tribunal-kit 5.8.5 → 6.0.1

package/.agent/skills/baseline-ui/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: baseline-ui
 description: Quickly deslop UI code by fixing spacing, hierarchy, typography, contrast, and small layout issues. Use when the interface needs a fast cleanup or polish pass.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: UI Cleanup & Refinement
-  tier: basic
-  co-requires: [better-ui, frontend-design]
-  trigger-signals:
-    strong: [baseline-ui, deslop, cleanup ui, fix spacing, visual hierarchy, fix alignment]
-    weak: [tidy up, fix css, layout cleanup]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - better-ui
+  - frontend-design
+  - better-colors
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Baseline UI — Fast Deslopping & Hierarchy Cleanup
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before cleaning up UI styles, you MUST inspect:
+1. `DESIGN.md` / `package.json` → Check Tailwind CSS configuration and accessibility primitives (`Base UI`, `Radix`)
+2. The 5-Step Deslop Protocol (Section 33) → Fix spacing violations, establish 3-tier typographic hierarchy, and eliminate harsh borders
+3. Anti-Slop Table (Section 43) → Replace hardcoded arbitrary paddings and low-contrast text with tokenized CSS variables
+
 Enforces an opinionated UI baseline to clean up sloppy code and prevent AI-generated interface slop without changing product architecture or feature scope.
 
 ---

package/.agent/skills/bash-linux/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: bash-linux
 description: Bash/Linux terminal mastery. Shell scripting, piping, stream redirection, process substitution, strict mode (set -euo pipefail), AWK, ripgrep parsing, and robust error handling. Use when writing CI scripts, debugging POSIX environments, or manipulating text pipelines.
-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:
+  - server-management
+  - devops-engineer
+  - cicd-pro
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Bash & Linux — Shell Scripting Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before writing Bash scripts or terminal automation pipelines, you MUST inspect:
+1. Strict Mode Flags (`set -euo pipefail`) (Section 39) → Always set `set -euo pipefail` and `IFS=$'\n\t'` at top of every script to fail fast on errors or unset vars
+2. Variable Quoting Safeguards (Section 122) → Double-quote all path and string variables (`"$FILE"`, `"${FILES[@]}"`) to prevent whitespace expansion bugs
+3. Modern CLI Efficiency Rules (Section 102) → Prefer `rg` over `grep`, `fd` over `find`, `jq` over regex JSON parsing for performance and safety
+
 ## Hallucination Traps (Read First)
 
 - ❌ Scripts without `set -euo pipefail` -> ✅ Always enable strict mode to catch silent failures

package/.agent/skills/behavioral-modes/SKILL.md

@@ -1,19 +1,31 @@
 ---
 name: behavioral-modes
 description: AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
-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:
+  - fabel-protocol
+  - agentic-patterns
+  - thinking-protocol
+scripts-binding:
+  - .agent/scripts/checklist.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Behavioral Modes
 
 ---
 
+## Mandatory Pre-Flight Context Inspection
+
+Before selecting an operational mode, you MUST inspect:
+1. User prompt intent & keywords (Section 148 Mode Selection Rules) → Classify request type (TEACH, DEBUG, REVIEW, PLAN, BUILD, DISCOVER, SHIP, ORCHESTRATE)
+2. Mode Leakage Mitigation rules (Section 160) → Prevent writing unapproved code during DISCOVER or REVIEW modes
+3. Output format contracts → Ensure findings use labeled severity tags (CRITICAL / WARNING / SUGGESTION)
+
+---
+
 ## Overview
 
 Different work contexts require different operating behaviors. A debugging session requires patience and hypothesis testing. A code review requires skepticism. A teaching response requires no implementation at all.

package/.agent/skills/better-colors/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: better-colors
 description: OKLCH color space for web projects. Convert hex/rgb/hsl to oklch, generate palettes, check contrast, handle gamut boundaries, and theme with Tailwind v4. Triggers on oklch, color conversion, palette generation, contrast ratio, gamut, display p3, design tokens, hue drift, chroma, dark mode colors.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: UI Craft & Design Engineering
-  tier: pro
-  co-requires: [colorize, better-ui]
-  trigger-signals:
-    strong: [better-colors, oklch, color palette, contrast ratio, gamut, display p3, hue drift, dark mode colors]
-    weak: [colors, palette, theme, dark mode]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - better-ui
+  - baseline-ui
+  - colorize
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Better Colors — OKLCH & Modern Web Color Systems
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before defining color palettes or CSS theme variables, you MUST inspect:
+1. `DESIGN.md` / `index.css` → Check existing CSS custom properties and color variables
+2. OKLCH Syntax & Relative Color Rules (Section 30) → Use `oklch(L C H)` format with subtle chroma (`C: 0.01-0.02`) for neutrals
+3. WCAG 2.2 AA Contrast Thresholds (Section 82) → Ensure `L ≤ 45%` for text on light background and `L ≥ 70%` on dark background
+
 Design engineering guidelines for building perceptually uniform, WCAG 2.2 AA compliant, P3-gamut color systems using the modern **OKLCH** color space.
 
 ---

package/.agent/skills/better-ui/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: better-ui
 description: Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, micro-interactions, or visual detail work.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: UI Craft & Design Engineering
-  tier: pro
-  co-requires: [emil-design-eng, baseline-ui]
-  trigger-signals:
-    strong: [better-ui, ui polish, feels off, design details, optical alignment, micro-interactions, stagger animations, box shadows, make-interfaces-feel-better]
-    weak: [polish, refine, clean up ui, border radius]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - baseline-ui
+  - better-colors
+  - micro-interaction
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Better UI — Design Engineering & Polish Rules
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before engineering component polish or micro-interactions, you MUST inspect:
+1. Outer vs Inner Radius Formula (Section 32) → Enforce $\text{Radius}_{\text{outer}} = \text{Radius}_{\text{inner}} + \text{Padding}_{\text{inner}}$
+2. Transition Rules (Section 25) → Strictly prohibit `transition: all`; specify explicit property transitions
+3. Multi-Layer Shadows (Section 42) → Use ambient + direct lighting stacks and dark mode surface elevation highlights
+
 Distilled design engineering principles for transforming functional UIs into polished, state-of-the-art software interfaces, based on Jakub Krehel's *Details that make interfaces feel better*.
 
 ---

package/.agent/skills/bolder/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: bolder
 description: Increase visual impact, punch, and personality for generic or bland interfaces. Use when the user asks to make the UI pop, stand out, have more character, or feel less template-like.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Visual Design & Brand Identity
-  tier: pro
-  co-requires: [better-colors, better-typography, impeccable]
-  trigger-signals:
-    strong: [bolder, make it pop, more punch, stand out, add character, feel less generic]
-    weak: [bold design, vibrant, striking]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - better-colors
+  - better-ui
+  - impeccable
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Bolder — Injecting Punch & Personality into UI
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before applying bold visual transformations, you MUST inspect:
+1. `DESIGN.md` / `package.json` → Check existing brand color variables and design tokens
+2. Typographic Contrast Scaling rules (Section 24) → Enforce extreme scale jumps (`1.5rem` to `4.5rem`) for display headings
+3. Single Electric Accent System (Section 28) → Use one high-chroma accent color sparingly for primary CTAs and badges
+
 Transform generic, boring template UIs into high-impact, distinctive interfaces with strong visual presence.
 
 ---

package/.agent/skills/brainstorming/SKILL.md

@@ -1,15 +1,25 @@
 ---
 name: brainstorming
 description: Socratic methodology, ideation, and architectural exploration mastery. Generating extensive feature options, analyzing trade-offs, questioning assumptions, mind-mapping components, and delaying execution. Use when evaluating new features, defining project goals, or guiding users through ambiguous design spaces.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 3.1.0
-last-updated: 2026-04-06
-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:
+  - plan-writing
+  - fabel-protocol
+  - behavioral-modes
+scripts-binding:
+  - .agent/scripts/checklist.js
+  - .agent/scripts/verify_all.js
 ---
 
+## Mandatory Pre-Flight Context Inspection
+
+Before initiating ideation sessions or generating architectural options, you MUST inspect:
+1. `package.json` / `ARCHITECTURE.md` → Check existing technology stack, libraries, and architectural boundaries
+2. The Socratic Protocol (Section 1) → Provide 3 distinct options (Conservative, Balanced, Ambitious) with tabular trade-offs
+3. Final Brainstorming Assertions schema (Section 4) → Distill options into actionable requirement items before planning
+
 ## Hallucination Traps (Read First)
 
 - ❌ Jumping to implementation during brainstorming -> ✅ Brainstorming is exploration only; no code is written in this phase

package/.agent/skills/browser-native-ai/SKILL.md

@@ -1,13 +1,29 @@
 ---
 name: browser-native-ai
 description: Browser-native AI mastery. Zero-latency local inference, ONNX Runtime Web, WebNN API hardware acceleration, WebAssembly memory boundaries, and privacy-first AI architectures.
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - generative-ui-expert
+  - webgpu-performance
+  - 60fps-animation
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Browser-Native AI (Local SLMs)
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before writing browser-native AI or client-side inference code, you MUST inspect:
+1. Main Thread Isolation (Section 44) → Run ONNX Runtime / Wasm inference inside a dedicated Web Worker (`worker.js`) to prevent blocking UI
+2. Quantization Rules (Section 42) → Target 4-bit quantized (`q4`) small language models (0.5B to 1.5B parameters) to prevent mobile device crashes
+3. Download Progress Callback (Section 50) → Provide a `progress_callback` to display model weight download percentages to the user
+
 You are an expert at running AI models directly on the client's device, inside the web browser. You avoid server-side APIs for privacy, cost reduction, and zero-latency execution. Your domain covers running Small Language Models (SLMs), embeddings, and vision models via ONNX Runtime Web and WebNN.
 
 ## 1. Core Principles

package/.agent/skills/build-primitive/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: build-primitive
 description: Build foundational, unstyled, accessible UI primitives from scratch with strong ARIA attributes, keyboard navigation, focus traps, and state management. Use when creating custom Headless UI components (Dialog, Combobox, Accordion, Popover, Menu).
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Headless UI & Accessible Primitives
-  tier: pro
-  co-requires: [web-accessibility-auditor, react-specialist]
-  trigger-signals:
-    strong: [build-primitive, headless UI, custom dialog primitive, custom popover, accessible primitive, ARIA combobox, keyboard navigation primitive]
-    weak: [custom component, headless component]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - react-specialist
+  - baseline-ui
+  - better-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Build Primitive — Headless & Accessible UI Primitives
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before building headless UI primitives, you MUST inspect:
+1. WAI-ARIA Design Patterns (Section 24) → Attach exact roles (`dialog`, `combobox`, `tablist`), `aria-expanded`, and ID associations (`aria-labelledby`, `aria-describedby`)
+2. Focus Traps & Restoration (Section 29) → Trap focus inside modals on open; return focus to trigger on close; dismiss on `Escape`
+3. Data Attributes (Section 41) → Expose clean `data-state="open|closed"` and `data-disabled` attributes for unstyled CSS consumer integration
+
 Build rock-solid, framework-agnostic or React headless UI primitives with complete ARIA pattern compliance, keyboard control, and focus management.
 
 ---

package/.agent/skills/building-native-ui/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: building-native-ui
 description: Cross-platform Native UI mastery (React Native / Expo). Building seamless, 60fps mobile interfaces, handling safe areas, navigation architectures (Expo Router), native modules, gestures/animations (Reanimated), and platform-specific styling. Use when building React Native or Expo mobile apps.
-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
+  - react-specialist
+  - 60fps-animation
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Building Native UI — React Native & Expo Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before building React Native / Expo UI components, you MUST inspect:
+1. Safe Area Setup → Use `SafeAreaProvider` + `useSafeAreaInsets()` for granular notch/inset handling instead of raw `SafeAreaView`
+2. Virtualized List Rendering (Section 130) → Use `FlashList` (Shopify) or `FlatList` with `estimatedItemSize` instead of `ScrollView` for large lists
+3. Native Thread Animations (Section 99) → Use `react-native-reanimated` with `useSharedValue` to keep animations off the JS bridge thread
+
 ## Hallucination Traps (Read First)
 
 - ❌ `SafeAreaView` wrapping everything -> ✅ Use `SafeAreaProvider` + `useSafeAreaInsets()` for granular control

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

@@ -1,18 +1,29 @@
 ---
 name: cicd-pro
 description: Enterprise-grade CI/CD mastery. Golden Path - GitHub Actions + Docker + AWS ECS. 3-stage pipeline architecture (Validate→Build→Deploy), OIDC-based AWS auth (no static secrets), Blue/Green and Canary deployment with ECS, environment promotion gates (dev→staging→production), rollback playbooks, Slack notifications, and reusable workflow patterns. Use when designing or implementing production CI/CD pipelines.
-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: devops
-  tier: pro
-  co-requires: [containerization-pro, cloud-architect]
-  trigger-signals:
-    strong: [CI/CD pipeline, GitHub Actions, Blue/Green deploy, OIDC AWS]
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - containerization-pro
+  - cloud-architect
+  - devops-engineer
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# CI/CD Pro — Enterprise Pipeline Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before designing CI/CD workflows or deployment scripts, you MUST inspect:
+1. Concurrency Mutex Requirement (Section 18) → Configure top-level `concurrency:` blocks in GitHub Actions workflows to prevent parallel deploy collisions
+2. OIDC Authentication Protocol (Section 20) → Use OIDC (`id-token: write` permission) for AWS/cloud credentials; ban static access keys in secrets
+3. Production Promotion Gates (Section 21) → Enforce environment promotion gates (`staging` → `production` with manual reviewers) before deploying
+
 ## Hallucination Traps (Read First)
 
 - ❌ Missing `concurrency:` block → ✅ Without it, parallel deploys collide and corrupt production state

package/.agent/skills/clarify/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: clarify
 description: Improve UX microcopy, label optimization, error messages, and cognitive clarity. Use when text in a UI is confusing, wordy, ambiguous, or unhelpful.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: UX Writing & Microcopy
-  tier: pro
-  co-requires: [distill, shape]
-  trigger-signals:
-    strong: [clarify, UX copy, microcopy, error message copy, button labels, cognitive clarity, clear writing]
-    weak: [fix text, rewording, rewrite label]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - distill
+  - shape
+  - baseline-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Clarify — UX Microcopy & Cognitive Clarity
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before optimizing UI text or error messages, you MUST inspect:
+1. Target UI labels & modals → Check for vague "Submit" or "OK" buttons and passive corporate jargon
+2. Active Verb Rules (Section 24) → Ensure action buttons start with specific verbs describing outcomes (e.g. *Save changes*, *Download export*)
+3. Actionable Error Messages (Section 30) → Pair error descriptions with explicit resolution steps
+
 Optimize user interface text, button labels, error messaging, and helper copy for maximum clarity and minimum cognitive friction.
 
 ---

package/.agent/skills/clean-code/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: clean-code
 description: Clean code mastery. Naming conventions, function design, DRY vs WET, SOLID principles with code examples, refactoring patterns, code smells detection, error handling philosophy, comments that add value, and the art of simplicity. Use when reviewing code quality, refactoring, or establishing coding standards.
-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:
+  - codebase-design
+  - code-review-checklist
+  - tdd-workflow
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Clean Code — The Art of Readable Software
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before refactoring code or evaluating clean code standards, you MUST inspect:
+1. Intent-Revealing Naming (Section 25) → Name variables/functions to reveal explicit intent; ban cryptic abbreviations (`d`, `proc`, `u`)
+2. Single-Purpose Functions (Section 95) → Ensure functions perform 1 single task; extract sub-operations if function exceeds ~30 lines
+3. Guard Clause Early Returns (Section 344) → Flatten nested logic (>3 levels) using guard clauses and fail-fast early returns
+
 ## Hallucination Traps (Read First)
 
 - ❌ Over-abstracting code that is used in only one place -> ✅ Don't DRY single-use code; premature abstraction is worse than duplication

package/.agent/skills/cloud-architect/SKILL.md

@@ -1,18 +1,29 @@
 ---
 name: cloud-architect
 description: Production AWS cloud architecture mastery. Service selection (ECS Fargate vs Lambda vs EC2, RDS vs Aurora vs DynamoDB), Terraform IaC patterns with HCL examples, VPC networking design, IAM least privilege, Secrets Manager, CloudWatch observability, cost optimization, and multi-environment AWS Organizations strategy. Golden Path - AWS. Use when architecting cloud infrastructure, writing Terraform, or making AWS service selection decisions.
-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: devops
-  tier: pro
-  co-requires: [cicd-pro]
-  trigger-signals:
-    strong: [AWS, Terraform, ECS Fargate, VPC design, IAM]
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - cicd-pro
+  - devops-engineer
+  - platform-engineer
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Cloud Architect — Production AWS Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before architecting AWS cloud infrastructure or writing Terraform HCL, you MUST inspect:
+1. Dynamic Account ID & Region Resolution (Section 20) → Use `data.aws_caller_identity.current.account_id` and `var.region`; ban hardcoded account IDs or ARNs
+2. Private Subnet Application Placement (Section 23) → Place application compute (ECS, Lambda) strictly in private subnets; only ALB and NAT Gateway live in public subnets
+3. Secrets Manager Secret Injection (Section 21) → Reference secret ARNs from AWS Secrets Manager in ECS task definitions; ban plaintext environment variables for passwords/tokens
+
 ## Hallucination Traps (Read First)
 
 - ❌ Confusing availability zones with regions → ✅ `us-east-1` is a region. `us-east-1a` is an AZ within that region. Multi-AZ ≠ multi-region.

package/.agent/skills/cobejs/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: cobejs
 description: Build lightweight, hardware-accelerated 3D interactive animated globes and web orbs using Cobe WebGL.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: 3D Graphics & Canvas Visuals
-  tier: pro
-  co-requires: [60fps-animation, threejs-fundamentals]
-  trigger-signals:
-    strong: [cobejs, Cobe globe, 3D animated globe, interactive WebGL globe, Cobe orb]
-    weak: [globe component, 3D globe]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - 60fps-animation
+  - motion-engineering
+  - baseline-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Cobe JS — Lightweight 3D WebGL Globe Visuals
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before building WebGL 3D globe components with Cobe, you MUST inspect:
+1. `package.json` → Verify `cobe` dependency exists
+2. WebGL Context Cleanup (Section 59) → Ensure `globe.destroy()` is called in the `useEffect` unmount cleanup to prevent memory leaks
+3. Canvas Sizing (Section 65) → Match `devicePixelRatio` to high-DPI screens and set `aspectRatio: 1` to prevent visual stretching
+
 Integrate ultra-fast, 5KB WebGL interactive globes for landing page hero sections and interactive location maps.
 
 ---

package/.agent/skills/code-review-checklist/SKILL.md

@@ -1,19 +1,33 @@
 ---
 name: code-review-checklist
 description: Code review guidelines covering code quality, security, and best practices.
-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:
+  - clean-code
+  - lint-and-validate
+  - thermo-nuclear-code-quality-review
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Code Review Standards
 
 ---
 
+## Mandatory Pre-Flight Context Inspection
+
+Before performing code reviews or writing PR comments, you MUST inspect:
+1. Label Convention Standardization (Section 27) → Categorize all feedback into `BLOCKER:`, `CONCERN:`, `SUGGESTION:`, or `NOTE:`
+2. Context Window Discipline (Section 120) → Quote concise 1-3 line snippets with line numbers; ban pasting massive blocks of unchanged code
+3. Anti-Nitpicking Rule (Section 130) → Delegate syntax/formatting formatting checks to linters (`eslint`/Prettier); focus reviews on logic and security
+
+# Code Review Standards
+
+---
+
 ## Review Mindset
 
 Reviews are collaborative. The goal is better code — not proof that the reviewer is smarter.