tribunal-kit 8.0.0 → 9.0.0

package/.agent/skills/fixing-metadata/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: fixing-metadata
 description: Audit and fix page metadata including page titles, meta descriptions, Open Graph, Twitter cards, canonical URLs, and JSON-LD structured data.
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - nextjs-react-expert
   - baseline-ui
@@ -27,6 +27,12 @@ Before engineering metadata or Open Graph tags, you MUST inspect:
 
 Audit, generate, and fix page metadata for rich social previews, search engine indexing, and structured data.
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Audit and fix page metadata including page titles, meta descriptions, Open Graph, Twitter cards, canonical URLs, and JSON-LD structured data..
+- **DO NOT activate when:** The task falls strictly outside fixing-metadata domain or belongs to a different dedicated specialist.
+
 ---
 
 ## 4 Metadata Standard Requirements
@@ -90,28 +96,25 @@ export const metadata: Metadata = {
 
 ---
 
-## 🤖 LLM-Specific Traps
+## 🏛️ Tribunal Verification & Guardrails
 
-1. **Relative Image URLs in OG Metadata**: Using `<meta property="og:image" content="/og.jpg">` instead of full absolute HTTPS URLs (`https://domain.com/og.jpg`).
-2. **Missing `summary_large_image`**: Forgetting `twitter:card` type, causing Twitter/X to render a tiny square thumbnail instead of a prominent banner preview.
-
----
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
-
-**Active reviewers: `seo-specialist` · `frontend-reviewer`**
+### ❌ 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
-
 ```
-✅ Are OpenGraph and Twitter card image URLs absolute HTTPS links?
-✅ Is title length between 50 and 60 characters?
-✅ Is canonical URL explicitly defined?
+✅ 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/fixing-motion-performance/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: fixing-motion-performance
 description: Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - 60fps-animation
   - motion-engineering
@@ -27,6 +27,12 @@ Before auditing or fixing animation performance, you MUST inspect:
 
 Guidelines for auditing and resolving web animation jank, layout thrashing, and GPU rendering bottlenecks.
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance..
+- **DO NOT activate when:** The task falls strictly outside fixing-motion-performance domain or belongs to a different dedicated specialist.
+
 ---
 
 ## 1. Browser Rendering Pipeline & Compositor Rules
@@ -85,23 +91,25 @@ elements.forEach((el, i) => {
 
 ---
 
-## 🤖 LLM-Specific Traps
+## 🏛️ Tribunal Verification & Guardrails
 
-1. **`transition: all`**: Using `all` causes layout recalculation and repaint on every hover.
-2. **`requestAnimationFrame` Memory Leaks**: Launching continuous `rAF` loops without cancellation logic (`cancelAnimationFrame`).
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
 
----
-
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+### ❌ 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
-
 ```
-✅ Are all continuous animations restricted strictly to transform and opacity?
-✅ Are DOM reads and writes batched to eliminate layout thrashing?
-✅ Is will-change used sparingly on active animated elements only?
+✅ 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
-
-Inspect Chrome Performance tab rendering profile in live preview to verify 60/120fps motion without frame drops.
+**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/framer-motion-expert/SKILL.md

@@ -2,8 +2,8 @@
 name: framer-motion-expert
 description: Framer Motion 12+ for React. Declarative animations, layout transitions, gestures, scroll-linked motion, AnimatePresence, useAnimate, LazyMotion. Use when building component animations, page transitions, shared layout animations, or gesture-driven UI.
 tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - motion-engineering
   - 60fps-animation
@@ -25,6 +25,12 @@ Before writing Framer Motion code in React, you MUST inspect:
 2. AnimatePresence & layoutId Rules (Section 117) → Enforce `mode="wait"` and ensure every `<AnimatePresence>` child has a unique `key`
 3. Bundle Optimization (Section 182) → Use `<LazyMotion features={domAnimation}>` with `m.div` for lightweight production bundles
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Framer Motion 12+ for React. Declarative animations, layout transitions, gestures, scroll-linked motion, AnimatePresence, useAnimate, LazyMotion. Use when building component animations, page transitions, shared layout animations, or gesture-driven UI..
+- **DO NOT activate when:** The task falls strictly outside framer-motion-expert domain or belongs to a different dedicated specialist.
+
 ## Hallucination Traps (Read First)
 
 - ❌ `<Motion>` (capital M) → ✅ `motion.div` (lowercase dot notation)
@@ -244,69 +250,17 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-**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)
+## 🏛️ Tribunal Verification & Guardrails
 
 **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?
@@ -315,8 +269,6 @@ Review these questions before confirming output:
 ```
 
 ### 🛑 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/frontend-design/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: frontend-design
 description: Design engineering principles for React/Next.js. Relative color syntax (OKLCH), spatial grid math, fluid container queries, and contrast validation.
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - baseline-ui
   - better-colors
@@ -27,6 +27,12 @@ Before implementing front-end designs or CSS layout systems, you MUST inspect:
 
 This skill guides the implementation of responsive layout systems, color science, and spatial tokens.
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Design engineering principles for React/Next.js. Relative color syntax (OKLCH), spatial grid math, fluid container queries, and contrast validation..
+- **DO NOT activate when:** The task falls strictly outside frontend-design domain or belongs to a different dedicated specialist.
+
 ---
 
 ## 1. Relative Color Syntax & OKLCH Theme Tokens
@@ -110,11 +116,25 @@ Ensure that typography meets the APCA Lc guidelines:
 
 ---
 
-## Pre-Flight Checklist
+## 🏛️ Tribunal Verification & Guardrails
 
-- [ ] Have I reviewed the user's specific constraints and requests?
-- [ ] Have I checked the environment for relevant existing implementations?
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
 
-## VBC Protocol (Verification-Before-Completion)
+### ❌ 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
+```
+✅ 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?
+```
 
-You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
+### 🛑 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/frontend-security-expert/SKILL.md

@@ -2,8 +2,8 @@
 name: frontend-security-expert
 description: Frontend security auditing for modern meta-frameworks. Focuses on React/Next.js UI paradigms, hydration poisoning, third-party script supply chain, local storage security, and XSS prevention in modern environments.
 tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - backend-security-expert
   - api-security-auditor
@@ -25,7 +25,11 @@ Before auditing or writing client-side code, you MUST inspect:
 2. HttpOnly Auth Token Storage (Section 34) → Ban storing JWTs or auth tokens in `localStorage` or `sessionStorage`; use `HttpOnly`, `Secure`, `SameSite` cookies
 3. PostMessage Origin Verification (Section 46) → Never use `targetOrigin: '*'` and always validate `event.origin` on receiving handlers
 
-# Frontend Security Expert — Modern Meta-Frameworks
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Frontend security auditing for modern meta-frameworks. Focuses on React/Next.js UI paradigms, hydration poisoning, third-party script supply chain, local storage security, and XSS prevention in modern environments..
+- **DO NOT activate when:** The task falls strictly outside frontend-security-expert domain or belongs to a different dedicated specialist.
 
 ## Hallucination Traps (Read First)
 
@@ -73,69 +77,17 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-**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)
+## 🏛️ Tribunal Verification & Guardrails
 
 **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?
@@ -144,8 +96,6 @@ Review these questions before confirming output:
 ```
 
 ### 🛑 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/game-design-expert/SKILL.md

@@ -2,8 +2,8 @@
 name: game-design-expert
 description: Game Design, UX, and Flow State mastery. Replaces fragmented legacy skills. Core gameplay loop design, 3Cs (Character, Camera, Controls), input buffering, coyote time, juice (game feel), telemetry tracking, narrative alignment, and audio spatialization integration. Use when crafting player experience, progression arcs, or systemic balance.
 tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - game-engineering-expert
   - 12-principles-of-animation
@@ -25,6 +25,12 @@ Before designing gameplay systems or controller feel, you MUST inspect:
 2. Macro Gameplay Loop Validation (Section 42) → Ensure upgrading systems directly alter action and combat feel to prevent player churn
 3. Juicing & Hitstop Feel (Section 58) → Incorporate screen shake, hitstop (3 freeze frames), particle explosions, and squash-and-stretch for impact feedback
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Game Design, UX, and Flow State mastery. Replaces fragmented legacy skills. Core gameplay loop design, 3Cs (Character, Camera, Controls), input buffering, coyote time, juice (game feel), telemetry tracking, narrative alignment, and audio spatialization integration. Use when crafting player experience, progression arcs, or systemic balance..
+- **DO NOT activate when:** The task falls strictly outside game-design-expert domain or belongs to a different dedicated specialist.
+
 ## Hallucination Traps (Read First)
 
 - ❌ Designing reward systems without testing for compulsion loops -> ✅ Playtesting must verify engagement without addiction patterns
@@ -33,8 +39,6 @@ Before designing gameplay systems or controller feel, you MUST inspect:
 
 ---
 
-# Game Design Expert — Player Experience & Flow Mastery
-
 ---
 
 ## 1. The 3Cs (Character, Camera, Controls)
@@ -111,69 +115,17 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-**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)
+## 🏛️ Tribunal Verification & Guardrails
 
 **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?
@@ -182,8 +134,6 @@ Review these questions before confirming output:
 ```
 
 ### 🛑 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/game-engineering-expert/SKILL.md

@@ -2,8 +2,8 @@
 name: game-engineering-expert
 description: Game Engineering and Systems Architecture mastery. Replaces fragmented legacy skills. Entity Component Systems (ECS), Unity (C#) / Godot (GDScript) integration, physics calculations, deterministic engine state, WebGL memory management, multiplayer sync architectures (deterministic lockstep vs traditional authoritative), spatial partitioning, and rendering pipelines.
 tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - game-design-expert
   - csharp-developer
@@ -25,6 +25,12 @@ Before engineering game state loops or physics engines, you MUST inspect:
 2. Garbage Collection & Object Pooling (Section 50) → Pre-allocate and pool game objects; ban `Instantiate()` or dynamic memory allocations in frame update loops
 3. FixedUpdate vs Update Separation (Section 43) → Put all physics logic in `FixedUpdate()`; use `Update()` strictly for visual interpolation and input collection
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Game Engineering and Systems Architecture mastery. Replaces fragmented legacy skills. Entity Component Systems (ECS), Unity (C#) / Godot (GDScript) integration, physics calculations, deterministic engine state, WebGL memory management, multiplayer sync architectures (deterministic lockstep vs traditional authoritative), spatial partitioning, and rendering pipelines..
+- **DO NOT activate when:** The task falls strictly outside game-engineering-expert domain or belongs to a different dedicated specialist.
+
 ## Hallucination Traps (Read First)
 
 - ❌ Using deltaTime without clamping -> ✅ Unclamped deltaTime causes physics explosions on frame spikes; clamp to max 0.05s
@@ -33,8 +39,6 @@ Before engineering game state loops or physics engines, you MUST inspect:
 
 ---
 
-# Game Engineering Expert — Performance & State Mastery
-
 ---
 
 ## 1. Frame Rate Architecture (The Update Loop)
@@ -127,69 +131,17 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-**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)
+## 🏛️ Tribunal Verification & Guardrails
 
 **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?
@@ -198,8 +150,6 @@ Review these questions before confirming output:
 ```
 
 ### 🛑 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.