tribunal-kit 5.8.4 → 6.0.0

package/.agent/skills/ui-ux-researcher/SKILL.md

@@ -1,20 +1,31 @@
 ---
 name: ui-ux-researcher
 description: Expert auditor for accessibility, cognitive load, and premium design heuristics.
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
 skills:
   - web-design-guidelines
   - frontend-design
   - trend-researcher
-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
 ---
 
 # UI/UX Researcher Skill
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before conducting UX audits or evaluating cognitive load heuristics, you MUST inspect:
+1. P0 Safety & Accessibility Gates (Section 49) → Audit contrast ($\ge 4.5:1$), touch target sizes ($\ge 44\times 44\text{px}$), keyboard focus rings, and screen reader labels
+2. Nielsen 10 Heuristics Alignment (Section 162) → Map all P1 findings explicitly to Nielsen heuristics (H1–H10)
+3. Quantitative UX Scoring Formula (Section 96) → Calculate UX score strictly via formula: `Score = (P0 × 0.5) + (P1 × 0.3) + (P2 × 0.2)`
+
+# UI/UX Researcher Skill
+
 You are an expert UX auditor specializing in accessibility compliance, cognitive load optimization, and premium design heuristics. You audit existing UI against 2026 best practices and provide scored, actionable reports.
 
 ## When to Activate

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

@@ -1,16 +1,29 @@
 ---
 name: vue-expert
 description: Vue 3.5+ Composition API. Script setup, reactive refs, computed, watchers, composables, Pinia, Vue Router 4, Nuxt 4. Use when building Vue/Nuxt applications.
-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:
+  - baseline-ui
+  - better-ui
+  - 60fps-animation
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Vue 3.5+ & Nuxt 4 — Dense Reference
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before writing Vue 3.5+ or Nuxt 4 components, you MUST inspect:
+1. Script Setup Architecture → Use `<script setup lang="ts">` exclusively; ban legacy Options API
+2. Pinia & Reactivity Rules (Section 133) → Use `storeToRefs(store)` when destructuring Pinia state to preserve reactivity
+3. Model & Watcher Syntax (Section 42) → Use `defineModel<T>()` (Vue 3.4+) and `watch(() => state.prop, ...)` for primitive watchers
+
 ## Hallucination Traps (Read First)
 
 - ❌ Options API (`data()`, `methods:`, `computed:`) → ✅ `<script setup lang="ts">`

package/.agent/skills/vulnerability-scanner/SKILL.md

@@ -1,19 +1,33 @@
 ---
 name: vulnerability-scanner
 description: Security vulnerability analysis mastery. OWASP Top 10 (2025), injection attacks (SQL, XSS, SSRF, command), authentication/authorization flaws, dependency vulnerabilities, secret scanning, CORS misconfiguration, supply chain attacks, and security headers. Use when auditing security, reviewing code for vulnerabilities, or hardening applications.
-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:
+  - backend-security-expert
+  - frontend-security-expert
+  - api-security-auditor
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Vulnerability Scanner — Security Analysis Mastery
 
 ---
 
+## Mandatory Pre-Flight Context Inspection
+
+Before scanning codebases for security vulnerabilities, you MUST inspect:
+1. SQL Injection Vectors (Section 39) → Ban template literal interpolation in SQL queries (`SELECT ... WHERE id = ${id}`); require parameterized queries
+2. Explicit JWT Algorithms (Section 121) → Verify `jwt.verify(token, secret, { algorithms: ["HS256"] })` specifies explicit algorithms to prevent "None" attacks
+3. SSRF Domain Allowlist (Section 87) → Validate external request URLs against a strict domain allowlist and block private IP ranges (169.254.169.254, 127.0.0.1)
+
+# Vulnerability Scanner — Security Analysis Mastery
+
+---
+
 ## OWASP Top 10 (2025)
 
 ```

package/.agent/skills/web-accessibility-auditor/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: web-accessibility-auditor
 description: Web Accessibility (a11y) mastery. WCAG 2.2 AA standards, semantic HTML, ARIA attributes, keyboard navigation, focus management, screen reader compatibility, color contrast, and dynamic content announcements. Use when building UI components or auditing frontend code for accessibility compliance.
-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-accessibility
+  - audit-and-fix
+  - build-primitive
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Web Accessibility (a11y) — Inclusive UI Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before auditing accessibility or building UI components, you MUST inspect:
+1. Native Semantic HTML First Rule (Section 28) → Use native `<button>`, `<a>`, `<label>` elements; ban adding `role="button"` to non-interactive `<div>` tags
+2. Keyboard Focus Visibility (Section 61) → Preserve `:focus-visible` outlines; ban global outline removal (`*:focus { outline: none; }`)
+3. Explicit Form Label Linking (Section 129) → Explicitly link inputs to `<label>` via `id`/`for` attributes; ban using `placeholder` as a label replacement
+
 ## Hallucination Traps (Read First)
 
 - ❌ Adding `role='button'` to a `<div>` instead of using `<button>` -> ✅ Native HTML elements have built-in keyboard and screen reader support

package/.agent/skills/web-design-guidelines/SKILL.md

@@ -1,234 +1,60 @@
 ---
 name: web-design-guidelines
-description: 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".
-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
+description: Enforces next-generation web interface guidelines, covering APCA contrast thresholds, Core Web Vitals, and sustainable battery-efficient UI rendering.
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - baseline-ui
+  - better-colors
+  - 60fps-animation
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
-## Hallucination Traps (Read First)
-
-- ❌ Designing mobile-last (desktop first, then shrinking) -> ✅ Design mobile-first, then enhance for larger screens
-- ❌ Using more than 2-3 font families -> ✅ Stick to 1-2 font families maximum; more creates visual noise
-- ❌ Ignoring touch target sizes on mobile -> ✅ Minimum 44x44px touch targets (Apple HIG) / 48x48dp (Material Design)
-
----
-
-# Next-Gen Web Interface Review Guidelines (Pro-Max Level)
-
----
-
-## Review Trigger
-
-Load this skill when asked to:
-
-- Review or audit a UI
-- Check accessibility compliance (WCAG 3.0 / APCA)
-- Improve UX & Cognitive Safety
-- Check a site against best practices
+# Web Design Guidelines — Core Web Vitals & Sustainable UI
 
 ---
 
-## Extreme Review Categories
-
-### 1. Neuro-Inclusivity & Accessibility (WCAG 3.0 APCA Base)
-
-Non-negotiable baseline for any public interface in 2026+:
-
-| Check                   | How to Verify                                                                                                                                         |
-| ----------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **APCA Contrast**       | Ensure Lc (Lightness Contrast) is > 75 for body text, > 60 for large text. (Do not rely solely on old WCAG 2.1 4.5:1 math).                           |
-| **Cognitive Safety**    | Check if `prefers-reduced-motion` is respected. No infinite spinning loaders.                                                                         |
-| **Keyboard Fluidity**   | Tab order must follow visual order. Focus states cannot be just a 1px dotted line; use `outline: 2px solid var(--focus-color); outline-offset: 2px;`. |
-| **Semantic AI Context** | Images must have `alt` tags, but complex charts need full `<details>` breakdowns for screen readers and AI agents crawling the site.                  |
-| **Interaction Buffers** | Are touch targets mathematically ≥48px (Fitts' Law)?                                                                                                  |
-
-### 2. Extreme Core Web Vitals (CWV)
-
-Drop the old 2022 standards. The new baseline for premium web:
-
-| Metric                              | Premium Target | Common Failures                                                                                      |
-| ----------------------------------- | -------------- | ---------------------------------------------------------------------------------------------------- |
-| **LCP** (Largest Contentful Paint)  | **< 1.5s**     | Missing `fetchpriority="high"` on hero images. Heavy client-side React rendering blocking the paint. |
-| **INP** (Interaction to Next Paint) | **< 100ms**    | Main thread blocked by React hydrate. Use `startTransition` or Web Workers for heavy JS.             |
-| **CLS** (Cumulative Layout Shift)   | **0.00**       | Missing `width` and `height` on images. Late-loading web fonts (use `font-display: optional`).       |
-
-### 3. Energy Efficiency & Sustainability
-
-Code has a carbon footprint and a battery cost.
+## Mandatory Pre-Flight Context Inspection
 
-- **OLED Pure Black:** Does the dark mode use `#000` or `#010101` to physically turn off pixels?
-- **Animation Tax:** Are animations using CPU-heavy properties (`margin`, `width`) instead of GPU-accelerated ones (`transform`, `opacity`)?
-- **Asset Weight:** Are images AVIF/WebP? Are fonts subsetted Variable Fonts?
+Before enforcing web design guidelines or reviewing UI code, you MUST inspect:
+1. APCA Contrast Thresholds (Section 14) → Require Lc > 75 for body text, Lc > 60 for headings, Lc > 45 for controls/borders
+2. Core Web Vitals Targets (Section 23) → Ensure LCP < 1.5s (fetchpriority="high"), INP < 100ms, and CLS = 0.00 (explicit aspect-ratio)
+3. Compositor-Only Motion (Section 30) → Restrict animations strictly to `transform` and `opacity` to avoid layout reflows
 
-### 4. Visual Design Quality (Pro-Max)
-
-Evaluate these brutally honestly:
-
-- **Mathematical Spacing:** Does spacing follow a strict scale (e.g., 4, 8, 16, 24, 32) or is it a mess of arbitrary pixels?
-- **Fluid Typography:** Is text using `clamp()` to scale, or does it awkwardly jump at breakpoints?
-- **The "Purple Ban":** Is the site heavily relying on deep purple/violet as a primary color? (Flag this as an overused AI-generated cliché).
-- **Z-Axis Depth:** Are shadows realistic (multi-layered CSS shadows) or flat and cheap (`box-shadow: 0 4px 6px #000`)?
-- **Micro-Interactions:** Do buttons scale down slightly on `:active`? Do elements use spring-physics easing (`cubic-bezier(0.34, 1.56, 0.64, 1)`)?
-
-### 5. AI & Streaming UX
-
-- **Zero-Wait States:** If the app is waiting for an LLM/Server response, does it show a static spinner (BAD) or stream the skeleton/content (GOOD)?
-- **Optimistic UI:** Do likes/saves update the UI _instantly_ before the server confirms?
+This skill defines performance, accessibility, and rendering efficiency guidelines.
 
 ---
 
-## Common Review Findings
-
-| Finding                         | Severity  | Fix                                           |
-| ------------------------------- | --------- | --------------------------------------------- |
-| Missing/Weak focus styles       | High      | Add visible `:focus-visible` with offset      |
-| `margin`/`padding` animated     | High      | Change to `transform: translate()`            |
-| Touch targets under 48px        | High      | Increase padding/min-height                   |
-| Layout shifts on load (CLS > 0) | High      | Pre-allocate space for async content/images   |
-| Linear CSS transitions          | Medium    | Upgrade to spring-based `cubic-bezier` curves |
-| Purple as primary color         | Low/Brand | Rethink palette — overused AI design cliché   |
-
----
-
-## Audit Format Template
-
-When reporting a UI review, use this exact brutal structure:
-
-```markdown
-## UI/UX Pro-Max Review: [Component/Page Name]
-
-### ♿ Neuro-Inclusivity & A11y
-
-- [BLOCKER] [Finding with specific element and fix]
-- [WARN] [Finding]
-
-### ⚡ Performance & Energy (CWV)
-
-- [Finding]
-
-### 🎨 Visual & Spatial Quality
-
-- [Finding]
-
-### 🛠️ Interaction & Physics
+## 1. APCA Contrast Guidelines (WCAG 3.0 Base)
 
-- [Finding]
-
-### Summary
-
-X blockers, Y warnings, Z suggestions.
-Recommended action before shipping: [specific steps]
-```
+APCA calculates lightness contrast mathematically based on font size and background luminance.
+*   **Body Text:** Lc > 75 is required for body text readability.
+*   **Headings:** Lc > 60 is required for headings.
+*   **Controls/Borders:** Lc > 45 is required for visual divider borders and focus rings.
 
 ---
 
-## Output Format
-
-When this skill produces a recommendation or design decision, structure your output as:
-
-```
-━━━ Web Design Guidelines Recommendation ━━━━━━━━━━━━━━━━
-Decision:    [what was chosen / proposed]
-Rationale:   [why — one concise line]
-Trade-offs:  [what is consciously accepted]
-Next action: [concrete next step for the user]
-─────────────────────────────────────────────────
-Pre-Flight:  ✅ All checks passed
-             or ❌ [blocking item that must be resolved first]
-```
+## 2. Core Web Vitals (CWV)
+*   **Largest Contentful Paint (LCP < 1.5s):** Hero banners and images must use the `fetchpriority="high"` tag. Avoid blocking layout paints with heavy JS scripts.
+*   **Interaction to Next Paint (INP < 100ms):** Enforce main-thread speed. Wrap heavy operations in `startTransition` or React's deferred values.
+*   **Cumulative Layout Shift (CLS = 0.00):** Image nodes must declare explicit width/height dimensions or aspect-ratios. Pre-allocate spaces for dynamic elements.
 
 ---
 
----
-
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
-
-1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
-2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
-3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
-4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
+## 3. Sustainable & Battery-Efficient UI
+*   **Compositor Properties:** Transitions and animations must only animate `transform` and `opacity`. Animating properties like `margin`, `width`, `height`, or `top` triggers layout reflows and wastes CPU cycles.
+*   **OLED Blacks:** For dark luxury themes, base backgrounds must use OLED-friendly blacks (`oklch(0.08 0.005 250)` or `#000000`) to physically turn off pixels on compatible screens.
+*   **Font Subsetting:** Self-host typography files and use variable fonts to minimize network payloads.
+*   **Image Formats:** Serve images exclusively in AVIF or WebP formats.
 
 ---
 
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
-
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-
-Review these questions before confirming output:
-
-```
-✅ Did I rely ONLY on real, verified tools and methods?
-✅ Is this solution appropriately scoped to the user's constraints?
-✅ Did I handle potential failure modes and edge cases?
-✅ Have I avoided generic boilerplate that doesn't add value?
-```
-
-### 🛑 Verification-Before-Completion (VBC) Protocol
-
-**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
-- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
-
 ## Pre-Flight Checklist
-
 - [ ] Have I reviewed the user's specific constraints and requests?
 - [ ] Have I checked the environment for relevant existing implementations?
 
 ## VBC Protocol (Verification-Before-Completion)
-
 You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
-
----
-
-## 🤖 LLM-Specific Traps
-
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
-
-1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
-2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
-3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
-4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
-
----
-
-## 🏛️ Tribunal Integration (Anti-Hallucination)
-
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
-
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-
-### ✅ Pre-Flight Self-Audit
-
-Review these questions before confirming output:
-
-```
-✅ Did I rely ONLY on real, verified tools and methods?
-✅ Is this solution appropriately scoped to the user's constraints?
-✅ Did I handle potential failure modes and edge cases?
-✅ Have I avoided generic boilerplate that doesn't add value?
-```
-
-### 🛑 Verification-Before-Completion (VBC) Protocol
-
-**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
-- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.

package/.agent/skills/web-quality-audit/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: web-quality-audit
 description: Web quality auditing skill for Lighthouse-style analysis across Performance, Accessibility, Best Practices, and SEO signals.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Full-Stack Web Quality & Lighthouse Signals
-  tier: pro
-  co-requires: [web-accessibility-auditor, fixing-metadata, performance-profiling]
-  trigger-signals:
-    strong: [web-quality-audit, Lighthouse audit, Core Web Vitals audit, web quality report, LCP CLS INP audit]
-    weak: [quality audit, site audit]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - web-design-guidelines
+  - fixing-accessibility
+  - fixing-metadata
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Web Quality Audit — Lighthouse & Core Web Vitals
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before executing web quality audits or Lighthouse-style evaluations, you MUST inspect:
+1. Core Web Vitals Benchmarks (Section 24) → LCP $\le 2.5\text{s}$, INP $\le 200\text{ms}$, CLS $\le 0.1$
+2. Layout Shift Prevention (Section 27) → Enforce explicit `width`/`height` or aspect-ratio declarations on all media tags
+3. Async Script Loading (Section 46) → Enforce `async` or `defer` attributes on all third-party script tags in `<head>`
+
 Conduct a comprehensive multi-pillar web quality audit covering Performance, Accessibility, Best Practices, and SEO signals.
 
 ---

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

@@ -1,15 +1,29 @@
 ---
 name: webapp-testing
 description: Comprehensive Web Application Testing strategy. Test Pyramid, Vitest/Jest for unit logic, React Testing Library for component integrity, MSW (Mock Service Worker) for API layer simulation, and visual regression. Use when setting up testing environments or defining global test strategies across a web stack.
-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:
+  - testing-patterns
+  - playwright-best-practices
+  - tdd-workflow
+scripts-binding:
+  - .agent/scripts/test_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Webapp Testing — Full Stack Pipeline Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before building web application test suites or configuring component mocks, you MUST inspect:
+1. Testing Trophy Allocation (Section 27) → Prioritize Integration tests (60% RTL + MSW) over pure Unit (20%) or E2E (10%)
+2. MSW Network Interception Rule (Section 40) → Intercept HTTP network calls via MSW (`setupServer`); ban mocking library clients like `axios.get.mockResolvedValue`
+3. Decouple Business Logic from React (Section 99) → Extract complex calculations into pure testable functions outside React components
+
 ## Hallucination Traps (Read First)
 
 - ❌ Mocking everything in integration tests -> ✅ Integration tests verify real interactions; mock only external services (APIs, DBs)

package/.agent/skills/webgpu-performance/SKILL.md

@@ -1,13 +1,29 @@
 ---
 name: webgpu-performance
 description: High-performance browser graphics and compute mastery. Transitioning from WebGL to WebGPU API, WGSL compute shaders, explicit GPU memory management, and browser-side tensor calculations.
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - 60fps-animation
+  - fixing-motion-performance
+  - motion-engineering
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # WebGPU Performance Mastery
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before implementing WebGPU shaders or pipelines, you MUST inspect:
+1. Feature Detection (Section 64) → Always feature-detect WebGPU with `if (!navigator.gpu)` and provide WebGL fallback
+2. WGSL Buffer Alignment (Section 17) → Pad WGSL structs strictly to 16-byte boundaries (`vec4<f32>`) to prevent memory corruption
+3. Async Buffer Mapping (Section 68) → Use `mapAsync(GPUMapMode.READ)` to read GPU buffers without main-thread blocking
+
 You are an expert in writing low-level, high-performance browser graphics and compute pipelines using WebGPU and WGSL (WebGPU Shading Language). You prioritize explicit memory management, avoiding main-thread blocking, and utilizing the GPU for parallel computations (Compute Shaders) in modern web apps.
 
 ## 1. Core Principles

package/.agent/skills/whimsy-injector/SKILL.md

@@ -1,19 +1,29 @@
 ---
 name: whimsy-injector
 description: Micro-delight generator for frontend interfaces. Suggests and implements subtle animations, playful transitions, and interaction polish across any frontend stack.
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
 skills:
-  - frontend-design
-  - trend-researcher
-  - ui-ux-researcher
-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
+  - delight
+  - micro-interaction
+  - 60fps-animation
+  - accessible-animation
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
-# Whimsy Injector Skill
+# Whimsy Injector Skill — Micro-Delight Generator
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before injecting micro-animations or interaction polish, you MUST inspect:
+1. `package.json` → Check installed motion dependencies (`framer-motion`, `gsap`, `@vueuse/motion`, CSS-only)
+2. Whimsy Quota Rules (Section 228) → Max 3 distinct animation types per page; keep CLS impact at ZERO
+3. Duration Constraints (Section 238) → Keep hover interactions $\le 150\text{ms}$ and entrance animations $\le 300\text{ms}$
 
 You are a specialized agent for injecting "micro-delights" into user interfaces — small, tasteful animations and interaction polish that make an app feel alive and premium. You work across all frontend stacks: vanilla CSS, React, Vue, Svelte, Angular, and static HTML.
 

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

@@ -1,19 +1,29 @@
 ---
 name: workflow-optimizer
 description: Analyzes agent tool-calling patterns and task execution efficiency to suggest process improvements.
+version: 3.0.0
+last-updated: 2026-07-30
 skills:
   - parallel-agents
   - plan-writing
-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
+  - fabel-protocol
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/verify_all.js
+  - .agent/scripts/checklist.js
 ---
 
 # Workflow Optimizer Skill
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before analyzing tool-calling logs or task efficiency, you MUST inspect:
+1. Tool Call Pattern Analysis table (Section 1) → Classify redundant reads, serial bottlenecks, and context dumps
+2. Parallelism Opportunity Detection (Section 2) → Verify read/write dependency rules for batch tool calls
+3. Efficiency Score formula (Section 105) → Compute actual vs optimal call ratios accurately
+
 You are a specialized agent for analyzing and optimizing the efficiency of AI agent workflows, task execution loops, and tool-calling patterns. You act as a "meta-debugger" — debugging the _process_, not the _code_.
 
 ## When to Activate