tribunal-kit 5.8.5 → 6.0.0

package/.agent/skills/swiftui-expert/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: swiftui-expert
 description: SwiftUI development mastery. View architecture, state management (@State, @Binding, @Environment, @Observable), performance optimization (identifiable loops, implicit vs explicit animations), architectural patterns (MVVM vs TCA), and iOS-native UX paradigms. Use when writing native Apple platforms code.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 2.0.0
-last-updated: 2026-04-02
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - mobile-design
+  - building-native-ui
+  - apple-design
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# SwiftUI Expert — Native Apple Platforms Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before writing or refactoring SwiftUI components, you MUST inspect:
+1. Modern Observable Macro (iOS 17+) (Section 43) → Use `@Observable` macro for reference types; ban legacy `@StateObject` / `@Published` boilerplate in iOS 17+ code
+2. Identifiable Protocol in ForEach (Section 125) → Conform model types to `Identifiable` for `ForEach`; ban integer index iteration (`0..<items.count`)
+3. NavigationStack Standard (Section 18) → Use `NavigationStack` or `NavigationSplitView`; ban deprecated legacy `NavigationView`
+
 ## Hallucination Traps (Read First)
 
 - ❌ Using `@State` for shared data between views -> ✅ `@State` is local to a view; use `@Binding`, `@Environment`, or `@Observable` for sharing

package/.agent/skills/swiss-design/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: swiss-design
 description: International Typographic Style (Swiss Design) principles for web interfaces. Strict grid discipline, asymmetric layouts, bold typographic contrast, flush-left un-justified text, and mathematical negative space.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Print-Inspired UI & Swiss Typography
-  tier: pro
-  co-requires: [better-typography, baseline-ui, industrial-brutalist-ui]
-  trigger-signals:
-    strong: [swiss-design, Swiss style UI, International Typographic Style, grid discipline, Helvetica layout, print inspired web]
-    weak: [swiss layout, grid UI]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - typeset
+  - baseline-ui
+  - better-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Swiss Design — International Typographic Style for Web
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before applying Swiss Design aesthetics, you MUST inspect:
+1. `DESIGN.md` / `index.css` → Check grid system tokens and grotesque font declarations (Helvetica, Inter, Geist)
+2. Asymmetric Structural Balance (Section 32) → Align headings and content to strong left vertical axes; strictly prohibit `text-align: justify` or centered body paragraphs
+3. Mathematical Section Numbering (Section 35) → Enforce small uppercase badges (`SECTION 01 // OVERVIEW`) with `tabular-nums`
+
 Architect pristine, print-inspired interfaces grounded in grid discipline, objective clarity, and asymmetric typographic hierarchy.
 
 ---

package/.agent/skills/system-design-pro/SKILL.md

@@ -1,17 +1,29 @@
 ---
 name: system-design-pro
 description: Industry-level system design mastery for interviews and production. The 6-step design framework, scale estimation (DAU→QPS→storage→bandwidth), core building blocks (load balancers L4/L7, CDN, caches, queues), database selection matrix, CAP Theorem applied, and reference designs for URL shortener, rate limiter, Twitter feed, distributed cache, and notification system. Use when designing systems for scale, conducting architecture reviews, or preparing system design discussions.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 1.0.0
-last-updated: 2026-06-21
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: architecture
-  tier: pro
-  trigger-signals:
-    strong: [design a system, scale estimation, CAP Theorem, rate limiter]
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - architecture
+  - database-design
+  - cloud-architect
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# System Design Pro — Industry-Level Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before designing system architecture or writing scale proposals, you MUST inspect:
+1. 6-Step Design Framework (Section 27) → Execute Clarify Scope, Scale Estimation, API Definition, Data Model, High-Level Design, and Deep Dive in exact order
+2. Quantified Scale Estimation (Section 65) → Calculate read/write QPS, storage growth, and bandwidth before selecting database or caching tiers
+3. Monolith First Rule (Section 17) → Start with modular monolith for $<10\text{K}$ RPM; ban introducing microservices or sharding prematurely
+
 ## Hallucination Traps (Read First)
 
 - ❌ "Just use microservices" for <10K RPM → ✅ Microservices add operational complexity that kills small teams. Start monolith.

package/.agent/skills/systematic-debugging/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: systematic-debugging
 description: Systematic debugging framework. Root-cause isolation, 4-phase methodology, hypothesis testing, log tracing, avoiding shotgun-surgery, memory allocation analysis, and empirical evidence gathering. Use when debugging complex, highly-coupled, or elusive bugs across mixed execution environments.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 2.0.0
-last-updated: 2026-04-02
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - diagnosing-bugs
+  - test-result-analyzer
+  - clean-code
+scripts-binding:
+  - .agent/scripts/test_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Systematic Debugging — Root Cause Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before debugging issues or analyzing stack traces, you MUST inspect:
+1. Single Variable Isolation (Section 15) → Change ONE variable at a time when debugging; ban shotgun debugging or multi-file edits simultaneously
+2. Deterministic Reproduction Pre-requisite (Section 29) → Write a failing deterministic test/reproduction script FIRST before modifying code logic
+3. Stack Trace Application Line Extraction (Section 98) → Trace up past `node_modules` to locate the top-most application code frame you wrote
+
 ## Hallucination Traps (Read First)
 
 - ❌ Changing multiple things at once to fix a bug -> ✅ Change ONE variable at a time; multiple changes make it impossible to identify the fix

package/.agent/skills/tailwind-patterns/SKILL.md

@@ -1,19 +1,33 @@
 ---
 name: tailwind-patterns
 description: Tailwind CSS v4+ mastery. CSS-first configuration, @theme directive, container queries, scroll-driven animations, logical properties, clamp(), fluid typography, responsive design, dark mode, custom variants, component extraction, and performance optimization. Use when styling with Tailwind, building design systems, or optimizing CSS output.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 2.0.0
-last-updated: 2026-04-01
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - baseline-ui
+  - better-colors
+  - shadcn-ui-expert
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Tailwind CSS v4+ — CSS-First Mastery
 
 ---
 
+## Mandatory Pre-Flight Context Inspection
+
+Before engineering Tailwind CSS styles or themes, you MUST inspect:
+1. CSS-First v4 Configuration (Section 19) → Use `@import "tailwindcss";` and `@theme { }` in CSS files instead of deprecated `tailwind.config.js`
+2. Viewport Height Units (Section 151) → Use `min-h-svh` (small viewport height) or `min-h-dvh` instead of broken mobile `min-h-screen`
+3. Container Query Prefix (Section 204) → Use `@sm:`, `@md:`, `@lg:` container prefixes for component-level responsiveness rather than viewport `sm:`, `md:`, `lg:`
+
+# Tailwind CSS v4+ — CSS-First Mastery
+
+---
+
 ## v4 Configuration (CSS-First)
 
 ### The @theme Directive

package/.agent/skills/taste-skill/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: taste-skill
 description: Senior UI/UX frontend skill that enforces anti-slop design decisions, motion quality, visual rhythm, micro-craft, and architectural discipline.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Design Taste & Anti-Slop Discipline
-  tier: pro
-  co-requires: [better-ui, impeccable, frontend-design]
-  trigger-signals:
-    strong: [taste-skill, design taste, anti-slop, frontend craft discipline, high taste UI]
-    weak: [taste, good design]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - better-ui
+  - impeccable
+  - baseline-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Taste Skill — Senior Design Taste & Anti-Slop Discipline
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before rendering UI components, you MUST inspect:
+1. Banned AI Clichés (Section 24) → Strictly ban purple/indigo gradients (`from-purple-600 to-indigo-600`), glowing neon borders, and floating 3D spheres
+2. Typography Rules (Section 30) → Apply negative tracking (`-0.025em`) + `text-wrap: balance` to display headings; cap body text at `65ch` max width
+3. Tactile Press Feedback (Section 39) → Enforce `:active` press feedback (`transform: scale(0.97)`) on all interactive buttons/cards
+
 Enforce senior-level design taste, anti-slop constraints, and visual craft across every component.
 
 ---

package/.agent/skills/tdd-workflow/SKILL.md

@@ -1,20 +1,31 @@
 ---
 name: tdd-workflow
 description: Test-Driven Development (TDD) mastery. Red-Green-Refactor cycles, behavior-driven design (BDD), strict mutation coverage, test doubles (mocks/stubs/spies), and avoiding test-induced design damage. Use when building complex algorithms, deep business logic, or strictly regulated systems.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Test-Driven Development & Quality Assurance
-  tier: pro
-  co-requires: [webapp-testing, clean-code]
-  trigger-signals:
-    strong: [tdd-workflow, red green refactor, test driven development, TDD, slice by slice testing, write test first]
-    weak: [write test, unit test logic]
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - testing-patterns
+  - clean-code
+  - webapp-testing
+scripts-binding:
+  - .agent/scripts/test_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # TDD Workflow — Red-Green-Refactor Mastery
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before implementing feature logic or writing unit tests, you MUST inspect:
+1. Red-Green-Refactor Cycle (Section 25) → Write failing test FIRST (Red) → minimal passing code SECOND (Green) → cleanup THIRD (Refactor)
+2. Behavior-First Assertion Rule (Section 36) → Assert public contract results (GIVEN/WHEN/THEN); ban asserting internal private fields or state
+3. IO Boundary-Only Mocking (Section 50) → Mock ONLY un-owned external boundaries (DB IO, network APIs); ban mocking domain entities or pure utils
+
+# TDD Workflow — Red-Green-Refactor Mastery
+
 Build features and fixes one slice at a time using strict Test-Driven Development (TDD) discipline.
 
 ---

package/.agent/skills/test-result-analyzer/SKILL.md

@@ -1,19 +1,31 @@
 ---
 name: test-result-analyzer
 description: Ingests test logs and identifies root causes across multiple failing test files. Provides actionable fix recommendations.
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
 skills:
   - systematic-debugging
   - testing-patterns
-version: 1.0.0
-last-updated: 2026-03-12
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+  - tdd-workflow
+scripts-binding:
+  - .agent/scripts/test_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Test Result Analyzer Skill
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before analyzing failing test logs or output traces, you MUST inspect:
+1. First Point of Failure (FPF) Isolation (Section 114) → Identify the initial root failure in execution order first; ban fixing cascading downstream failures beforehand
+2. Cluster Categorization Rule (Section 88) → Group failures by shared module/error type to resolve dozens of failures via single root fixes
+3. Literal Trace Extract Discipline (Section 257) → Quote exact Expected/Received values and line numbers strictly from actual logs; ban guessing assertion details
+
+# Test Result Analyzer Skill
+
 You are a specialist in analyzing test output — not writing tests, but _understanding why tests fail_. You turn walls of red error text into a prioritized action plan.
 
 ## When to Activate

package/.agent/skills/testing-patterns/SKILL.md

@@ -1,19 +1,33 @@
 ---
 name: testing-patterns
 description: Testing mastery across stacks. Unit testing with Jest/Vitest/pytest, integration testing, E2E with Playwright, mocking strategies, test architecture (AAA, Given-When-Then), code coverage, snapshot testing, API testing, component testing with Testing Library, and TDD workflow. Use when writing tests, designing test architecture, or improving test coverage.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 2.1.0
-last-updated: 2026-04-26
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - tdd-workflow
+  - test-result-analyzer
+  - playwright-best-practices
+scripts-binding:
+  - .agent/scripts/test_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Testing Patterns — Cross-Stack Testing Mastery
 
 ---
 
+## Mandatory Pre-Flight Context Inspection
+
+Before writing unit, integration, or component tests, you MUST inspect:
+1. AAA Pattern & Single Act Rule (Section 37) → Structure tests strictly as Arrange-Act-Assert; perform only 1 single action per test case
+2. Accessibility-First Query Hierarchy (Section 343) → Query React components by `getByRole` or `getByLabelText`; ban default `getByTestId` queries
+3. Dependency Injection Over Global Mocks (Section 268) → Prefer constructor dependency injection over global `vi.mock()` to prevent cross-test state leakage
+
+# Testing Patterns — Cross-Stack Testing Mastery
+
+---
+
 ## Test Architecture
 
 ### The Testing Pyramid

package/.agent/skills/thermo-nuclear-code-quality-review/SKILL.md

@@ -1,20 +1,31 @@
 ---
 name: thermo-nuclear-code-quality-review
 description: Run an extremely strict maintainability review for abstraction quality, giant files, spaghetti-condition growth, and architectural debt.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Ultra-Strict Code Quality Review
-  tier: pro
-  co-requires: [clean-code, codebase-design, code-review-checklist]
-  trigger-signals:
-    strong: [thermo-nuclear-code-quality-review, strict code review, maintainability audit, spaghetti code review, giant file audit, strict maintainability]
-    weak: [deep review, strict audit]
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - clean-code
+  - codebase-design
+  - code-review-checklist
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Thermo-Nuclear Code Quality Review — Zero-Tolerance Maintainability Audit
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before performing ultra-strict maintainability code audits, you MUST inspect:
+1. File Size Hard Limit Rule (300 lines max) (Section 24) → Flag any file >300 lines for immediate module decomposition
+2. Cyclomatic Nesting Limit (3 levels max) (Section 27) → Flag nested conditionals >3 levels deep; require early guard clause returns
+3. Direct Dependency Coupling Ban (Section 53) → Flag domain logic directly importing vendor SDKs or DB models instead of interface adapters
+
+# Thermo-Nuclear Code Quality Review — Zero-Tolerance Maintainability Audit
+
 Execute a ruthless, zero-tolerance code maintainability audit targeting abstraction leaks, file bloat, and spaghetti conditionals.
 
 ---

package/.agent/skills/thinking-protocol/SKILL.md

@@ -1,16 +1,28 @@
 ---
 name: thinking-protocol
 description: Tribunal Agent Kit thinking and cognitive reasoning rules. Helps agents structure their thoughts and follow protocols.
-allowed-tools: all
-version: 1.0.0
-last-updated: 2026-07-07
-applies-to-model: *
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - fabel-protocol
+  - behavioral-modes
+  - clean-code
+scripts-binding:
+  - .agent/scripts/checklist.js
+  - .agent/scripts/verify_all.js
 ---
 
-# Thinking Protocol
+# Thinking Protocol — Cognitive Reasoning Rules
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before beginning any cognitive reasoning loop, you MUST inspect:
+1. Cognitive Boundaries (Fabel Protocol) → Verify epistemic certainty levels L1 through L5
+2. Precision Budget → Scale tool calls to task complexity (Simple: 1 call, Medium: 3-5 calls, Deep: 5-10 calls)
+3. Stale Context rules → Re-read files after every edit to update internal context representation
 
 Guidelines for structural reasoning and cognitive loop execution.
 

package/.agent/skills/to-spring-or-not-to-spring/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: to-spring-or-not-to-spring
 description: Audit and decide when to use physics-based spring animations (stiffness, damping, mass) vs duration-based cubic-bezier easing curves.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Motion Physics & Animation Decisions
-  tier: pro
-  co-requires: [emil-design-eng, framer-motion-expert]
-  trigger-signals:
-    strong: [to-spring-or-not-to-spring, spring physics, spring animation vs cubic bezier, stiffness damping mass, motion physics decision]
-    weak: [spring animation, spring vs easing]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - motion-engineering
+  - framer-motion-expert
+  - 60fps-animation
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # To Spring or Not to Spring — Motion Physics Decision Matrix
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before selecting animation model (Spring vs Cubic-Bezier), you MUST inspect:
+1. Spring vs Duration Decision Matrix (Section 22) → Use Spring physics ONLY for interruptible gestures, drag, toggles, and playful badges
+2. Modal & Dropdown Rule → Use deterministic cubic-bezier curves (`cubic-bezier(0.16, 1, 0.3, 1)`) for modals, dropdowns, and route transitions
+3. Anti-Conflict Rule (Section 46) → Never specify both `duration` AND spring `stiffness/damping` parameters together in Framer Motion
+
 Decide when to use physics-driven spring models (Framer Motion / Reanimated) vs duration-based cubic-bezier easing curves.
 
 ---

package/.agent/skills/transitions-dev/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: transitions-dev
 description: Production-ready CSS transition patterns for web apps with drop-in snippets for cards, modals, dropdowns, panels, and accordions.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: CSS Transitions & Production Snippets
-  tier: pro
-  co-requires: [better-ui, micro-interaction, 60fps-animation]
-  trigger-signals:
-    strong: [transitions-dev, CSS transition snippets, card hover transition, modal transition CSS, accordion expand animation]
-    weak: [css transitions, transition snippet]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - better-ui
+  - micro-interaction
+  - 60fps-animation
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Transitions Dev — Production CSS Transition Snippets
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before implementing CSS transitions, you MUST inspect:
+1. Accordion Pattern (Section 35) → Use `grid-template-rows: 0fr -> 1fr` with `overflow: hidden` on inner wrapper instead of animating `height: auto`
+2. Modal Overlay Transitions (Section 52) → Scale modal content from `scale(0.96) translateY(8px)` with opacity
+3. Target transition properties → Enforce explicit property transitions (`transform`, `opacity`, `box-shadow`) and ban `transition: all`
+
 Drop-in, hardware-accelerated CSS transition utility classes for modern web components.
 
 ---

package/.agent/skills/trend-researcher/SKILL.md

@@ -1,20 +1,31 @@
 ---
 name: trend-researcher
 description: Creative muse and design trend analyzer for modern web/mobile interfaces.
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
 skills:
   - frontend-design
   - web-design-guidelines
   - seo-fundamentals
-version: 1.0.0
-last-updated: 2026-03-12
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Trend Researcher Skill
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before recommending design trends or visual directions, you MUST inspect:
+1. Banned AI Cliché Rule (Section 40) → Ban purple/violet gradients, generic mesh backgrounds, and un-justified left-text/right-image hero layouts
+2. WCAG 2.2 AA Contrast Compliance (Section 61) → Calculate HSL palette contrast ($\ge 4.5:1$ text, $\ge 3:1$ large text) before finalizing tokens
+3. Verified Google Fonts Only (Section 175) → Ensure typography recommendations are active in Google Fonts or system defaults
+
+# Trend Researcher Skill
+
 You are a creative muse and design trend analyst. Your purpose is to bridge the gap between "generic UI" and "stunning, intentional design" by grounding aesthetic decisions in real-world trends, documented design systems, and measurable user impact.
 
 ## When to Activate

package/.agent/skills/typescript-advanced/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: typescript-advanced
 description: Advanced TypeScript mastery. Generics with constraints, conditional types, mapped types, template literal types, the satisfies operator, discriminated unions, branded/nominal types, type-level programming, utility type internals, variance annotations, module augmentation, and declaration merging. Use when writing complex type definitions, building type-safe libraries, or solving "how do I type this?" problems.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 1.0.0
-last-updated: 2026-04-17
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - clean-code
+  - data-validation-schemas
+  - lint-and-validate
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Advanced TypeScript — Type-Level Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before writing complex TypeScript types or library abstractions, you MUST inspect:
+1. Zero `as any` Cast Rule (Section 15) → Fix the underlying type signature or use `as unknown as T` with explicit reasoning comment; ban `as any`
+2. Discriminated Unions for State Machine Modeling (Section 62) → Model multi-state objects with tagged discriminated unions for compile-time exhaustive checks
+3. The `satisfies` Operator vs Type Assertion (Section 193) → Use `satisfies` to validate types without widening object literals
+
 ## Hallucination Traps (Read First)
 
 - ❌ Using `as any` to silence type errors -> ✅ Fix the type; `as any` hides bugs that crash at runtime

package/.agent/skills/typeset/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: typeset
 description: Professional web typography scaling, font pairing, optical sizing, tracking, line height cadence, text-wrap balance, and OpenType features. Use when refining typography systems or text styling.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Typography & Typesetting
-  tier: pro
-  co-requires: [better-typography, frontend-design]
-  trigger-signals:
-    strong: [typeset, typography scale, font pairing, optical sizing, tracking, line height cadence, text-wrap balance, OpenType features]
-    weak: [text styling, font setup]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - swiss-design
+  - better-ui
+  - baseline-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Typeset — Professional Web Typography System
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before refining typography scales or text styles, you MUST inspect:
+1. `DESIGN.md` / `index.css` → Verify typography scale variables, font families, and OpenType settings
+2. Optical Tracking & Line-Height Cadence (Section 24) → Enforce `1.1` line-height for display headings, `1.5` for body text, and `-0.03em` tracking
+3. Modern Text Wrapping (Section 36) → Apply `text-wrap: balance` to headings and limit paragraph line width to `65ch`
+
 Architect disciplined, optically balanced typography systems across web components.
 
 ---