tribunal-kit 8.0.0 → 9.0.1

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

@@ -1,13 +1,13 @@
 ---
 name: git-pro
-description: Industry-level Git & GitHub mastery. Advanced Git internals (bisect, worktrees, reflog), monorepo strategies (Turborepo/Nx), semantic-release, OIDC-based GitHub Actions auth (no static AWS secrets), CODEOWNERS, matrix builds, reusable workflows, and release engineering. Use when advanced Git operations, complex branching strategies, or production-grade CI/CD workflow authoring is required.
-tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+description: Use when Industry-level Git & GitHub mastery. Advanced Git internals (bisect, worktrees, reflog), monorepo strategies (Turborepo/Nx), semantic-release, OIDC-based GitHub Actions auth (no static AWS secrets), CODEOWNERS, matrix builds, reusable workflows, and release engineering. Use when advanced Git operations, complex branching strategies, or production-grade CI/CD workflow authoring is required.
+version: 5.0.0
+last-updated: 2026-09-13
 skills:
   - github-operations
   - cicd-pro
   - bash-linux
+tools: Read, Grep, Glob, Bash, Edit, Write
 scripts-binding:
   - .agent/scripts/lint_runner.js
   - .agent/scripts/verify_all.js
@@ -15,15 +15,41 @@ scripts-binding:
 
 # Git Pro — Industry-Level Mastery
 
+## Mandatory Pre-Flight Context Inspection
+
+Before generating, refactoring, or reviewing code in the `git-pro` domain, inspect these 5 critical parameters:
+
+1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
+2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
+3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
+4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
+5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).
+
+## Activation Boundaries
+
+- **Activate when:** Use when Industry-level Git & GitHub mastery. Advanced Git internals (bisect, worktrees, reflog), monorepo strategies (Turborepo/Nx), semantic-release, OIDC-based GitHub Actions auth (no static AWS secrets), CODEOWNERS, matrix builds, reusable workflows, and release engineering. Use when advanced Git operations, complex branching strategies, or production-grade CI/CD workflow authoring is required.
+- **DO NOT activate when:** The task falls outside the `git-pro` domain or is managed by a different dedicated specialist.
+
+## 🔁 Multi-Pass Execution Protocol
+
+Execute all non-trivial tasks through this 7-pass cognitive loop:
+
+| Pass | Phase | Core Action |
+|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
+| **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
+| **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
+| **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
+| **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
+
 ---
 
-## Mandatory Pre-Flight Context Inspection
+## 🛠️ Technical Architecture & Reference Recipes
 
-Before running complex Git operations or writing release workflows, you MUST inspect:
+---
 
-1. Safe Force Push Rule (Section 18) → Use `--force-with-lease` exclusively; ban raw `git push --force` on shared/remote branches
-2. Reflog Recovery Strategy (Section 30) → Inspect `git reflog` to recover lost commits or bad resets before discarding uncommitted state
-3. OIDC Authentication Protocol (Section 208) → Configure OIDC AWS auth (`id-token: write`) in GitHub Actions workflows; ban static AWS access keys
 
 ## Hallucination Traps (Read First)
 
@@ -35,8 +61,6 @@ Before running complex Git operations or writing release workflows, you MUST ins
 
 ---
 
-# Git Pro — Industry-Level Mastery
-
 ## 1. Advanced Git Internals
 
 ### Reflog Recovery (Your Safety Net)
@@ -408,40 +432,45 @@ resource "github_branch_protection" "main" {
 
 ---
 
-## 🤖 LLM-Specific Traps
+## 🚨 Edge-Case & Failure Mode Matrix
 
-1. **`--force` without `--force-with-lease`**: Always use `--force-with-lease`. It fails safely if the remote has new commits, preventing accidental overwrite of teammates' work.
-2. **Rebasing public history**: Never rebase commits already pushed to a shared branch. Use `git revert` to safely undo public commits.
-3. **`GITHUB_TOKEN` scope confusion**: `secrets.GITHUB_TOKEN` cannot trigger other workflows and has limited cross-repo access. Use a GitHub App token for automation.
-4. **Missing `fetch-depth: 0`**: `semantic-release` and `git describe` require full history. Shallow clones (`fetch-depth: 1`) will cause failures.
-5. **Hardcoded branch names in workflows**: Use `github.event.repository.default_branch` or `vars.` instead of hardcoding `main`.
+| Scenario | Risk | Mitigation Strategy |
+|:---|:---|:---|
+| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
+| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
+| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
+| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
+| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
 
 ---
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+## 🤖 LLM-Specific Traps Table
+
+| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
+|:---|:---|:---|
+| **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
+| **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
+| **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
 
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor` · `devops-engineer`**
+---
 
-### ❌ Forbidden AI Tropes
+## 🏛️ Tribunal Verification & Guardrails
 
-1. **Blind Assumptions**: Never assume AWS account IDs, role ARNs, or org names. Always use variables/inputs.
-2. **Static Secrets**: Never suggest `AWS_ACCESS_KEY_ID` in GitHub Actions. Always use OIDC.
-3. **`git push --force`**: Never suggest force pushing to shared/protected branches without `--force-with-lease`.
+**Active Reviewers:** `orchestrator` · `agent-organizer` · `logic-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
 
-### ✅ Pre-Flight Self-Audit
+### ✅ Pre-Flight Self-Audit Checklist
 
 ```
-✅ Are all AWS credentials using OIDC (not static keys)?
-✅ Are all branch operations checked for public/shared status first?
-✅ Did I verify `semantic-release` plugins are in package.json?
-✅ Are CODEOWNERS paths relative to repository root?
-✅ Did I include `fetch-depth: 0` where git history is required?
+✅ Did I deconstruct the root objective before proposing architecture?
+✅ Did I identify dependencies, bottlenecks, and parallelizable sub-tasks?
+✅ Did I avoid over-engineering and select the simplest effective pattern?
+✅ Did I verify assumptions with concrete file reads instead of speculation?
+✅ Did I establish measurable verification criteria before completion?
 ```
 
 ### 🛑 Verification-Before-Completion (VBC) Protocol
 
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
-- ❌ **Forbidden**: Declaring a workflow correct because the YAML "looks right."
-- ✅ **Required**: Verify with `act` locally or confirm CI run passes before declaring success.
+- ❌ **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 test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agent/skills/github-operations/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: github-operations
-description: Git and GitHub workflow mastery. Branching strategies (Git Flow, trunk-based), commit message conventions, interactive rebase, merge conflict resolution, pull request best practices, GitHub Actions, branch protection rules, monorepo strategies, and git hooks. Use when working with Git, GitHub Actions, or any version control operations.
-tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+description: Use when Git and GitHub workflow mastery. Branching strategies (Git Flow, trunk-based), commit message conventions, interactive rebase, merge conflict resolution, pull request best practices, GitHub Actions, branch protection rules, monorepo strategies, and git hooks. Use when working with Git, GitHub Actions, or any version control operations.
+version: 5.0.0
+last-updated: 2026-09-13
 skills:
   - git-pro
   - cicd-pro
   - bash-linux
+tools: Read, Grep, Glob, Bash, Edit, Write
 scripts-binding:
   - .agent/scripts/lint_runner.js
   - .agent/scripts/verify_all.js
@@ -15,17 +15,41 @@ scripts-binding:
 
 # GitHub Operations — Git & CI/CD Workflow Mastery
 
----
-
 ## Mandatory Pre-Flight Context Inspection
 
-Before running Git commands or writing GitHub workflows, you MUST inspect:
+Before generating, refactoring, or reviewing code in the `github-operations` domain, inspect these 5 critical parameters:
 
-1. Local-Only Interactive Rebase (Section 172) → Perform interactive rebases (`git rebase -i`) ONLY on local unpushed commits; ban rebasing public/shared history
-2. Conventional Commit Standards (Section 55) → Format commit messages using Conventional Commits (`type(scope): description`) for automated changelogs
-3. Squash Merge Default (Section 146) → Enforce squash merge strategy for feature branches merging into main to keep history linear and clean
+1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
+2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
+3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
+4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
+5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).
+
+## Activation Boundaries
+
+- **Activate when:** Use when Git and GitHub workflow mastery. Branching strategies (Git Flow, trunk-based), commit message conventions, interactive rebase, merge conflict resolution, pull request best practices, GitHub Actions, branch protection rules, monorepo strategies, and git hooks. Use when working with Git, GitHub Actions, or any version control operations.
+- **DO NOT activate when:** The task falls outside the `github-operations` domain or is managed by a different dedicated specialist.
+
+## 🔁 Multi-Pass Execution Protocol
+
+Execute all non-trivial tasks through this 7-pass cognitive loop:
+
+| Pass | Phase | Core Action |
+|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
+| **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
+| **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
+| **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
+| **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
+
+---
+
+## 🛠️ Technical Architecture & Reference Recipes
+
+---
 
-# GitHub Operations — Git & CI/CD Workflow Mastery
 
 ---
 
@@ -302,91 +326,45 @@ export default {
 
 ---
 
----
-
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
+## 🚨 Edge-Case & Failure Mode Matrix
 
-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.
+| Scenario | Risk | Mitigation Strategy |
+|:---|:---|:---|
+| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
+| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
+| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
+| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
+| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
 
 ---
 
-**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.
+## 🤖 LLM-Specific Traps Table
 
-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.
+| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
+|:---|:---|:---|
+| **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
+| **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
+| **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
 
 ---
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
-
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
+## 🏛️ Tribunal Verification & Guardrails
 
-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.
+**Active Reviewers:** `orchestrator` · `agent-organizer` · `logic-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
 
-### ✅ Pre-Flight Self-Audit
-
-Review these questions before confirming output:
+### ✅ Pre-Flight Self-Audit Checklist
 
 ```
-✅ 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?
+✅ Did I deconstruct the root objective before proposing architecture?
+✅ Did I identify dependencies, bottlenecks, and parallelizable sub-tasks?
+✅ Did I avoid over-engineering and select the simplest effective pattern?
+✅ Did I verify assumptions with concrete file reads instead of speculation?
+✅ Did I establish measurable verification criteria before completion?
 ```
 
 ### 🛑 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.
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agent/skills/gpt-taste/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: gpt-taste
-description: High-agency UX/UI skill with strict layout variance, typography, and GSAP motion engineering constraints for superior visual judgment.
-version: 3.0.0
-last-updated: 2026-07-30
+description: Use when High-agency UX/UI skill with strict layout variance, typography, and GSAP motion engineering constraints for superior visual judgment.
+version: 5.0.0
+last-updated: 2026-09-13
 skills:
   - taste-skill
   - better-ui
@@ -15,17 +15,41 @@ scripts-binding:
 
 # GPT Taste — High-Agency Visual Refinement & Layout Variance
 
----
-
 ## Mandatory Pre-Flight Context Inspection
 
-Before generating UI layouts or visual code, you MUST inspect:
+Before generating, refactoring, or reviewing code in the `gpt-taste` domain, inspect these 5 critical parameters:
+
+1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
+2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
+3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
+4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
+5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).
+
+## Activation Boundaries
+
+- **Activate when:** Use when High-agency UX/UI skill with strict layout variance, typography, and GSAP motion engineering constraints for superior visual judgment.
+- **DO NOT activate when:** The task falls outside the `gpt-taste` domain or is managed by a different dedicated specialist.
 
-1. Structural Layout Variance (Section 24) → Vary structural layout across sections; ban uniform 3-card bento grids
-2. OKLCH Perceptual Palette (Section 30) → Declare all color tokens using OKLCH color space for perceptual uniformity
-3. Zero Truncation Rule (Section 39) → Strictly ban `// TODO: add remaining items` placeholder comments; generate complete production-ready code
+## 🔁 Multi-Pass Execution Protocol
+
+Execute all non-trivial tasks through this 7-pass cognitive loop:
+
+| Pass | Phase | Core Action |
+|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
+| **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
+| **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
+| **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
+| **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
+
+---
+
+## 🛠️ Technical Architecture & Reference Recipes
+
+---
 
-Inject high-agency visual judgment and layout variance into AI-generated interfaces.
 
 ---
 
@@ -57,28 +81,45 @@ Never output placeholder `// TODO: add remaining items` comments in UI code. Gen
 
 ---
 
-## 🤖 LLM-Specific Traps
+## 🚨 Edge-Case & Failure Mode Matrix
+
+| Scenario | Risk | Mitigation Strategy |
+|:---|:---|:---|
+| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
+| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
+| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
+| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
+| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
+
+---
+
+## 🤖 LLM-Specific Traps Table
 
-1. **Truncated Code Outputs**: Outputting incomplete code snippets or placeholder comments.
-2. **Symmetrical Grid Boredom**: Using 3 identical square cards side-by-side without visual hierarchy differentiation.
+| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
+|:---|:---|:---|
+| **Uncontrolled Re-render Loop** | Mutating state inside render bodies or omitting hook dependencies | Wrap effects with explicit deps and isolate reactive derivations in useMemo |
+| **Accessibility Neglect** | Interactive <div> without role="button", tabIndex, or onKeyDown | Use semantic <button> or provide ARIA role, keyboard handlers, and focus ring |
+| **Layout Shift Flash** | Images/dynamic content without aspect-ratio or explicit dimensions | Enforce aspect-ratio or skeleton placeholders to guarantee zero CLS |
 
 ---
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+## 🏛️ Tribunal Verification & Guardrails
 
-**Active reviewers: `frontend-reviewer` · `ui-ux-auditor`**
+**Active Reviewers:** `frontend-reviewer` · `type-safety` · `ui-ux-auditor` · `complexity-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
 
-### ✅ Pre-Flight Self-Audit
+### ✅ Pre-Flight Self-Audit Checklist
 
 ```
-✅ Are code outputs 100% complete without placeholder TODOs?
-✅ Is structural layout varied across different page sections?
-✅ Are colors declared via OKLCH variables?
+✅ Are all component props strictly typed with zero implicit "any"?
+✅ Are responsive breakpoints, fluid typography, and optical balance verified?
+✅ Is accessibility (ARIA labels, keyboard focus, contrast) validated?
+✅ Are re-renders minimized and state lifecycles cleanly separated?
+✅ Did I verify all imported UI components and icon sets actually exist?
 ```
 
 ### 🛑 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.
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.