tribunal-kit 3.0.0 → 4.0.0

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 (233) hide show
  1. package/.agent/ARCHITECTURE.md +99 -99
  2. package/.agent/GEMINI.md +52 -52
  3. package/.agent/agents/accessibility-reviewer.md +187 -220
  4. package/.agent/agents/ai-code-reviewer.md +199 -233
  5. package/.agent/agents/backend-specialist.md +215 -238
  6. package/.agent/agents/code-archaeologist.md +161 -181
  7. package/.agent/agents/database-architect.md +184 -207
  8. package/.agent/agents/debugger.md +191 -218
  9. package/.agent/agents/dependency-reviewer.md +103 -136
  10. package/.agent/agents/devops-engineer.md +218 -238
  11. package/.agent/agents/documentation-writer.md +201 -221
  12. package/.agent/agents/explorer-agent.md +160 -180
  13. package/.agent/agents/frontend-reviewer.md +160 -194
  14. package/.agent/agents/frontend-specialist.md +248 -237
  15. package/.agent/agents/game-developer.md +48 -52
  16. package/.agent/agents/logic-reviewer.md +116 -149
  17. package/.agent/agents/mobile-developer.md +200 -223
  18. package/.agent/agents/mobile-reviewer.md +162 -195
  19. package/.agent/agents/orchestrator.md +181 -211
  20. package/.agent/agents/penetration-tester.md +157 -174
  21. package/.agent/agents/performance-optimizer.md +183 -203
  22. package/.agent/agents/performance-reviewer.md +178 -211
  23. package/.agent/agents/precedence-reviewer.md +213 -0
  24. package/.agent/agents/product-manager.md +142 -162
  25. package/.agent/agents/product-owner.md +6 -25
  26. package/.agent/agents/project-planner.md +142 -162
  27. package/.agent/agents/qa-automation-engineer.md +225 -242
  28. package/.agent/agents/security-auditor.md +174 -194
  29. package/.agent/agents/seo-specialist.md +193 -213
  30. package/.agent/agents/sql-reviewer.md +161 -194
  31. package/.agent/agents/supervisor-agent.md +184 -203
  32. package/.agent/agents/swarm-worker-contracts.md +17 -17
  33. package/.agent/agents/swarm-worker-registry.md +46 -46
  34. package/.agent/agents/test-coverage-reviewer.md +160 -193
  35. package/.agent/agents/test-engineer.md +0 -21
  36. package/.agent/agents/type-safety-reviewer.md +175 -208
  37. package/.agent/patterns/generator.md +9 -9
  38. package/.agent/patterns/inversion.md +12 -12
  39. package/.agent/patterns/pipeline.md +9 -9
  40. package/.agent/patterns/reviewer.md +13 -13
  41. package/.agent/patterns/tool-wrapper.md +9 -9
  42. package/.agent/rules/GEMINI.md +63 -63
  43. package/.agent/scripts/append_flow.js +72 -0
  44. package/.agent/scripts/case_law_manager.py +525 -0
  45. package/.agent/scripts/compress_skills.py +167 -0
  46. package/.agent/scripts/consolidate_skills.py +173 -0
  47. package/.agent/scripts/deep_compress.py +202 -0
  48. package/.agent/scripts/minify_context.py +80 -0
  49. package/.agent/scripts/security_scan.py +1 -1
  50. package/.agent/scripts/skill_evolution.py +563 -0
  51. package/.agent/scripts/strip_tribunal.py +41 -0
  52. package/.agent/skills/agent-organizer/SKILL.md +100 -126
  53. package/.agent/skills/agentic-patterns/SKILL.md +0 -70
  54. package/.agent/skills/ai-prompt-injection-defense/SKILL.md +134 -160
  55. package/.agent/skills/api-patterns/SKILL.md +123 -215
  56. package/.agent/skills/api-security-auditor/SKILL.md +143 -177
  57. package/.agent/skills/app-builder/SKILL.md +334 -50
  58. package/.agent/skills/app-builder/templates/SKILL.md +13 -15
  59. package/.agent/skills/app-builder/templates/astro-static/TEMPLATE.md +16 -16
  60. package/.agent/skills/app-builder/templates/chrome-extension/TEMPLATE.md +22 -22
  61. package/.agent/skills/app-builder/templates/cli-tool/TEMPLATE.md +18 -18
  62. package/.agent/skills/app-builder/templates/electron-desktop/TEMPLATE.md +20 -20
  63. package/.agent/skills/app-builder/templates/express-api/TEMPLATE.md +17 -17
  64. package/.agent/skills/app-builder/templates/flutter-app/TEMPLATE.md +18 -18
  65. package/.agent/skills/app-builder/templates/monorepo-turborepo/TEMPLATE.md +21 -21
  66. package/.agent/skills/app-builder/templates/nextjs-fullstack/TEMPLATE.md +19 -19
  67. package/.agent/skills/app-builder/templates/nextjs-saas/TEMPLATE.md +26 -26
  68. package/.agent/skills/app-builder/templates/nextjs-static/TEMPLATE.md +26 -26
  69. package/.agent/skills/app-builder/templates/nuxt-app/TEMPLATE.md +19 -19
  70. package/.agent/skills/app-builder/templates/python-fastapi/TEMPLATE.md +18 -18
  71. package/.agent/skills/app-builder/templates/react-native-app/TEMPLATE.md +20 -20
  72. package/.agent/skills/appflow-wireframe/SKILL.md +95 -121
  73. package/.agent/skills/architecture/SKILL.md +169 -331
  74. package/.agent/skills/authentication-best-practices/SKILL.md +139 -173
  75. package/.agent/skills/bash-linux/SKILL.md +129 -154
  76. package/.agent/skills/behavioral-modes/SKILL.md +8 -69
  77. package/.agent/skills/brainstorming/SKILL.md +436 -104
  78. package/.agent/skills/building-native-ui/SKILL.md +152 -174
  79. package/.agent/skills/clean-code/SKILL.md +331 -360
  80. package/.agent/skills/code-review-checklist/SKILL.md +0 -62
  81. package/.agent/skills/config-validator/SKILL.md +115 -141
  82. package/.agent/skills/csharp-developer/SKILL.md +468 -528
  83. package/.agent/skills/database-design/SKILL.md +104 -369
  84. package/.agent/skills/deployment-procedures/SKILL.md +119 -145
  85. package/.agent/skills/devops-engineer/SKILL.md +295 -332
  86. package/.agent/skills/devops-incident-responder/SKILL.md +87 -113
  87. package/.agent/skills/doc.md +5 -5
  88. package/.agent/skills/documentation-templates/SKILL.md +27 -63
  89. package/.agent/skills/edge-computing/SKILL.md +131 -157
  90. package/.agent/skills/extract-design-system/SKILL.md +108 -134
  91. package/.agent/skills/framer-motion-expert/SKILL.md +111 -855
  92. package/.agent/skills/frontend-design/SKILL.md +151 -499
  93. package/.agent/skills/game-design-expert/SKILL.md +79 -105
  94. package/.agent/skills/game-engineering-expert/SKILL.md +96 -122
  95. package/.agent/skills/geo-fundamentals/SKILL.md +97 -124
  96. package/.agent/skills/github-operations/SKILL.md +279 -314
  97. package/.agent/skills/gsap-expert/SKILL.md +119 -826
  98. package/.agent/skills/i18n-localization/SKILL.md +113 -138
  99. package/.agent/skills/intelligent-routing/SKILL.md +167 -127
  100. package/.agent/skills/lint-and-validate/SKILL.md +16 -52
  101. package/.agent/skills/llm-engineering/SKILL.md +344 -357
  102. package/.agent/skills/local-first/SKILL.md +128 -154
  103. package/.agent/skills/mcp-builder/SKILL.md +92 -118
  104. package/.agent/skills/mobile-design/SKILL.md +213 -219
  105. package/.agent/skills/motion-engineering/SKILL.md +184 -0
  106. package/.agent/skills/nextjs-react-expert/SKILL.md +99 -698
  107. package/.agent/skills/nodejs-best-practices/SKILL.md +498 -559
  108. package/.agent/skills/observability/SKILL.md +293 -330
  109. package/.agent/skills/parallel-agents/SKILL.md +96 -122
  110. package/.agent/skills/performance-profiling/SKILL.md +217 -254
  111. package/.agent/skills/plan-writing/SKILL.md +92 -118
  112. package/.agent/skills/platform-engineer/SKILL.md +97 -123
  113. package/.agent/skills/playwright-best-practices/SKILL.md +137 -162
  114. package/.agent/skills/powershell-windows/SKILL.md +112 -146
  115. package/.agent/skills/project-idioms/SKILL.md +87 -0
  116. package/.agent/skills/python-patterns/SKILL.md +15 -35
  117. package/.agent/skills/python-pro/SKILL.md +148 -754
  118. package/.agent/skills/react-specialist/SKILL.md +123 -827
  119. package/.agent/skills/readme-builder/SKILL.md +23 -85
  120. package/.agent/skills/realtime-patterns/SKILL.md +269 -304
  121. package/.agent/skills/red-team-tactics/SKILL.md +18 -51
  122. package/.agent/skills/rust-pro/SKILL.md +623 -701
  123. package/.agent/skills/seo-fundamentals/SKILL.md +129 -154
  124. package/.agent/skills/server-management/SKILL.md +164 -190
  125. package/.agent/skills/shadcn-ui-expert/SKILL.md +181 -206
  126. package/.agent/skills/skill-creator/SKILL.md +24 -56
  127. package/.agent/skills/sql-pro/SKILL.md +579 -633
  128. package/.agent/skills/supabase-postgres-best-practices/SKILL.md +35 -66
  129. package/.agent/skills/swiftui-expert/SKILL.md +151 -176
  130. package/.agent/skills/systematic-debugging/SKILL.md +92 -118
  131. package/.agent/skills/tailwind-patterns/SKILL.md +516 -576
  132. package/.agent/skills/tdd-workflow/SKILL.md +111 -137
  133. package/.agent/skills/test-result-analyzer/SKILL.md +33 -73
  134. package/.agent/skills/testing-patterns/SKILL.md +512 -573
  135. package/.agent/skills/trend-researcher/SKILL.md +30 -71
  136. package/.agent/skills/ui-ux-pro-max/SKILL.md +8 -41
  137. package/.agent/skills/ui-ux-researcher/SKILL.md +51 -91
  138. package/.agent/skills/vue-expert/SKILL.md +127 -866
  139. package/.agent/skills/vulnerability-scanner/SKILL.md +354 -269
  140. package/.agent/skills/web-accessibility-auditor/SKILL.md +168 -193
  141. package/.agent/skills/web-design-guidelines/SKILL.md +25 -61
  142. package/.agent/skills/webapp-testing/SKILL.md +119 -145
  143. package/.agent/skills/whimsy-injector/SKILL.md +58 -132
  144. package/.agent/skills/workflow-optimizer/SKILL.md +28 -68
  145. package/.agent/workflows/api-tester.md +151 -151
  146. package/.agent/workflows/audit.md +127 -138
  147. package/.agent/workflows/brainstorm.md +110 -110
  148. package/.agent/workflows/changelog.md +112 -112
  149. package/.agent/workflows/create.md +124 -124
  150. package/.agent/workflows/debug.md +165 -189
  151. package/.agent/workflows/deploy.md +180 -189
  152. package/.agent/workflows/enhance.md +128 -151
  153. package/.agent/workflows/fix.md +114 -135
  154. package/.agent/workflows/generate.md +13 -4
  155. package/.agent/workflows/migrate.md +160 -160
  156. package/.agent/workflows/orchestrate.md +168 -168
  157. package/.agent/workflows/performance-benchmarker.md +114 -123
  158. package/.agent/workflows/plan.md +173 -173
  159. package/.agent/workflows/preview.md +80 -80
  160. package/.agent/workflows/refactor.md +161 -183
  161. package/.agent/workflows/review-ai.md +101 -129
  162. package/.agent/workflows/review.md +116 -116
  163. package/.agent/workflows/session.md +94 -94
  164. package/.agent/workflows/status.md +79 -79
  165. package/.agent/workflows/strengthen-skills.md +138 -139
  166. package/.agent/workflows/swarm.md +179 -179
  167. package/.agent/workflows/test.md +189 -211
  168. package/.agent/workflows/tribunal-backend.md +94 -113
  169. package/.agent/workflows/tribunal-database.md +95 -115
  170. package/.agent/workflows/tribunal-frontend.md +96 -118
  171. package/.agent/workflows/tribunal-full.md +93 -133
  172. package/.agent/workflows/tribunal-mobile.md +95 -119
  173. package/.agent/workflows/tribunal-performance.md +110 -133
  174. package/.agent/workflows/ui-ux-pro-max.md +122 -143
  175. package/README.md +30 -1
  176. package/bin/tribunal-kit.js +175 -12
  177. package/package.json +25 -4
  178. package/.agent/skills/api-patterns/api-style.md +0 -42
  179. package/.agent/skills/api-patterns/auth.md +0 -24
  180. package/.agent/skills/api-patterns/documentation.md +0 -26
  181. package/.agent/skills/api-patterns/graphql.md +0 -41
  182. package/.agent/skills/api-patterns/rate-limiting.md +0 -31
  183. package/.agent/skills/api-patterns/response.md +0 -37
  184. package/.agent/skills/api-patterns/rest.md +0 -40
  185. package/.agent/skills/api-patterns/security-testing.md +0 -122
  186. package/.agent/skills/api-patterns/trpc.md +0 -41
  187. package/.agent/skills/api-patterns/versioning.md +0 -22
  188. package/.agent/skills/app-builder/agent-coordination.md +0 -71
  189. package/.agent/skills/app-builder/feature-building.md +0 -53
  190. package/.agent/skills/app-builder/project-detection.md +0 -34
  191. package/.agent/skills/app-builder/scaffolding.md +0 -118
  192. package/.agent/skills/app-builder/tech-stack.md +0 -40
  193. package/.agent/skills/architecture/context-discovery.md +0 -43
  194. package/.agent/skills/architecture/examples.md +0 -94
  195. package/.agent/skills/architecture/pattern-selection.md +0 -68
  196. package/.agent/skills/architecture/patterns-reference.md +0 -50
  197. package/.agent/skills/architecture/trade-off-analysis.md +0 -77
  198. package/.agent/skills/brainstorming/dynamic-questioning.md +0 -360
  199. package/.agent/skills/database-design/database-selection.md +0 -43
  200. package/.agent/skills/database-design/indexing.md +0 -39
  201. package/.agent/skills/database-design/migrations.md +0 -48
  202. package/.agent/skills/database-design/optimization.md +0 -36
  203. package/.agent/skills/database-design/orm-selection.md +0 -30
  204. package/.agent/skills/database-design/schema-design.md +0 -56
  205. package/.agent/skills/frontend-design/animation-guide.md +0 -331
  206. package/.agent/skills/frontend-design/color-system.md +0 -329
  207. package/.agent/skills/frontend-design/decision-trees.md +0 -418
  208. package/.agent/skills/frontend-design/motion-graphics.md +0 -306
  209. package/.agent/skills/frontend-design/typography-system.md +0 -363
  210. package/.agent/skills/frontend-design/ux-psychology.md +0 -1116
  211. package/.agent/skills/frontend-design/visual-effects.md +0 -383
  212. package/.agent/skills/intelligent-routing/router-manifest.md +0 -65
  213. package/.agent/skills/mobile-design/decision-trees.md +0 -516
  214. package/.agent/skills/mobile-design/mobile-backend.md +0 -491
  215. package/.agent/skills/mobile-design/mobile-color-system.md +0 -420
  216. package/.agent/skills/mobile-design/mobile-debugging.md +0 -122
  217. package/.agent/skills/mobile-design/mobile-design-thinking.md +0 -357
  218. package/.agent/skills/mobile-design/mobile-navigation.md +0 -458
  219. package/.agent/skills/mobile-design/mobile-performance.md +0 -767
  220. package/.agent/skills/mobile-design/mobile-testing.md +0 -356
  221. package/.agent/skills/mobile-design/mobile-typography.md +0 -433
  222. package/.agent/skills/mobile-design/platform-android.md +0 -666
  223. package/.agent/skills/mobile-design/platform-ios.md +0 -561
  224. package/.agent/skills/mobile-design/touch-psychology.md +0 -537
  225. package/.agent/skills/nextjs-react-expert/1-async-eliminating-waterfalls.md +0 -312
  226. package/.agent/skills/nextjs-react-expert/2-bundle-bundle-size-optimization.md +0 -240
  227. package/.agent/skills/nextjs-react-expert/3-server-server-side-performance.md +0 -490
  228. package/.agent/skills/nextjs-react-expert/4-client-client-side-data-fetching.md +0 -264
  229. package/.agent/skills/nextjs-react-expert/5-rerender-re-render-optimization.md +0 -581
  230. package/.agent/skills/nextjs-react-expert/6-rendering-rendering-performance.md +0 -432
  231. package/.agent/skills/nextjs-react-expert/7-js-javascript-performance.md +0 -684
  232. package/.agent/skills/nextjs-react-expert/8-advanced-advanced-patterns.md +0 -150
  233. package/.agent/skills/vulnerability-scanner/checklists.md +0 -121
package/.agent/skills/i18n-localization/SKILL.md CHANGED
@@ -1,138 +1,113 @@
1
- ---
2
- name: i18n-localization
3
- description: Internationalization (i18n) and localization mastery. Abstracting hardcoded strings, managing JSON/YAML translation dictionaries, bidirectional routing (RTL support for Arabic/Hebrew), Pluralization algorithms, date/currency formatting, and SSR locale detection in Next.js/React. Use when preparing an application for global multilingual scaling.
4
- allowed-tools: Read, Write, Edit, Glob, Grep
5
- version: 2.0.0
6
- last-updated: 2026-04-02
7
- applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
8
- ---
9
-
10
- # i18n & Localization — Global Scale Mastery
11
-
12
- > Translating text is easy. Localizing variables, dates, plurals, and reading directions is complex.
13
- > Do not build your own translation hash-map engine. It will break on Arabic plurals.
14
-
15
- ---
16
-
17
- ## 1. The i18n Architecture (Next.js / React)
18
-
19
- Do not hardcode strings inside UI components. Use a standardized library (e.g., `next-intl` or `react-i18next`).
20
-
21
- ### Step 1: Dictionary Abstraction
22
- ```json
23
- // messages/en.json
24
- {
25
- "Dashboard": {
26
- "welcomeMessage": "Welcome back, {name}!",
27
- "unreadAlerts": "{count, plural, =0 {No unread alerts} one {You have 1 unread alert} other {You have # unread alerts}}"
28
- }
29
- }
30
- ```
31
-
32
- ### Step 2: Component Implementation
33
- ```tsx
34
- // ❌ BAD: Hardcoded English text and manual variable interpolation
35
- export function Header({ user, alertCount }) {
36
- return <h1>Welcome back, {user.name}! You have {alertCount} alerts.</h1>;
37
- }
38
-
39
- // ✅ GOOD: i18n Abstraction (using next-intl)
40
- import { useTranslations } from 'next-intl';
41
-
42
- export function Header({ user, alertCount }) {
43
- const t = useTranslations('Dashboard');
44
-
45
- return (
46
- <header>
47
- <h1>{t('welcomeMessage', { name: user.name })}</h1>
48
- <p>{t('unreadAlerts', { count: alertCount })}</p>
49
- </header>
50
- );
51
- }
52
- ```
53
-
54
- ---
55
-
56
- ## 2. Advanced Native Formatting (`Intl`)
57
-
58
- Do not install `moment.js` or write massive regex string parsers to format currencies in Euros vs Dollars. The browser handles this natively with the `Intl` API.
59
-
60
- ```typescript
61
- // Data/Currency Formatting correctly tied to the active locale
62
- const locale = 'de-DE';
63
-
64
- // ✅ Currency
65
- const price = new Intl.NumberFormat(locale, { style: 'currency', currency: 'EUR' }).format(1200.50);
66
- // Output in Germany: "1.200,50 €"
67
-
68
- // ✅ Dates
69
- const date = new Intl.DateTimeFormat(locale, { dateStyle: 'full' }).format(new Date());
70
- // Output in Germany: "Freitag, 2. April 2026"
71
-
72
- // ✅ Relative Time
73
- const rtf = new Intl.RelativeTimeFormat(locale, { numeric: 'auto' });
74
- rtf.format(-2, 'day'); // Output: "vorgestern" (the day before yesterday)
75
- ```
76
-
77
- ---
78
-
79
- ## 3. Bidirectional Architecture (RTL)
80
-
81
- For languages like Arabic and Hebrew, the UI must fundamentally flip horizontally. Right-To-Left (RTL) breaks standard CSS `marginLeft` and `marginRight`.
82
-
83
- **The Solution:** Logical CSS Properties.
84
- Tailwind v4 (and modern CSS) natively supports logical direction.
85
-
86
- ```css
87
- /* ❌ BAD: Hardcoded physical space */
88
- .btn { margin-left: 10px; } /* Will break layout in Hebrew */
89
-
90
- /* ✅ GOOD: Logical spacing (Tailwind: ms-4, me-4) */
91
- .btn { margin-inline-start: 10px; } /* Automatically flips in RTL mode */
92
- ```
93
-
94
- *In React HTML tag:* `<html lang="ar" dir="rtl">`
95
-
96
- ---
97
-
98
- ## 4. Routing and SSR Detection
99
-
100
- Users should not face English UI natively in Japan. Detect their browser headers at the edge routing layer.
101
-
102
- In Next.js Middleware:
103
- 1. Parse the incoming `Accept-Language` header.
104
- 2. Intercept requests to `/dashboard`.
105
- 3. Rewrite URL to the detected locale (e.g., `/ja/dashboard`).
106
-
107
- ---
108
-
109
- ## 🤖 LLM-Specific Traps (i18n)
110
-
111
- 1. **Building Custom Maps:** AI writes generic `const dict = { en: "Hello", es: "Hola" }` and queries it via `dict[locale]`. This fundamentally fails for plurals, interpolation, and rich text. Use standard libraries.
112
- 2. **Ignoring Plural Rules:** English has 2 plural forms (singular, plural). Arabic has 6 (zero, one, two, few, many, other). Hallucinating `count === 1 ? 'apple' : 'apples'` logic breaks internationally. Ensure ICU message formatting.
113
- 3. **Physical CSS Layouts:** Writing `ml-4` or `pr-2` (margin-left, padding-right) in Tailwind. Standardize exclusively on `ms-4` (margin-start) and `pe-2` (padding-end) to guarantee RTL flip compliance.
114
- 4. **Hardcoded Date Formats:** AI using `date.toLocaleDateString('en-US')` globally inside an i18n abstraction library, overriding the dynamic user locality entirely.
115
- 5. **Component Cracking for Rich Text:** The AI tries to translate "Click *here* to login" by breaking it into 3 separate translation keys (Start, Link, End). This destroys translator context. Modern libraries support `t.rich('key', { span: (chunks) => <span>{chunks}</span> })`.
116
- 6. **Server vs Client Disconnect:** AI suggests using a React Context `LocaleProvider` heavily in Next.js Server Components. SSR apps must extract locale explicitly from the URL route (`params.locale`), not React Context.
117
- 7. **Dictionary Bloat:** Trying to load a massive 5MB `global.json` translation file on initial boot, completely destroying First Contentful Paint. AI must segment routing into domain namespaces (e.g., `Checkout.json`).
118
- 8. **Locale Fallbacks Missing:** Failing to set `en` as the default fallback logic when a key is missing in the requested language, causing catastrophic `undefined` crashes on runtime rendering.
119
- 9. **Translating Variable Identities:** Accidentally translating JSON mapping keys or CSS classes inside the codebase when attempting to internationalize display text.
120
- 10. **Timezone Blindness:** Assuming formatting a DateTime automatically translates the underlying timezone shift. Timezone and Locale are two distinct configurations. Displaying local time requires tracking client offset via timezone context.
121
-
122
- ---
123
-
124
- ## 🏛️ Tribunal Integration
125
-
126
- ### ✅ Pre-Flight Self-Audit
127
- ```
128
- ✅ Are strings fully abstracted into standard JSON/YAML dictionaries using ICU format?
129
- ✅ Is variable interpolation utilizing standard library bindings rather than raw string concatenation?
130
- ✅ Have pluralization logic been delegated to the i18n engine to support multi-form languages?
131
- ✅ Are physical CSS layouts stripped in favor of Logical Properties (e.g., `start`, `end`, `margin-inline`)?
132
- ✅ Has the `<html dir="rtl">` tag generation been integrated for Right-To-Left language requests?
133
- ✅ Is data formatting (dates, currency, relative time) natively executed via target-aware `Intl` APIs?
134
- ✅ Did I ensure Rich-Text translations (links within blocks) remain unified in one single translation key?
135
- ✅ Is Next.js routing actively leveraging `[locale]` parameters accurately in SSR domains?
136
- ✅ Are JSON translation files segmented logically by namespace to prevent massive client-side bloat?
137
- ✅ Did I enforce strict error-bypassing fallback logic to default language upon missing translation keys?
138
- ```
1
+ ---
2
+ name: i18n-localization
3
+ description: Internationalization (i18n) and localization mastery. Abstracting hardcoded strings, managing JSON/YAML translation dictionaries, bidirectional routing (RTL support for Arabic/Hebrew), Pluralization algorithms, date/currency formatting, and SSR locale detection in Next.js/React. Use when preparing an application for global multilingual scaling.
4
+ allowed-tools: Read, Write, Edit, Glob, Grep
5
+ version: 2.0.0
6
+ last-updated: 2026-04-02
7
+ applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
8
+ ---
9
+
10
+ ## Hallucination Traps (Read First)
11
+ - ❌ Concatenating translated strings (`'Hello ' + name`) -> ✅ Use interpolation: `t('greeting', { name })` to handle word order differences
12
+ - ❌ Hardcoding date/number formats -> ✅ Use `Intl.DateTimeFormat` and `Intl.NumberFormat` with the user's locale
13
+ - ❌ Assuming all languages read left-to-right -> ✅ Arabic, Hebrew, Farsi are RTL; use CSS `dir='auto'` and logical properties
14
+ - ❌ Using string length for validation on translated text -> ✅ Translations can be 30-200% longer than English; design for expansion
15
+
16
+ ---
17
+
18
+
19
+ # i18n & Localization — Global Scale Mastery
20
+
21
+ ---
22
+
23
+ ## 1. The i18n Architecture (Next.js / React)
24
+
25
+ Do not hardcode strings inside UI components. Use a standardized library (e.g., `next-intl` or `react-i18next`).
26
+
27
+ ### Step 1: Dictionary Abstraction
28
+ ```json
29
+ // messages/en.json
30
+ {
31
+ "Dashboard": {
32
+ "welcomeMessage": "Welcome back, {name}!",
33
+ "unreadAlerts": "{count, plural, =0 {No unread alerts} one {You have 1 unread alert} other {You have # unread alerts}}"
34
+ }
35
+ }
36
+ ```
37
+
38
+ ### Step 2: Component Implementation
39
+ ```tsx
40
+ // ❌ BAD: Hardcoded English text and manual variable interpolation
41
+ export function Header({ user, alertCount }) {
42
+ return <h1>Welcome back, {user.name}! You have {alertCount} alerts.</h1>;
43
+ }
44
+
45
+ // ✅ GOOD: i18n Abstraction (using next-intl)
46
+ import { useTranslations } from 'next-intl';
47
+
48
+ export function Header({ user, alertCount }) {
49
+ const t = useTranslations('Dashboard');
50
+
51
+ return (
52
+ <header>
53
+ <h1>{t('welcomeMessage', { name: user.name })}</h1>
54
+ <p>{t('unreadAlerts', { count: alertCount })}</p>
55
+ </header>
56
+ );
57
+ }
58
+ ```
59
+
60
+ ---
61
+
62
+ ## 2. Advanced Native Formatting (`Intl`)
63
+
64
+ Do not install `moment.js` or write massive regex string parsers to format currencies in Euros vs Dollars. The browser handles this natively with the `Intl` API.
65
+
66
+ ```typescript
67
+ // Data/Currency Formatting correctly tied to the active locale
68
+ const locale = 'de-DE';
69
+
70
+ // ✅ Currency
71
+ const price = new Intl.NumberFormat(locale, { style: 'currency', currency: 'EUR' }).format(1200.50);
72
+ // Output in Germany: "1.200,50 €"
73
+
74
+ // ✅ Dates
75
+ const date = new Intl.DateTimeFormat(locale, { dateStyle: 'full' }).format(new Date());
76
+ // Output in Germany: "Freitag, 2. April 2026"
77
+
78
+ // ✅ Relative Time
79
+ const rtf = new Intl.RelativeTimeFormat(locale, { numeric: 'auto' });
80
+ rtf.format(-2, 'day'); // Output: "vorgestern" (the day before yesterday)
81
+ ```
82
+
83
+ ---
84
+
85
+ ## 3. Bidirectional Architecture (RTL)
86
+
87
+ For languages like Arabic and Hebrew, the UI must fundamentally flip horizontally. Right-To-Left (RTL) breaks standard CSS `marginLeft` and `marginRight`.
88
+
89
+ **The Solution:** Logical CSS Properties.
90
+ Tailwind v4 (and modern CSS) natively supports logical direction.
91
+
92
+ ```css
93
+ /* ❌ BAD: Hardcoded physical space */
94
+ .btn { margin-left: 10px; } /* Will break layout in Hebrew */
95
+
96
+ /* ✅ GOOD: Logical spacing (Tailwind: ms-4, me-4) */
97
+ .btn { margin-inline-start: 10px; } /* Automatically flips in RTL mode */
98
+ ```
99
+
100
+ *In React HTML tag:* `<html lang="ar" dir="rtl">`
101
+
102
+ ---
103
+
104
+ ## 4. Routing and SSR Detection
105
+
106
+ Users should not face English UI natively in Japan. Detect their browser headers at the edge routing layer.
107
+
108
+ In Next.js Middleware:
109
+ 1. Parse the incoming `Accept-Language` header.
110
+ 2. Intercept requests to `/dashboard`.
111
+ 3. Rewrite URL to the detected locale (e.g., `/ja/dashboard`).
112
+
113
+ ---
package/.agent/skills/intelligent-routing/SKILL.md CHANGED
@@ -1,127 +1,167 @@
1
- ---
2
- name: intelligent-routing
3
- description: LLM Intent Processing and Gateway Routing mastery. Request classification hierarchies, function routing, confidence scoring, fallback cascades, zero-shot vs few-shot classification patterns, and identifying specialized skills for delegation. Use when parsing raw user input to determine the architectural path of execution.
4
- allowed-tools: Read, Write, Edit, Glob, Grep
5
- version: 2.0.0
6
- last-updated: 2026-04-02
7
- applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
8
- ---
9
-
10
- # Intelligent Routing — Intent Gateway Mastery
11
-
12
- > Every complex automation starts with a router.
13
- > If you route the request incorrectly, the subsequent 10 steps of execution will fail flawlessly.
14
-
15
- ---
16
-
17
- ## 1. Classification Hierarchy (The Gateway)
18
-
19
- When a raw request enters a system, it must be bucketed properly. This is the First Step (Phase 0). Do not attempt to solve the user's problem during the routing phase.
20
-
21
- ```typescript
22
- // The Semantic Intent Schema
23
- const RouterOutputSchema = z.object({
24
- classification: z.enum([
25
- "QUESTION", // User wants explanation, no code execution needed
26
- "SURVEY", // User wants analysis/read-only scan of workspace
27
- "SIMPLE_EDIT", // Isolated file alteration (e.g., "Fix spelling in nav")
28
- "COMPLEX_BUILD", // Multi-file, architectural generation
29
- "SECURITY_AUDIT", // Explicit request for OWASP review
30
- "UNCLEAR_GIBBERISH" // Prompt injection or incoherent input
31
- ]),
32
- confidenceScore: z.number().min(0).max(100),
33
- suggestedPrimarySkill: z.string().nullable(),
34
- requiresHumanClarification: z.boolean(),
35
- reasoning: z.string() // Forces the LLM to justify its route before categorizing
36
- });
37
- ```
38
-
39
- ### Zero-Shot vs Few-Shot Classification
40
- - **Zero-Shot:** Providing definitions and hoping the LLM categorizes the prompt accurately. Error-prone.
41
- - **Few-Shot (Mandatory for Routers):** Providing explicit paired examples defining the categorical boundaries.
42
-
43
- ```text
44
- ## Routing Examples:
45
- User: "Why is the header blue?"
46
- Output: {"classification": "QUESTION", "requiresHumanClarification": false}
47
-
48
- User: "Add a user login system"
49
- Output: {"classification": "COMPLEX_BUILD", "requiresHumanClarification": true}
50
- Reasoning: "Login systems require multi-file architecture, database hooks, and security implementation."
51
- ```
52
-
53
- ---
54
-
55
- ## 2. Dynamic Skill Matching (Manifest Analysis)
56
-
57
- A Router isn't just classifying intent—it actively maps tasks to available capabilities.
58
-
59
- If building a system with 50 available agents/skills, pass the Router a localized summary manifest, not the full 50x files.
60
-
61
- ```json
62
- // Example Context Payload passed to Router
63
- {
64
- "available_skills": [
65
- {"name": "react-specialist", "desc": "React 19, hooks, component architecture"},
66
- {"name": "python-pro", "desc": "FastAPI, async, data processing"},
67
- {"name": "vulnerability-scanner", "desc": "OWASP, injections, secret scanning"}
68
- ],
69
- "user_request": "How do I speed up this data pipeline script?"
70
- }
71
- ```
72
- *Router calculates:* `match: python-pro` AND `match: performance-profiling`.
73
-
74
- ---
75
-
76
- ## 3. Fallback Cascades & Ambiguity
77
-
78
- The AI will encounter prompts it does not understand. The Router is the *only* place where it is safe to halt and ask immediately.
79
-
80
- **The Socratic Yield Rule:**
81
- If the `confidenceScore` of a categorization is `< 85`, the router MUST yield back to the user with a clarifying question instead of guessing the intent.
82
-
83
- *User:* "Fix the thing."
84
- *Router Action (Incorrect):* Assume they mean standard linter execution and run scripts.
85
- *Router Action (Correct):* Halt. "Which file or feature are you referring to?"
86
-
87
- ---
88
-
89
- ## 4. Bounding the Exploder Pattern
90
-
91
- Certain requests sound simple but require massive execution matrices (The "Exploder" pattern).
92
- *User:* "Translate my entire app to French."
93
-
94
- The Router must recognize execution scales. If an execution requires touching >10 files, the Router must switch the system into `PLANNING_MODE` to generate an itinerary, rather than attempting an outright sequential execution.
95
-
96
- ---
97
-
98
- ## 🤖 LLM-Specific Traps (Intelligent Routing)
99
-
100
- 1. **Solving in the Router:** An LLM prompted to "Route this coding request" often replies with the actual finalized code rather than selecting the routing node. Stiffly enforce JSON outputs via schema constraint.
101
- 2. **Zero-Shot Halucination:** The router guesses an intent bucket that isn't functionally defined (e.g., returning `classification: "DATABASE_MODE"` when that isn't a valid system enum).
102
- 3. **Skill Name Invention:** Suggesting the invocation of a skill that doesn't exist (`suggestedSkill: "docker-expert"`) instead of matching against the explicitly provided manifest of available internal skills.
103
- 4. **Ignoring Confidence Thresholds:** Proceeding with architectural execution even when the user's prompt is completely ambiguous, resulting in 5 wasted LLM token loops.
104
- 5. **The God-Agent Fallback:** Categorizing complex requests into generic root workflows instead of isolating the exact specialist (e.g., dispatching `app-builder` when `playwright-best-practices` was the explicitly requested optimization).
105
- 6. **No Escapes for Gibberish:** Failing to identify prompt-injections or copy-paste errors, trying to parse random garbled text into a functional execution path instead of instantly rejecting it.
106
- 7. **Scale Blindness:** Treating "Add a console.log" and "Create an authentication system" as identical linear tasks without switching the heavier task into a designated `PLANNING_MODE` phase.
107
- 8. **Missing Reasoning Chain:** Categorizing an intent *before* writing the justification text. Enforcing `reasoning: string` at the *top* of the output schema forces Chain-of-Thought (CoT) and drastically improves routing accuracy.
108
- 9. **Single-Node Assignment:** Assuming a complex goal only requires one skill. High-order tasks require an array of skills (e.g., `[react-specialist, tailwind-patterns, web-accessibility-auditor]`).
109
- 10. **Losing Socratic Contact:** Halting to ask the user a question, but not tracking the context so that when the user replies "Oh I meant the login page", the router forgets the initial objective.
110
-
111
- ---
112
-
113
- ## 🏛️ Tribunal Integration
114
-
115
- ### ✅ Pre-Flight Self-Audit
116
- ```
117
- ✅ Are routing outputs strictly constrained to JSON Enums (Zod / Schema validation)?
118
- ✅ Does the schema demand `reasoning` be printed *before* the definitive classification (CoT)?
119
- ✅ Have explicit Few-Shot examples been provided to anchor the categorical definitions?
120
- ✅ Are available skills mapped correctly using a localized manifest provided to the prompt?
121
- ✅ Does the router explicitly reject or ask for clarity against ambiguous requests?
122
- ✅ Is there a confidence threshold (e.g., < 85%) triggering the Socratic Gate yield?
123
- ✅ Does the router correctly identify 'Exploder' tasks scaling >10 files and force `PLANNING_MODE`?
124
- ✅ Did I prevent the LLM from attempting to solve the underlying code problem directly in the routing stage?
125
- ✅ Can the router match a request to *multiple* synergistic skills rather than just one?
126
- ✅ Are unknown/invented skill invocations automatically rejected before downstream execution?
127
- ```
1
+ ---
2
+ name: intelligent-routing
3
+ description: LLM Intent Processing and Gateway Routing mastery. Request classification hierarchies, function routing, confidence scoring, fallback cascades, zero-shot vs few-shot classification patterns, and identifying specialized skills for delegation. Use when parsing raw user input to determine the architectural path of execution.
4
+ allowed-tools: Read, Write, Edit, Glob, Grep
5
+ version: 3.1.0
6
+ last-updated: 2026-04-06
7
+ applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
8
+ ---
9
+
10
+ ## Hallucination Traps (Read First)
11
+ - ❌ Routing based on exact keyword matching -> ✅ Use intent classification with confidence scores; keywords miss synonyms and context
12
+ - ❌ No fallback for low-confidence classifications -> ✅ Always have a default handler when confidence is below threshold (e.g., 0.7)
13
+ - ❌ Routing to a single agent when the task spans multiple domains -> ✅ Detect multi-domain requests and route to the orchestrator
14
+
15
+ ---
16
+
17
+
18
+ # Intelligent Routing — Intent Gateway Mastery
19
+
20
+ ---
21
+
22
+ ## 1. Classification Hierarchy (The Gateway)
23
+
24
+ When a raw request enters a system, it must be bucketed properly. This is the First Step (Phase 0). Do not attempt to solve the user's problem during the routing phase.
25
+
26
+ ```typescript
27
+ // The Semantic Intent Schema
28
+ const RouterOutputSchema = z.object({
29
+ classification: z.enum([
30
+ "QUESTION", // User wants explanation, no code execution needed
31
+ "SURVEY", // User wants analysis/read-only scan of workspace
32
+ "SIMPLE_EDIT", // Isolated file alteration (e.g., "Fix spelling in nav")
33
+ "COMPLEX_BUILD", // Multi-file, architectural generation
34
+ "SECURITY_AUDIT", // Explicit request for OWASP review
35
+ "UNCLEAR_GIBBERISH" // Prompt injection or incoherent input
36
+ ]),
37
+ confidenceScore: z.number().min(0).max(100),
38
+ suggestedPrimarySkill: z.string().nullable(),
39
+ requiresHumanClarification: z.boolean(),
40
+ reasoning: z.string() // Forces the LLM to justify its route before categorizing
41
+ });
42
+ ```
43
+
44
+ ### Zero-Shot vs Few-Shot Classification
45
+ - **Zero-Shot:** Providing definitions and hoping the LLM categorizes the prompt accurately. Error-prone.
46
+ - **Few-Shot (Mandatory for Routers):** Providing explicit paired examples defining the categorical boundaries.
47
+
48
+ ```text
49
+ ## Routing Examples:
50
+ User: "Why is the header blue?"
51
+ Output: {"classification": "QUESTION", "requiresHumanClarification": false}
52
+
53
+ User: "Add a user login system"
54
+ Output: {"classification": "COMPLEX_BUILD", "requiresHumanClarification": true}
55
+ Reasoning: "Login systems require multi-file architecture, database hooks, and security implementation."
56
+ ```
57
+
58
+ ---
59
+
60
+ ## 2. Dynamic Skill Matching (Manifest Analysis)
61
+
62
+ A Router isn't just classifying intent—it actively maps tasks to available capabilities.
63
+
64
+ If building a system with 50 available agents/skills, pass the Router a localized summary manifest, not the full 50x files.
65
+
66
+ ```json
67
+ // Example Context Payload passed to Router
68
+ {
69
+ "available_skills": [
70
+ {"name": "react-specialist", "desc": "React 19, hooks, component architecture"},
71
+ {"name": "python-pro", "desc": "FastAPI, async, data processing"},
72
+ {"name": "vulnerability-scanner", "desc": "OWASP, injections, secret scanning"}
73
+ ],
74
+ "user_request": "How do I speed up this data pipeline script?"
75
+ }
76
+ ```
77
+ *Router calculates:* `match: python-pro` AND `match: performance-profiling`.
78
+
79
+ ---
80
+
81
+ ## 3. Fallback Cascades & Ambiguity
82
+
83
+ The AI will encounter prompts it does not understand. The Router is the *only* place where it is safe to halt and ask immediately.
84
+
85
+ **The Socratic Yield Rule:**
86
+ If the `confidenceScore` of a categorization is `< 85`, the router MUST yield back to the user with a clarifying question instead of guessing the intent.
87
+
88
+ *User:* "Fix the thing."
89
+ *Router Action (Incorrect):* Assume they mean standard linter execution and run scripts.
90
+ *Router Action (Correct):* Halt. "Which file or feature are you referring to?"
91
+
92
+ ---
93
+
94
+ ## 4. Bounding the Exploder Pattern
95
+
96
+ Certain requests sound simple but require massive execution matrices (The "Exploder" pattern).
97
+ *User:* "Translate my entire app to French."
98
+
99
+ The Router must recognize execution scales. If an execution requires touching >10 files, the Router must switch the system into `PLANNING_MODE` to generate an itinerary, rather than attempting an outright sequential execution.
100
+
101
+ ---
102
+
103
+ ## Intelligent Routing: Skill Manifest
104
+ This file contains all available skills and workflows as a condensed index for the pre-router.
105
+
106
+ |Skill Name|Description|
107
+ |---|---|
108
+ |`agent-organizer`|Senior agent organizer with expertise in assembling and coordinating multi-agent teams. Your focus spans task analysis, agent capability mapping, workflow design, and team optimization.|
109
+ |`agentic-patterns`|AI agent design principles. Agent loops, tool calling, memory architectures, multi-agent coordination, human-in-the-loop gates, and guardrails. Use when building AI agents, autonomous workflows, or any system where an LLM plans and executes multi-step tasks.|
110
+ |`api-patterns`|API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.|
111
+ |`app-builder`|Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.|
112
+ |`architecture`|Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.|
113
+ |`bash-linux`|Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.|
114
+ |`behavioral-modes`|AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.|
115
+ |`brainstorming`|Socratic questioning protocol + user communication. MANDATORY for complex requests, new features, or unclear requirements. Includes progress reporting and error handling.|
116
+ |`clean-code`|Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments|
117
+ |`code-review-checklist`|Code review guidelines covering code quality, security, and best practices.|
118
+ |`config-validator`|Self-validation skill for the .agent directory. Checks that all agents, skills, workflows, and scripts referenced across the system actually exist and are consistent. Use after modifying agent configuration files.|
119
+ |`csharp-developer`|Senior C# developer with mastery of .NET 8+ and the Microsoft ecosystem. Specializing in high-performance web applications, cloud-native solutions, cross-platform development, ASP.NET Core, Blazor, and Entity Framework Core.|
120
+ |`database-design`|Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.|
121
+ |`deployment-procedures`|Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.|
122
+ |`devops-engineer`|Senior DevOps engineer with expertise in building scalable, automated infrastructure and deployment pipelines. Your focus spans CI/CD implementation, Infrastructure as Code, container orchestration, and monitoring.|
123
+ |`devops-incident-responder`|Senior DevOps incident responder with expertise in managing critical production incidents, performing rapid diagnostics, and implementing permanent fixes. Reduces MTTR and builds resilient systems.|
124
+ |`documentation-templates`|Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.|
125
+ |`dotnet-core-expert`|Senior .NET Core expert with expertise in .NET 10, C# 14, and modern minimal APIs. Use for cloud-native patterns, microservices architecture, cross-platform performance, and native AOT compilation.|
126
+ |`edge-computing`|Edge function design principles. Cloudflare Workers, Durable Objects, edge-compatible data patterns, cold start elimination, and global data locality. Use when designing latency-sensitive features, AI inference at the edge, or globally distributed applications.|
127
+ |`frontend-design`|Design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.|
128
+ |`game-development`|Game development orchestrator. Routes to platform-specific skills based on project needs.|
129
+ |`geo-fundamentals`|Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).|
130
+ |`i18n-localization`|Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.|
131
+ |`intelligent-routing`|Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.|
132
+ |`lint-and-validate`|Linting and validation principles for code quality enforcement.|
133
+ |`llm-engineering`|LLM engineering principles for production AI systems. RAG pipeline design, vector store selection, prompt engineering, evals, and LLMOps. Use when building AI features, chat interfaces, semantic search, or any system calling an LLM API.|
134
+ |`local-first`|Local-first software principles. Offline-capable apps, CRDTs, sync engines (ElectricSQL, Replicache, Zero), conflict resolution, and the migration path from REST-first to local-first architecture. Use when building apps that need offline support, fast UI, or collaborative editing.|
135
+ |`mcp-builder`|MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.|
136
+ |`mobile-design`|Mobile-first and Spatial computing design thinking for iOS, Android, Foldables, and WebXR. Touch interaction, advanced haptics, on-device AI patterns, performance extremis. Teaches principles, not fixed values.|
137
+ |`nextjs-react-expert`|Next.js App Router and React v19+ performance optimization from Vercel Engineering. Use when building React components, optimizing performance, implementing React Compiler patterns, eliminating waterfalls, reducing JS payload, or implementing Streaming/PPR optimizations.|
138
+ |`nodejs-best-practices`|Node.js development principles and decision-making. Framework selection, async patterns, security, and architecture. Teaches thinking, not copying.|
139
+ |`observability`|Production observability principles. OpenTelemetry traces, structured logs, metrics, SLOs/SLIs/error budgets, and AI observability. Use when setting up monitoring, debugging production issues, or designing observable distributed systems.|
140
+ |`parallel-agents`|Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.|
141
+ |`performance-profiling`|Performance profiling principles. Measurement, analysis, and optimization techniques.|
142
+ |`plan-writing`|Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.|
143
+ |`platform-engineer`|Senior platform engineer with deep expertise in building internal developer platforms, self-service infrastructure, and developer portals. Reduces cognitive load and accelerates software delivery.|
144
+ |`powershell-windows`|PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.|
145
+ |`python-patterns`|Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying.|
146
+ |`python-pro`|Senior Python developer (3.11+) specializing in idiomatic, type-safe, and performant Python. Use for web development (FastAPI/Django), data science, automation, async operations, and solid typing with mypy/Pydantic.|
147
+ |`react-specialist`|Senior React specialist (React 18+) focusing on advanced patterns, state management, performance optimization, and production architectures (Next.js/Remix).|
148
+ |`realtime-patterns`|Real-time and collaborative application patterns. WebSockets, Server-Sent Events for AI streaming, CRDTs for conflict-free collaboration, presence, and sync engines. Use when building live collaboration, AI streaming UIs, live dashboards, or multiplayer features.|
149
+ |`red-team-tactics`|Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.|
150
+ |`rust-pro`|Master Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems programming. Expert in the latest Rust ecosystem including Tokio, axum, and cutting-edge crates. Use PROACTIVELY for Rust development, performance optimization, or systems programming.|
151
+ |`seo-fundamentals`|SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles.|
152
+ |`server-management`|Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands.|
153
+ |`sql-pro`|Senior SQL developer across major databases (PostgreSQL, MySQL, SQL Server, Oracle). Use for complex query design, performance optimization, indexing strategies, CTEs, window functions, and schema architecture.|
154
+ |`systematic-debugging`|4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.|
155
+ |`tailwind-patterns`|Tailwind CSS v4+ principles for extreme frontend engineering. CSS-first configuration, scroll-driven animations, logical properties, advanced container style queries, and `@property` Houdini patterns.|
156
+ |`tdd-workflow`|Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.|
157
+ |`test-result-analyzer`|Ingests test logs and identifies root causes across multiple failing test files. Provides actionable fix recommendations.|
158
+ |`testing-patterns`|Testing patterns and principles. Unit, integration, mocking strategies.|
159
+ |`trend-researcher`|Creative muse and design trend analyzer for modern web/mobile interfaces.|
160
+ |`ui-ux-pro-max`|Plan and implement cutting-edge advanced UI/UX. Create distinctive, production-grade frontend interfaces with high design quality.|
161
+ |`ui-ux-researcher`|Expert auditor for accessibility, cognitive load, and premium design heuristics.|
162
+ |`vue-expert`|Vue 3 Composition API and modern Vue ecosystem expert. Use when building Vue applications, optimizing reactivity, component architecture, Nuxt 3 development, performance tuning, and State Management (Pinia).|
163
+ |`vulnerability-scanner`|Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.|
164
+ |`web-design-guidelines`|Review UI code for Next-Generation Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".|
165
+ |`webapp-testing`|Web application testing principles. E2E, Playwright, deep audit strategies.|
166
+ |`whimsy-injector`|Micro-delight generator for frontend interfaces. Suggests and implements subtle animations, playful transitions, and interaction polish across any frontend stack.|
167
+ |`workflow-optimizer`|Analyzes agent tool-calling patterns and task execution efficiency to suggest process improvements.|