@buivietphi/skill-mobile-mt 2.0.1 → 2.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (10) hide show
  1. package/AGENTS.md +56 -38
  2. package/README.md +68 -40
  3. package/SKILL.md +471 -50
  4. package/package.json +1 -1
  5. package/shared/bug-detection.md +411 -27
  6. package/shared/code-review.md +899 -37
  7. package/shared/debugging-intelligence.md +787 -0
  8. package/shared/i18n-localization.md +426 -0
  9. package/shared/prompt-engineering.md +176 -20
  10. package/shared/storage-patterns.md +312 -0
package/AGENTS.md CHANGED
@@ -27,45 +27,48 @@
27
27
 
28
28
  ```
29
29
  skill-mobile-mt/
30
- ├── SKILL.md ← Entry point. Always load first.
30
+ ├── SKILL.md ← Entry point. Always load first. (~13,700 tokens)
31
31
  ├── AGENTS.md ← This file. Multi-agent config.
32
32
  │
33
33
  ├── react-native/
34
- │ └── react-native.md ← RN + Expo patterns (5,108 tokens)
34
+ │ └── react-native.md ← RN + Expo patterns (~3,300 tokens)
35
35
  │
36
36
  ├── flutter/
37
- │ └── flutter.md ← Flutter + Dart 3.x patterns (2,100 tokens)
37
+ │ └── flutter.md ← Flutter + Dart 3.x patterns (~1,200 tokens)
38
38
  │
39
39
  ├── ios/
40
- │ └── ios-native.md ← Swift + UIKit/SwiftUI patterns (1,452 tokens)
40
+ │ └── ios-native.md ← Swift + UIKit/SwiftUI patterns (~880 tokens)
41
41
  │
42
42
  ├── android/
43
- │ └── android-native.md ← Kotlin + Compose + Java legacy patterns (4,400 tokens)
43
+ │ └── android-native.md ← Kotlin + Compose + Java legacy patterns (~2,100 tokens)
44
44
  │
45
45
  └── shared/
46
46
  │
47
47
  ├── ── CORE (always load) ──────────────────────────────────
48
- ├── code-review.md ← Senior review checklist (865 tokens)
49
- ├── bug-detection.md ← Auto bug scanner (499 tokens)
50
- ├── prompt-engineering.md ← Auto-think + XML templates + advanced patterns (5,200 tokens)
48
+ ├── code-review.md ← 12-category PR-level review + grounded review + 25 production crash patterns (all platforms) (~6,600 tokens)
49
+ ├── bug-detection.md ← Intelligent bug scanner + git-aware Phase 0 + error classification + stack trace parser (~3,900 tokens)
50
+ ├── prompt-engineering.md ← Auto-think + XML templates + advanced patterns (~4,900 tokens)
51
51
  │
52
52
  ├── ── ON-DEMAND (load by task) ────────────────────────────
53
- ├── error-recovery.md ← 16 build/runtime error fixes (2,435 tokens)
54
- ├── document-analysis.md ← Parse images/PDFs/DOCX → code (1,200 tokens)
55
- ├── anti-patterns.md ← PII, cardinality, payload detection (2,800 tokens)
56
- ├── performance-prediction.md ← Frame budget, FPS prediction (1,500 tokens)
57
- ├── platform-excellence.md ← iOS 18+ vs Android 15+ UX + HIG (2,200 tokens)
58
- ├── version-management.md ← SDK compat matrix + release testing (3,500 tokens)
59
- ├── observability.md ← Sessions as 4th pillar (3,000 tokens)
60
- ├── architecture-intelligence.md ← Patterns from 30+ production repos (4,500 tokens)
61
- ├── common-pitfalls.md ← Known issue patterns (1,160 tokens)
62
- ├── release-checklist.md ← App Store/Play Store checklist (587 tokens)
53
+ ├── error-recovery.md ← 16 build/runtime error fixes (~1,800 tokens)
54
+ ├── document-analysis.md ← Parse images/PDFs/DOCX → code (~1,100 tokens)
55
+ ├── anti-patterns.md ← PII, cardinality, payload detection (~1,800 tokens)
56
+ ├── performance-prediction.md ← Frame budget, FPS prediction (~970 tokens)
57
+ ├── platform-excellence.md ← iOS 18+ vs Android 15+ UX + HIG (~1,300 tokens)
58
+ ├── version-management.md ← SDK compat matrix + release testing (~2,500 tokens)
59
+ ├── observability.md ← Sessions as 4th pillar (~2,800 tokens)
60
+ ├── architecture-intelligence.md ← Patterns from 30+ production repos (~2,600 tokens)
61
+ ├── common-pitfalls.md ← Known issue patterns (~970 tokens)
62
+ ├── release-checklist.md ← App Store/Play Store checklist (~600 tokens)
63
63
  │
64
- ├── offline-first.md ← Local-first + sync patterns (2,566 tokens)
65
- ├── testing-strategy.md ← Detox + Maestro + XCUITest + Espresso E2E (2,200 tokens)
66
- ├── ci-cd.md ← GitHub Actions CI templates (2,500 tokens)
67
- ├── ai-dlc-workflow.md ← AI-DLC structured workflow for complex features (2,500 tokens)
68
- ├── ui-ux-mobile.md ← Design system, screen templates, touch, navigation, a11y (5,500 tokens)
64
+ ├── offline-first.md ← Local-first + sync patterns (~1,600 tokens)
65
+ ├── testing-strategy.md ← Detox + Maestro + XCUITest + Espresso E2E (~1,300 tokens)
66
+ ├── ci-cd.md ← GitHub Actions CI templates (~1,300 tokens)
67
+ ├── ai-dlc-workflow.md ← AI-DLC structured workflow for complex features (~1,400 tokens)
68
+ ├── ui-ux-mobile.md ← Design system, screen templates, touch, navigation, a11y (~3,900 tokens)
69
+ ├── storage-patterns.md ← MMKV / SecureStore / SQLite / WatermelonDB / Keychain (~1,400 tokens)
70
+ ├── i18n-localization.md ← i18next / slang / .xcstrings / strings.xml / RTL / date format (~1,600 tokens)
71
+ ├── debugging-intelligence.md ← 45+ error patterns (RN+Flutter+iOS+Android) + git-aware debugging + search strategies (~5,900 tokens)
69
72
  │
70
73
  ├── ── TEMPLATES (copy to your project) ────────────────────
71
74
  ├── claude-md-template.md ← CLAUDE.md for Claude Code (copy to project root)
@@ -73,8 +76,12 @@ skill-mobile-mt/
73
76
  ```
74
77
 
75
78
  **Token totals:**
76
- - Smart load (1 platform + core shared): **~42,000 tokens** (32.8% of 128K)
77
- - Full load (all files): **~79,000 tokens** (61.7% of 128K)
79
+ - Smart load (1 platform + core shared): **~34,000 tokens** (26.6% of 128K)
80
+ - Full load (all files): **~76,300 tokens** (59.6% of 128K)
81
+ - debugging-intelligence.md, storage-patterns.md, i18n-localization.md: on-demand only — NOT loaded unless triggered
82
+ - code-review.md now ~6,600 tokens — 12-category PR-level review + grounded review + 25 production crash patterns (all 4 platforms)
83
+ - bug-detection.md now ~3,900 tokens — git-aware Phase 0, error classification, noise filter, stack trace parsing (all 4 platforms)
84
+ - debugging-intelligence.md now ~5,900 tokens — 45+ error patterns across RN, Flutter, iOS Swift, Android Kotlin
78
85
 
79
86
  ---
80
87
 
@@ -86,13 +93,13 @@ skill-mobile-mt/
86
93
 
87
94
  **Loads automatically:**
88
95
  ```
89
- SKILL.md (~15,800 tokens)
90
- + 1 platform file (~1,580–5,730 tokens depending on platform)
91
- + shared/code-review.md (~1,500 tokens)
92
- + shared/bug-detection.md (~800 tokens)
93
- + shared/prompt-engineering.md (~5,200 tokens)
96
+ SKILL.md (~13,700 tokens)
97
+ + 1 platform file (~880–3,300 tokens depending on platform)
98
+ + shared/code-review.md (~6,600 tokens)
99
+ + shared/bug-detection.md (~3,900 tokens)
100
+ + shared/prompt-engineering.md (~4,900 tokens)
94
101
  ─────────────────────────────────────────────────
95
- ≈ 42,000 tokens total (estimated)
102
+ ≈ 34,000 tokens total (estimated)
96
103
  ```
97
104
 
98
105
  **Use case:** Regular coding, new features, code review. Covers 90% of daily work.
@@ -106,6 +113,7 @@ The agent reads the task, then decides which extra file to load:
106
113
  | Task the user asks for | File loaded |
107
114
  |------------------------|-------------|
108
115
  | "Fix this crash / build error" | `shared/error-recovery.md` |
116
+ | "Complex bug / long stack trace / investigate issue" | `shared/debugging-intelligence.md` |
109
117
  | "Read this screenshot / PDF / DOCX" | `shared/document-analysis.md` |
110
118
  | "Add analytics / logging / crash tracking" | `shared/anti-patterns.md` + `shared/observability.md` |
111
119
  | "Build a FlatList / animation" | `shared/performance-prediction.md` |
@@ -117,8 +125,12 @@ The agent reads the task, then decides which extra file to load:
117
125
  | "Setup CI/CD / GitHub Actions" | `shared/ci-cd.md` |
118
126
  | "Big feature / multi-screen" | `shared/ai-dlc-workflow.md` |
119
127
  | "Create/design screen / demo UI" | `shared/ui-ux-mobile.md` |
128
+ | "Storage / MMKV / SecureStore / save data" | `shared/storage-patterns.md` |
129
+ | "i18n / multi-language / translation / RTL" | `shared/i18n-localization.md` |
130
+ | "Review PR / review code / accessibility check" | `shared/code-review.md` (already loaded) + `shared/anti-patterns.md` |
131
+ | "Compare options / best approach / upgrade vs stay" | SKILL.md Decision Matrix Protocol (already loaded) |
120
132
 
121
- **Load cost:** +500 to +3,500 tokens per on-demand file.
133
+ **Load cost:** +600 to +5,900 tokens per on-demand file.
122
134
 
123
135
  ---
124
136
 
@@ -126,7 +138,7 @@ The agent reads the task, then decides which extra file to load:
126
138
 
127
139
  **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.
128
140
 
129
- **Total:** ~72,300 tokens (56.5% of 128K, 36% of 200K)
141
+ **Total:** ~76,300 tokens (59.6% of 128K, 38.2% of 200K)
130
142
 
131
143
  **How it actually works:**
132
144
  - `@skill-mobile-mt` only injects SKILL.md into context
@@ -151,7 +163,7 @@ The agent reads the task, then decides which extra file to load:
151
163
  ```yaml
152
164
  skill:
153
165
  name: skill-mobile-mt
154
- version: "1.4.2"
166
+ version: "2.1.0"
155
167
  author: buivietphi
156
168
  category: engineering
157
169
  tags:
@@ -218,8 +230,8 @@ skill:
218
230
  java: ".java files in app/src/"
219
231
 
220
232
  context_budget:
221
- max_tokens: 77000
222
- smart_load_tokens: 40900
233
+ max_tokens: 76300
234
+ smart_load_tokens: 34000
223
235
  savings: "~47%"
224
236
  ```
225
237
 
@@ -266,6 +278,9 @@ Every agent MUST follow this loading sequence:
266
278
  - shared/observability.md (when adding logging, analytics, crash tracking)
267
279
  - shared/common-pitfalls.md (when encountering unfamiliar errors)
268
280
  - shared/release-checklist.md (when preparing for App Store/Play Store submission)
281
+ - shared/storage-patterns.md (when choosing or implementing local storage)
282
+ - shared/i18n-localization.md (when implementing multi-language or RTL)
283
+ - shared/debugging-intelligence.md (when investigating complex bugs or long stack traces)
269
284
 
270
285
  7. SKIP non-matching platform subfolders (saves ~66% context)
271
286
  ```
@@ -291,6 +306,9 @@ Priority 6 (ON-DEMAND): shared/testing-strategy.md — Detox + Maestro + XCUITes
291
306
  Priority 6 (ON-DEMAND): shared/ci-cd.md — GitHub Actions CI/CD templates
292
307
  Priority 6 (ON-DEMAND): shared/ai-dlc-workflow.md — AI-DLC structured workflow for complex features
293
308
  Priority 6 (ON-DEMAND): shared/ui-ux-mobile.md — Screen templates, design tokens, components, dark mode
309
+ Priority 6 (ON-DEMAND): shared/storage-patterns.md — MMKV, SecureStore, SQLite, WatermelonDB, Keychain
310
+ Priority 6 (ON-DEMAND): shared/i18n-localization.md — i18next, slang, .xcstrings, strings.xml, RTL
311
+ Priority 6 (ON-DEMAND): shared/debugging-intelligence.md — 30+ error patterns, git-aware debugging
294
312
  ```
295
313
 
296
314
  ---
@@ -469,10 +487,10 @@ npx @buivietphi/skill-mobile-mt --init all # → all files
469
487
  {
470
488
  "id": "skill-mobile-mt",
471
489
  "name": "skill-mobile-mt",
472
- "version": "2.0.0",
490
+ "version": "2.1.0",
473
491
  "author": "buivietphi",
474
492
  "category": "engineering",
475
- "description": "Master Senior Mobile Engineer. Patterns from 30+ production repos (200k+ GitHub stars) + research from top 53k+ star skill repos. Cardinal rules, self-critique loops, leverage pyramid, verification-first. React Native, Flutter, iOS, Android.",
493
+ "description": "Master Senior Mobile Engineer. Patterns from 30+ production repos (200k+ GitHub stars) + research from top 53k+ star skill repos. Cardinal rules, self-critique loops, leverage pyramid, verification-first, decision matrix, codebase scan strategy, grounded code review (anti-false-positive), git-aware debugging. React Native, Flutter, iOS, Android.",
476
494
  "risk": "low",
477
495
  "source": "buivietphi (MIT)",
478
496
  "platforms": ["react-native", "flutter", "ios", "android"],
package/README.md CHANGED
@@ -305,43 +305,46 @@ iOS only?
305
305
 
306
306
  | Scenario | Tokens | % of 128K | % of 200K |
307
307
  |----------|-------:|----------:|----------:|
308
- | SKILL.md only | ~15,800 | 12.3% | 7.9% |
309
- | + 1 platform + core shared/ | ~42,000 | 32.8% | 21.0% |
310
- | Cross-platform (RN/Flutter + iOS + Android) | ~58,000 | 45.3% | 29.0% |
311
- | All files loaded | ~79,000 | 61.7% | 39.5% |
312
- | **Smart load (recommended)** | **~42,000** | **32.8%** | **21.0%** |
308
+ | SKILL.md only | ~13,400 | 10.5% | 6.7% |
309
+ | + 1 platform + core shared/ | ~34,000 | 26.6% | 17.0% |
310
+ | Cross-platform (RN/Flutter + iOS + Android) | ~70,000 | 54.7% | 35.0% |
311
+ | All files loaded | ~76,300 | 59.6% | 38.2% |
312
+ | **Smart load (recommended)** | **~34,000** | **26.6%** | **17.0%** |
313
313
 
314
314
  ### Per-file token breakdown
315
315
 
316
316
  | File | Tokens |
317
317
  |------|-------:|
318
- | `SKILL.md` | 8,700 |
319
- | `AGENTS.md` | 1,600 |
320
- | `react-native/react-native.md` | 5,108 |
321
- | `flutter/flutter.md` | 2,100 |
322
- | `ios/ios-native.md` | 1,452 |
323
- | `android/android-native.md` | 4,400 |
324
- | `shared/code-review.md` | 865 |
325
- | `shared/bug-detection.md` | 499 |
326
- | `shared/prompt-engineering.md` | 5,200 |
327
- | `shared/architecture-intelligence.md` | 4,500 |
328
- | `shared/common-pitfalls.md` | 1,160 |
329
- | `shared/error-recovery.md` | 2,435 |
330
- | `shared/document-analysis.md` | 1,200 |
331
- | `shared/release-checklist.md` | 587 |
332
- | `shared/anti-patterns.md` | 2,800 |
333
- | `shared/performance-prediction.md` | 1,500 |
334
- | `shared/platform-excellence.md` | 2,200 |
335
- | `shared/version-management.md` | 3,500 |
336
- | `shared/observability.md` | 3,000 |
337
- | `shared/offline-first.md` | 2,566 |
338
- | `shared/testing-strategy.md` | 2,200 |
339
- | `shared/ci-cd.md` | 2,500 |
340
- | `shared/ai-dlc-workflow.md` | 2,500 |
341
- | `shared/ui-ux-mobile.md` | 5,500 |
342
- | `shared/claude-md-template.md` | ~500 |
343
- | `shared/agent-rules-template.md` | ~2,500 |
344
- | **Total** | **~59,100** |
318
+ | `SKILL.md` | ~13,400 |
319
+ | `AGENTS.md` | ~3,300 |
320
+ | `react-native/react-native.md` | ~3,200 |
321
+ | `flutter/flutter.md` | ~1,200 |
322
+ | `ios/ios-native.md` | ~860 |
323
+ | `android/android-native.md` | ~2,000 |
324
+ | `shared/code-review.md` | ~6,600 |
325
+ | `shared/bug-detection.md` | ~3,900 |
326
+ | `shared/debugging-intelligence.md` | ~5,900 |
327
+ | `shared/prompt-engineering.md` | ~4,700 |
328
+ | `shared/architecture-intelligence.md` | ~2,500 |
329
+ | `shared/common-pitfalls.md` | ~950 |
330
+ | `shared/error-recovery.md` | ~1,700 |
331
+ | `shared/document-analysis.md` | ~1,000 |
332
+ | `shared/release-checklist.md` | ~590 |
333
+ | `shared/anti-patterns.md` | ~1,750 |
334
+ | `shared/performance-prediction.md` | ~950 |
335
+ | `shared/platform-excellence.md` | ~1,250 |
336
+ | `shared/version-management.md` | ~2,400 |
337
+ | `shared/observability.md` | ~2,700 |
338
+ | `shared/offline-first.md` | ~1,560 |
339
+ | `shared/testing-strategy.md` | ~1,300 |
340
+ | `shared/ci-cd.md` | ~1,290 |
341
+ | `shared/ai-dlc-workflow.md` | ~1,380 |
342
+ | `shared/ui-ux-mobile.md` | ~3,850 |
343
+ | `shared/storage-patterns.md` | ~1,370 |
344
+ | `shared/i18n-localization.md` | ~1,570 |
345
+ | `shared/claude-md-template.md` | ~760 |
346
+ | `shared/agent-rules-template.md` | ~2,140 |
347
+ | **Total** | **~76,300** |
345
348
 
346
349
  ## Installed Structure
347
350
 
@@ -360,7 +363,8 @@ iOS only?
360
363
  │ └── android-native.md Android Kotlin + Java patterns
361
364
  └── shared/
362
365
  ├── code-review.md Senior review checklist
363
- ├── bug-detection.md Auto bug scanner
366
+ ├── bug-detection.md Auto bug scanner (4 modes + git-aware)
367
+ ├── debugging-intelligence.md 30+ error patterns + root cause tracing
364
368
  ├── prompt-engineering.md Auto-think + prompt templates
365
369
  ├── architecture-intelligence.md Patterns from 30+ production repos
366
370
  ├── common-pitfalls.md Problem → Symptoms → Solution
@@ -373,6 +377,8 @@ iOS only?
373
377
  ├── observability.md Sessions as 4th pillar
374
378
  ├── release-checklist.md Pre-release verification
375
379
  ├── offline-first.md Local-first + sync patterns
380
+ ├── storage-patterns.md Storage selection matrix (AsyncStorage/MMKV/SQLite/etc.)
381
+ ├── i18n-localization.md Internationalization + RTL + locale patterns
376
382
  ├── testing-strategy.md Detox + Maestro + XCUITest + Espresso E2E
377
383
  ├── ci-cd.md GitHub Actions CI/CD templates
378
384
  ├── ai-dlc-workflow.md AI-DLC structured dev workflow
@@ -409,15 +415,37 @@ your-project/
409
415
  - Single responsibility per file (max 300 lines)
410
416
  - Dependency injection, no hardcoded singletons
411
417
 
412
- ### Code Review Protocol
413
- - Architecture, correctness, performance, security, platform checklists
414
- - Severity levels: Critical / High / Medium / Low
415
- - Auto-fail patterns (console.log in production, hardcoded secrets, empty catch blocks)
418
+ ### Code Review Protocol (12-category, PR-level)
419
+ - **PR-Level Review**: size check, single responsibility, test accompaniment, commit hygiene — BEFORE code review
420
+ - **12 categories**: architecture, correctness, boundary conditions, test quality, readability, performance, security (expanded), accessibility (WCAG 2.1), breaking changes, platform, documentation, i18n
421
+ - **Severity levels**: Critical / High / Medium / Low with structured output format
422
+ - **Auto-fail patterns**: 10 code + 4 PR-level + 7 AI-specific grounding checks
423
+ - **Review output**: PR-level summary → findings by severity → verdict (APPROVE / CHANGES REQUESTED)
424
+ - **Boundary conditions**: null, empty, off-by-one, numeric limits, unicode, timezone — dedicated dimension
425
+ - **Accessibility**: touch targets (44pt/48dp), contrast ratios, screen reader, font scaling, focus management
426
+ - **Breaking change detection**: public API, deep links, DB schema, push payload, analytics events
427
+ - **Security depth**: certificate pinning, JWT lifecycle, bridge security, biometric auth, dependency audit
428
+ - **Grounded review (anti-false-positive)**: verify every finding before flagging — check actual installed APIs, don't flag from memory, confidence levels (high/medium/low)
429
+ - **Practical usage review**: 25 production crash patterns — 5 cross-platform + 5 React Native + 5 Flutter + 5 iOS Swift + 5 Android Kotlin
430
+ - **Library-specific traps**: React Native, Flutter, iOS Swift, Android Kotlin — real gotchas per platform
431
+ - **Cross-platform examples**: before/after code for all 4 platforms (not just RN)
416
432
 
417
433
  ### Bug Detection Scanner
418
- - Crash risks, memory leaks, race conditions
419
- - Security vulnerabilities, performance issues, UX problems
420
- - Platform-specific detection rules
434
+ - 4 debug modes: Error Analysis, Fix Bug, Investigate, Diagnostic Scan
435
+ - Git-aware debugging: checks recent commits before deep-diving (auto-skips if no git)
436
+ - 4-phase fix protocol: Root Cause → Pattern Analysis → Single Hypothesis → Defense in Depth
437
+ - 45+ error pattern database with exact search strategies — RN (7) + Flutter (6) + iOS Swift (5) + Android Kotlin (6) + Network (4) + State (3) + Navigation (2) + Build (4) + Platform (3)
438
+ - Anti-rationalization table: catches self-deception during debugging
439
+
440
+ ### Decision Matrix Protocol
441
+ - Structured comparison format when multiple valid approaches exist
442
+ - Estimation protocol: classify effort XS/S/M/L/XL with risk assessment
443
+ - Migration/upgrade decision protocol: breaking changes analysis + impact scan
444
+
445
+ ### Codebase Scan Strategy
446
+ - 3 scan levels: Quick (~5 reads), Standard (~15 reads), Deep (~30+ reads)
447
+ - Monorepo strategy: focus target package, scan shared deps
448
+ - Multi-module strategy: JS/TS vs Native vs Cross-layer task detection
421
449
 
422
450
  ### Grounding Protocol (Anti-Hallucination)
423
451
  - **Source hierarchy**: project code > skill files > official docs > production repos > AI knowledge