tribunal-kit 5.8.4 → 6.0.0

package/.agent/skills/python-pro/SKILL.md

@@ -1,16 +1,31 @@
 ---
 name: python-pro
 description: Python 3.12+ specialist. FastAPI, Pydantic v2, asyncio, modern types, pytest. Use when building Python APIs, data pipelines, automation, or any Python code.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 3.1.0
-last-updated: 2026-04-06
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - python-patterns
+  - data-validation-schemas
+  - api-patterns
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Python 3.12+ — Dense Reference
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before writing Python code or FastAPI endpoints, you MUST inspect:
+1. Pydantic v2 Migration Syntax (Section 17) → Use `model_dump()`, `model_dump_json()`, `model_validate()`, and `@field_validator`; ban v1 `.dict()` and `@validator`
+2. Modern Native Generics (Section 16) → Use native `list[str]`, `dict[k,v]`, and `X | None` (Python 3.10+); ban legacy `typing.List` / `typing.Optional`
+3. Non-Blocking Async Clients (Section 21) → Use `httpx.AsyncClient()` in async code; ban blocking `requests` library inside asyncio event loops
+
+# Python 3.12+ — Dense Reference
+
 ## Hallucination Traps (Read First)
 
 - ❌ `from typing import List, Dict, Optional, Union` → ✅ `list[str]`, `dict[k,v]`, `X | None`, `X | Y` (Python 3.10+)

package/.agent/skills/quieter/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: quieter
 description: Tone down overly loud, noisy, visually aggressive, or distracting designs while maintaining high visual quality. Use when a UI feels cluttered, overwhelming, tacky, or visually hyperactive.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Visual Design & Restraint
-  tier: pro
-  co-requires: [distill, swiss-design, compact-landing]
-  trigger-signals:
-    strong: [quieter, tone down, too loud, visual noise, too aggressive, tacky, calm ui, simplify visual]
-    weak: [subdue, tone down colors, lessen contrast]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - distill
+  - swiss-design
+  - baseline-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Quieter — Visual Restraint & Calm Interface Design
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before subduing visual design elements, you MUST inspect:
+1. `DESIGN.md` / `package.json` → Check background surface variables and contrast standards
+2. Palette Subjugation rules (Section 24) → Limit high-saturation colors to single primary actions
+3. Motion Restraint rules (Section 35) → Eliminate looping pulsing badges and restrict motion to user-initiated actions
+
 Reduce visual noise, eliminate unnecessary color competition, and restore calm focus to chaotic interfaces.
 
 ---

package/.agent/skills/react-doctor/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: react-doctor
 description: Scan React and Next.js applications for security, performance, re-render inefficiencies, memory leaks, and correctness issues.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: React Optimization & Code Health
-  tier: pro
-  co-requires: [react-specialist, nextjs-react-expert, performance-profiling]
-  trigger-signals:
-    strong: [react-doctor, React performance scan, fix React re-renders, React memory leak, Million.js audit]
-    weak: [React audit, fix React bugs]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - react-specialist
+  - nextjs-react-expert
+  - baseline-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # React Doctor — React Performance & Health Audit
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before auditing React components for performance or health issues, you MUST inspect:
+1. Re-render triggers (Section 24) → Identify inline object/array props and inline callback handlers breaking memoization
+2. `useEffect` Cleanup (Section 31) → Ensure all event listeners, intervals, and subscriptions return explicit cleanup functions
+3. Derived State Anti-Pattern (Section 41) → Ban props duplicated into state (`useState(props.val)`); derive values directly during render
+
 Diagnose and resolve unnecessary re-renders, state synchronization bugs, memory leaks, and hook dependency issues in React applications.
 
 ---

package/.agent/skills/react-specialist/SKILL.md

@@ -1,16 +1,29 @@
 ---
 name: react-specialist
 description: React 19+ specialist. use(), useActionState, useOptimistic, React Compiler, Server/Client Components, Zustand/Jotai, React Query. Use when building components, managing state, optimizing renders.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 3.1.0
-last-updated: 2026-04-06
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - nextjs-react-expert
+  - react-doctor
+  - baseline-ui
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # React 19+ — Dense Reference
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before writing React 19+ components or hooks, you MUST inspect:
+1. React 19 APIs (`useActionState` vs deprecated `useFormState`, `use()` vs `useContext`, `ref` as prop vs deprecated `forwardRef`)
+2. React Compiler Memoization (Section 125) → Avoid manual `useMemo`/`useCallback` unless React Compiler is explicitly disabled
+3. State Destructuring Traps (Section 189) → Never destructure entire Zustand stores; use granular selectors `useStore(s => s.value)`
+
 ## Hallucination Traps (Read First)
 
 - ❌ `useFormState` → ✅ `useActionState` (stable name)

package/.agent/skills/readme-builder/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: readme-builder
 description: Interactive README.md generation specialist. Creates professional, structured README files with badges, installation guides, usage examples, screenshots, and contribution guidelines. Use when asked to create, update, or improve a README file.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 1.0.0
-last-updated: 2026-03-19
-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:
+  - documentation-templates
+  - geo-fundamentals
+  - github-operations
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# README Builder Skill
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before generating or updating a README file, you MUST inspect:
+1. Mandatory Discovery Phase (Section 34) → Scan `package.json`, `pyproject.toml`, or project files first to collect factual metadata before writing
+2. Zero Placeholder Rule (Section 28) → Ban template placeholders (`[insert here]`); generate copy-paste ready code examples from actual project code
+3. Hero Section Lead-With-Value (Section 164) → Lead with a single-sentence value proposition and visual trust badges; ban starting with just the title
+
 ## Hallucination Traps (Read First)
 
 - ❌ Starting a README with the project name as the only heading -> ✅ Lead with what the project DOES, not just what it IS

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

@@ -1,19 +1,33 @@
 ---
 name: realtime-patterns
 description: Real-time application mastery. WebSockets, Server-Sent Events (SSE), CRDTs for conflict-free collaboration, presence systems, optimistic updates, live cursors, multiplayer state sync, reconnection strategies, and real-time database patterns (Supabase Realtime, Firebase). Use when building chat, live collaboration, dashboards, or multiplayer features.
-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:
+  - api-patterns
+  - backend-security-expert
+  - nodejs-best-practices
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Real-Time Patterns — Live Application Mastery
 
 ---
 
+## Mandatory Pre-Flight Context Inspection
+
+Before architecting real-time streaming or WebSocket infrastructure, you MUST inspect:
+1. One-Way SSE Selection Rule (Section 49) → Prefer SSE for one-way server-to-client streaming (AI responses, notifications); reserve WebSockets for bidirectional interactive features
+2. WebSocket Exponential Reconnection (Section 183) → Implement exponential backoff with random jitter for client reconnection loops to prevent thundering herd crashes
+3. Optimistic UI Rollback Handler (Section 207) → Capture previous state before optimistic mutations and implement explicit onError rollback logic
+
+# Real-Time Patterns — Live Application Mastery
+
+---
+
 ## Protocol Selection
 
 ```

package/.agent/skills/red-team-tactics/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: red-team-tactics
 description: Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.
-allowed-tools: Read, Write, Edit, Glob, Grep
-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
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - vulnerability-scanner
+  - backend-security-expert
+  - api-security-auditor
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Red Team & Penetration Testing Principles
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before performing red team assessments or security testing, you MUST inspect:
+1. Written Authorization Gate (Section 34) → Verify written authorization, defined scope, rules of engagement, and emergency contact before executing tests
+2. Reproducible PoC Rule (Section 16) → Include a reproducible Proof-of-Concept, CVSS risk score, and explicit remediation snippet for every finding
+3. Breach Discovery Halt (Section 162) → Immediately halt security testing and report if evidence of an active real-world breach is discovered
+
 ## Hallucination Traps (Read First)
 
 - ❌ Testing only happy-path authentication -> ✅ Red teaming must test token reuse, expired tokens, forged tokens, and privilege escalation

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

@@ -1,20 +1,29 @@
 ---
 name: redesign-skill
 description: Audit and upgrade existing interfaces to premium visual quality while preserving product functionality and business logic.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Interface Redesign & UI Upgrade
-  tier: pro
-  co-requires: [taste-skill, better-ui, baseline-ui]
-  trigger-signals:
-    strong: [redesign-skill, redesign existing project, UI upgrade, overhaul interface, modernize UI, upgrade visual quality]
-    weak: [redesign UI, revamp site]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - taste-skill
+  - better-ui
+  - baseline-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Redesign Skill — UI Upgrade Methodology
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before executing interface redesigns, you MUST inspect:
+1. Logic Isolation Rule (Section 24) → Extract and preserve ALL state hooks (`useState`), event handlers (`onClick`), and API props before altering layout
+2. Surface Hierarchy (Section 32) → Upgrade raw hex backgrounds to OKLCH surface levels (`--bg-base`, `--bg-surface`, `--bg-elevated`)
+3. Spatial Grid (Section 28) → Standardize spacing to an 8px system (`gap-4`, `p-6`) with `text-wrap: balance` on headings
+
 Audit legacy or unstyled user interfaces and transform them into modern, production-grade products without breaking underlying business logic.
 
 ---

package/.agent/skills/review-animations/SKILL.md

@@ -1,20 +1,31 @@
 ---
 name: review-animations
 description: Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
-version: 1.0.0
-last-updated: 2026-06-26
-applies-to-model: gemini-3-1-pro, claude-3-7-sonnet
-disable-model-invocation: true
-routing:
-  domain: review
-  tier: specialized
-  trigger-signals:
-    strong: [review animations, motion review, ui animation craft, 60fps, animation standards, evaluate motion]
-    weak: [review UI, check transitions, smooth animation]
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - emil-design-eng
+  - 60fps-animation
+  - accessible-animation
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Reviewing Animations
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before auditing animation code or reviewing motion diffs, you MUST inspect:
+1. Sub-300ms UI Duration Limit (Section 35) → Enforce maximum 300ms duration for UI element animations; flag any sluggish transitions >300ms
+2. GPU-Only Property Constraint (Section 38) → Flag any animation of layout-heavy properties (`width`/`height`/`top`/`left`); require `transform` and `opacity`
+3. Physical Correctness & Origin (Section 36) → Flag `scale(0)` entrances; require `scale(0.9–0.97)` with `opacity` and accurate `transform-origin`
+
+# Reviewing Animations
+
 A specialized review skill. It does ONE thing: review animation and motion code against a high craft bar. It does not write features, fix unrelated bugs, or review non-motion code. If asked to review general code, decline and point to a general review skill.
 
 ## Operating Posture

package/.agent/skills/rust-pro/SKILL.md

@@ -1,19 +1,33 @@
 ---
 name: rust-pro
 description: Master Rust 1.75+ with modern async patterns, ownership/borrowing, lifetimes, traits, error handling with thiserror/anyhow, async Tokio runtime, axum web framework, serde serialization, and systems programming. Use when building Rust services, CLI tools, WebAssembly, or performance-critical systems.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 2.0.0
-last-updated: 2026-03-30
-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
+  - api-patterns
+  - backend-security-expert
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Rust Pro — Rust 1.75+ Systems Mastery
 
 ---
 
+## Mandatory Pre-Flight Context Inspection
+
+Before writing Rust code or Axum handlers, you MUST inspect:
+1. Production Error Propagation (Section 130) → Use `?` operator and structured `Result<T, E>`; ban `.unwrap()` in production code
+2. Library vs App Error Strategy (Section 192) → Use `thiserror` for library crates to export structured errors; use `anyhow` only for application code
+3. Axum 0.7+ Route Parameters (Section 444) → Use `{id}` bracket syntax for path parameters (`/users/{id}`); ban legacy `:id` syntax
+
+# Rust Pro — Rust 1.75+ Systems Mastery
+
+---
+
 ## Ownership & Borrowing
 
 ### The Three Rules

package/.agent/skills/seo-fundamentals/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: seo-fundamentals
 description: Search Engine Optimization (SEO) mastery. Metadata implementation, Open Graph (OG) social card rendering, semantic HTML5 structuring, canonicalization, Core Web Vitals performance mapping, Sitemap/Robots configurations, structured data (JSON-LD), and Next.js SSR SEO implementations. Use when auditing site visibility or building consumer-facing web architectures.
-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:
+  - fixing-metadata
+  - web-quality-audit
+  - nextjs-react-expert
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# SEO Fundamentals — Visibility & Discoverability Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before implementing metadata or search optimization, you MUST inspect:
+1. One H1 Heading Law (Section 64) → Ensure exactly ONE `<h1>` per page for document title; ban multiple `<h1>` tags or missing H1s
+2. Server-Side Rendering (SSR/SSG) Rule (Section 18) → Use SSR/SSG for indexable pages; ban client-side-only rendering for public SEO content
+3. JSON-LD Structured Data Injection (Section 86) → Inject Schema.org JSON-LD scripts (`application/ld+json`) for rich entity indexing
+
 ## Hallucination Traps (Read First)
 
 - ❌ Using `<div>` for everything instead of semantic HTML -> ✅ Use `<main>`, `<article>`, `<nav>`, `<section>` for crawler comprehension

package/.agent/skills/server-management/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: server-management
 description: Production Linux server administration mastery. Systemd services, Nginx reverse proxy architecture, UFW firewalls, SSH key security, cron scheduling, log rotation, and server hardening. Use when configuring bare-metal, VPS instances, or reviewing deployment architecture.
-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:
+  - devops-engineer
+  - backend-security-expert
+  - bash-linux
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Server Management — Production Linux Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before configuring Linux servers, Nginx, or systemd services, you MUST inspect:
+1. Dedicated Non-Root User Execution (Section 39) → Run systemd services strictly under non-root users (`User=appuser`); ban running app services as root
+2. Nginx Syntax Verification (`nginx -t`) (Section 17) → Always verify Nginx configuration (`sudo nginx -t`) BEFORE reloading systemd services
+3. SSH & UFW Hardening Defaults (Section 126) → Disable password auth & root login (`PermitRootLogin no`), and configure UFW default deny incoming
+
 ## Hallucination Traps (Read First)
 
 - ❌ Running services as root -> ✅ Create a dedicated service user with minimal permissions; never run as root

package/.agent/skills/shadcn-ui-expert/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: shadcn-ui-expert
 description: shadcn/ui mastery. Installation, customization via tailwind.config, component extraction, state management with Radix Primitives, theme variables (CSS custom properties), dark mode implementations, and overriding default designs. Use when building or modifying shadcn/ui components in React/Next.js projects.
-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:
+  - build-primitive
+  - react-specialist
+  - baseline-ui
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# shadcn/ui Expert — Component Architecture Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before using or customizing shadcn/ui components, you MUST inspect:
+1. Component Installation State → Check `@/components/ui/` directory for existing components before running `npx shadcn@latest add`
+2. `cn` Utility Usage (Section 144) → Use `cn(...)` (combining `clsx` + `tailwind-merge`) for all conditional and overridden class names
+3. Client Component Boundaries (Section 166) → Add `"use client"` on interactive Radix primitives (Dialog, Select, Popover) before rendering in App Router
+
 ## Hallucination Traps (Read First)
 
 - ❌ `import { Button } from 'shadcn-ui'` -> ✅ shadcn/ui is NOT a package; components are copied into YOUR project. Import from `@/components/ui/button`

package/.agent/skills/shape/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: shape
 description: Plan feature UX before writing code via structured Socratic design interviews. Use when a user asks to plan a new screen, onboarding flow, feature UX, or user interaction before implementation.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Pre-Code UX Shaping
-  tier: pro
-  co-requires: [appflow-wireframe, brainstorming, plan-writing]
-  trigger-signals:
-    strong: [shape, UX shaping, feature design, pre-code planning, user flow interview, shape workflow]
-    weak: [plan UI, spec out feature]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - brainstorming
+  - plan-writing
+  - ui-reasoning-engine
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/checklist.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Shape — Pre-Code UX & Feature Shaping
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before generating UI component code for new features, you MUST inspect:
+1. Target feature scope & user goals → Execute the 3-Step Shaping Workflow (Section 22)
+2. State Inventory (Section 29) → Define 5 required component states (Default, Empty, Loading, Error, Success)
+3. Architecture Contract (Section 37) → Draft entry/exit points and primary action contract before coding
+
 Uncover core requirements, define interaction boundaries, and lock down screen flows BEFORE writing frontend code.
 
 ---

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

@@ -1,15 +1,29 @@
 ---
 name: skill-creator
 description: Meta-agent specialized in expanding the framework's procedural knowledge by creating new, highly-structured SKILL.md files.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 1.0.0
-last-updated: 2026-03-30
-applies-to-model: claude-3-7-sonnet, gemini-2.5-pro
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - clean-code
+  - documentation-templates
+  - fabel-protocol
+scripts-binding:
+  - .agent/scripts/skill_integrator.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Skill Creator — Meta-Skill Builder
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before creating a new skill module, you MUST inspect:
+1. `.agent/skills/` directory → Check if a skill in the same domain already exists to prevent duplication
+2. Option A+C Hybrid Skill Schema (Section 26) → Enforce frontmatter with `version: 3.0.0`, `scripts-binding`, `Pre-Flight Checklist`, and `VBC Protocol`
+3. Target skill path (`.agent/skills/<skill-name>/SKILL.md`) → Verify destination directory structure before creation
+
 ## Hallucination Traps (Read First)
 
 - ❌ Creating skills without frontmatter (name, description, version) -> ✅ Every SKILL.md MUST start with YAML frontmatter

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

@@ -1,20 +1,29 @@
 ---
 name: soft-skill
 description: High-end visual design guidance for premium typography, spacing, depth, and animation systems.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Luxury Visual Design & Soft Depth
-  tier: pro
-  co-requires: [taste-skill, progressive-blur, impeccable]
-  trigger-signals:
-    strong: [soft-skill, high end visual design, luxury depth, soft UI, elegant spacing system, soft shadow UI]
-    weak: [elegant UI, soft style]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - taste-skill
+  - progressive-blur
+  - impeccable
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Soft Skill — High-End Luxury Visual Design & Depth
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before engineering luxury or soft-depth UI interfaces, you MUST inspect:
+1. Multi-Layer Shadow Recipe (Section 25) → Blend low-opacity multi-layered ambient shadows ($\le 6\%$ opacity per layer) instead of heavy single drop shadows
+2. Spatial Cadence (Section 37) → Increase container padding by $1.5\times$ ($\ge 24\text{px}$) to provide generous negative space
+3. Color Harmonies (Section 40) → Use quiet, low-chroma monochromatic OKLCH palettes for background and typography
+
 Craft high-end, luxury interfaces featuring soft depth, gentle surface transitions, quiet typography, and tactile spatial rhythm.
 
 ---