-specific solutions (RN CLI, Expo, Flutter, iOS, Android)
+- General recovery protocol for systematic debugging
+
+### Release & Review
+- Pre-release checklist for App Store and Play Store submissions
+- Common pitfalls with Problem → Symptoms → Solution format
+- Security audit patterns
+
+### Security Non-Negotiables
+- No hardcoded secrets
+- Secure token storage (Keychain / EncryptedSharedPreferences / SecureStore)
+- Deep link validation, HTTPS only
+
+## Supported Agents
+
+| Agent | Install Path | Status |
+|-------|-------------|--------|
+| Claude Code | `~/.claude/skills/skill-mobile-mt/` | Full support |
+| Codex | `~/.codex/skills/skill-mobile-mt/` | Full support |
+| Gemini CLI | `~/.gemini/skills/skill-mobile-mt/` | Full support |
+| Kimi | `~/.kimi/skills/skill-mobile-mt/` | Full support |
+| Cursor | `~/.cursor/skills/skill-mobile-mt/` | Full support |
+| Copilot | `~/.copilot/skills/skill-mobile-mt/` | Full support |
+| Windsurf | `~/.windsurf/skills/skill-mobile-mt/` | Full support |
+| Antigravity | `~/.agents/skills/skill-mobile-mt/` | Full support |
+
+## License
+
+MIT — by [buivietphi](https://github.com/buivietphi)