tribunal-kit 7.0.0 → 9.0.0

package/.agent/skills/antfu-conventions/SKILL.md

@@ -2,8 +2,8 @@
 name: antfu-conventions
 description: Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects: ESM-first, zero-config, type-safe, and clean tooling standards.
 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:
   - clean-code
   - typescript-advanced
@@ -25,10 +25,14 @@ Before configuring JS/TS tooling or lint rules, you MUST inspect:
 2. ESLint Flat Config (`eslint.config.js`) (Section 28) → Use `@antfu/eslint-config` with flat config format; ban legacy `.eslintrc.json`
 3. Explicit Type Imports (`import type`) (Section 45) → Enforce `import type` for type-only symbols to allow clean tree-shaking compilation
 
-# Antfu Conventions — ESM-First & Opinionated Modern Tooling
-
 Enforce Anthony Fu's modern JavaScript/TypeScript engineering conventions: ESM-first, zero-config, pnpm workspaces, and strict type safety.
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects: ESM-first, zero-config, type-safe, and clean tooling standards..
+- **DO NOT activate when:** The task falls strictly outside antfu-conventions domain or belongs to a different dedicated specialist.
+
 ---
 
 ## 4 Core Tooling Conventions
@@ -63,28 +67,25 @@ export default antfu({
 
 ---
 
-## 🤖 LLM-Specific Traps
+## 🏛️ Tribunal Verification & Guardrails
 
-1. **Mixing CommonJS and ESM**: Generating `require()` calls inside `"type": "module"` ESM packages.
-2. **Legacy ESLint `.eslintrc.json`**: Generating deprecated legacy ESLint configs instead of modern Flat Config `eslint.config.js`.
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
 
----
-
-## 🏛️ Tribunal Integration (Anti-Hallucination)
-
-**Active reviewers: `type-safety` · `dependency-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
-
 ```
-✅ Is `"type": "module"` active in package.json?
-✅ Are type imports declared explicitly with `import type`?
-✅ Is `eslint.config.js` flat config format used?
+✅ 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/api-patterns/SKILL.md

@@ -2,8 +2,8 @@
 name: api-patterns
 description: API design mastery. REST, GraphQL, tRPC, and gRPC selection. Request/response design, pagination (cursor/offset), filtering, versioning, rate limiting, error formats (RFC 9457), authentication (JWT/OAuth2/API keys), idempotency, file uploads, webhooks, and OpenAPI documentation. Use when designing APIs, choosing protocols, or implementing API standards.
 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:
   - api-security-auditor
   - backend-security-expert
@@ -25,7 +25,11 @@ Before designing or implementing API endpoints, you MUST inspect:
 2. Cursor-Based Pagination (Section 19) → Use cursor pagination for datasets >10K rows to eliminate `OFFSET N` performance degradation
 3. Idempotency Header for Mutations (Section 21) → Require `Idempotency-Key` headers for state-changing `POST` or `PATCH` retry operations
 
-# API Patterns — Design & Protocol Mastery
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring API design mastery. REST, GraphQL, tRPC, and gRPC selection. Request/response design, pagination (cursor/offset), filtering, versioning, rate limiting, error formats (RFC 9457), authentication (JWT/OAuth2/API keys), idempotency, file uploads, webhooks, and OpenAPI documentation. Use when designing APIs, choosing protocols, or implementing API standards..
+- **DO NOT activate when:** The task falls strictly outside api-patterns domain or belongs to a different dedicated specialist.
 
 ## Hallucination Traps (Read First)
 
@@ -235,69 +239,17 @@ 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?
@@ -306,8 +258,6 @@ 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/api-security-auditor/SKILL.md

@@ -2,8 +2,8 @@
 name: api-security-auditor
 description: API Security auditing mastery. Rate limiting architecture, API key management, payload validation, IDOR (Insecure Direct Object Reference) prevention, mass assignment flaws, GraphQL security, and server-side mitigations. Use when building external APIs, B2B services, or reviewing endpoint security.
 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
   - vulnerability-scanner
@@ -25,7 +25,11 @@ Before auditing or hardening API endpoints, you MUST inspect:
 2. Mass Assignment Mitigations (Section 47) → Enforce strict Zod schemas (`.strict()`) to prevent parameter overposting into DB updates
 3. Distributed Rate Limiting (Section 80) → Store rate limit state in Redis for multi-pod load balanced environments to prevent limit bypasses
 
-# API Security Auditor — Endpoint Hardening Mastery
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring API Security auditing mastery. Rate limiting architecture, API key management, payload validation, IDOR (Insecure Direct Object Reference) prevention, mass assignment flaws, GraphQL security, and server-side mitigations. Use when building external APIs, B2B services, or reviewing endpoint security..
+- **DO NOT activate when:** The task falls strictly outside api-security-auditor domain or belongs to a different dedicated specialist.
 
 ---
 
@@ -174,69 +178,17 @@ 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?
@@ -245,8 +197,6 @@ 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/app-builder/SKILL.md

@@ -2,8 +2,8 @@
 name: app-builder
 description: Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
 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:
   - nextjs-react-expert
   - react-specialist
@@ -25,6 +25,12 @@ Before scaffolding or orchestrating application builds, you MUST inspect:
 2. Plan Verification (Section 220) → Ensure `{task-slug}.md` is created and verified in project root before invoking specialist agents
 3. Incremental Build Rule (Section 15) → Never generate entire applications in one shot; build and verify module by module
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents..
+- **DO NOT activate when:** The task falls strictly outside app-builder domain or belongs to a different dedicated specialist.
+
 ## Hallucination Traps (Read First)
 
 - ❌ Generating entire applications in one shot -> ✅ Build one module at a time, verify each
@@ -33,8 +39,6 @@ Before scaffolding or orchestrating application builds, you MUST inspect:
 
 ---
 
-# App Builder — Application Orchestrator
-
 ---
 
 ## When This Skill Activates
@@ -552,69 +556,17 @@ 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?
@@ -623,8 +575,6 @@ 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/appflow-wireframe/SKILL.md

@@ -2,16 +2,26 @@
 name: appflow-wireframe
 description: Application flow and wireframing mastery. Mermaid.js flowcharting, state diagrams, user journey mapping, interaction matrices, explicit screen boundary demarcation, and accessibility flow modeling. Use when planning UI architectures, designing user onboarding flows, or visualizing complex state machines before writing code.
 allowed-tools: Read, Write, Edit, Glob, Grep
-version: 2.0.0
-last-updated: 2026-04-02
+version: 4.0.0
+last-updated: 2026-09-07
 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
 ---
 
 ## Hallucination Traps (Read First)
 
+
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Application flow and wireframing mastery. Mermaid.js flowcharting, state diagrams, user journey mapping, interaction matrices, explicit screen boundary demarcation, and accessibility flow modeling. Use when planning UI architectures, designing user onboarding flows, or visualizing complex state machines before writing code..
+- **DO NOT activate when:** The task falls strictly outside appflow-wireframe domain or belongs to a different dedicated specialist.
+
 - ❌ Drawing wireframes without defined user personas -> ✅ Establish WHO uses each screen before designing
 - ❌ Skipping error/empty/loading states in flow diagrams -> ✅ Every screen needs 4 states: loading, empty, populated, error
 - ❌ Assuming linear user journeys -> ✅ Real users jump between screens, go back, and abandon flows mid-way
@@ -110,69 +120,17 @@ 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?
@@ -181,8 +139,6 @@ 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/apple-design/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: apple-design
 description: Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations behind Apple-style interfaces.
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - soft-skill
   - emil-design-eng
@@ -27,6 +27,12 @@ Before engineering Apple-style UIs or gesture-driven components, you MUST inspec
 
 Design engineering guidelines for bringing Apple's fluid, physical interface paradigms to modern web applications.
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations behind Apple-style interfaces..
+- **DO NOT activate when:** The task falls strictly outside apple-design domain or belongs to a different dedicated specialist.
+
 ---
 
 ## 1. Physics-Based Spring Animations
@@ -96,23 +102,25 @@ Apple depth relies on subtle, multi-layered backdrop blur and border highlights:
 
 ---
 
-## 🤖 LLM-Specific Traps
+## 🏛️ Tribunal Verification & Guardrails
 
-1. **Over-using Blur**: Applying `backdrop-filter: blur(30px)` to dozens of items causes severe GPU frame drops during scrolling. Apply blur to sticky headers or modal backdrops only.
-2. **Non-Interruptible Gestures**: Using CSS `transition: transform 0.5s ease` for drag or swipe handlers instead of gesture springs.
+**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 spring animations interruptible with realistic mass/stiffness/damping?
-✅ Is backdrop-filter limited to top-level sticky surfaces and modals?
-✅ Does letter-spacing scale inversely with font size (tighter for large titles)?
+✅ 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
-
-Test gesture response and spring motion in live preview to ensure 60/120fps fluidity without GPU lag.
+**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.