tribunal-kit 9.0.2 → 9.2.3

package/.agents/skills/improve-ui/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: improve-ui
-description: Use when Audit an existing product surface against its own design evidence, identify verified UI problems, and write self-contained implementation plans for another agent. Strictly read-only on product source. Use when asked to review, refine, improve, or clean up an interface without replacing its identity.
+description: "Use when Audit an existing product surface against its own design evidence, identify verified UI problems, and write self-contained implementation plans for another agent. Strictly read-only on product source. Use when asked to review, refine, improve, or clean up an interface without replacing its identity."
 version: 5.0.0
 last-updated: 2026-09-13
 skills:
@@ -15,42 +15,12 @@ scripts-binding:
 
 # Improve UI — Evidence-Based UI Audit & Implementation Planning
 
-## Mandatory Pre-Flight Context Inspection
-
-Before generating, refactoring, or reviewing code in the `improve-ui` 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 Audit an existing product surface against its own design evidence, identify verified UI problems, and write self-contained implementation plans for another agent. Strictly read-only on product source. Use when asked to review, refine, improve, or clean up an interface without replacing its identity.
-- **DO NOT activate when:** The task falls outside the `improve-ui` 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
 
 ---
 
-
 ---
 
 ## 1. Operating Rules & Boundaries
@@ -98,48 +68,3 @@ Write a self-contained plan specifying:
 | Rewriting entire components    | Targeted visual diff plan                     | Preserves business logic & state |
 | Guessing design tokens         | Citing verified `var(--...)` declarations     | Ensures token adherence          |
 | Speculative visual preferences | Reporting only verified WCAG/token violations | Prevents arbitrary churn         |
-
----
-
-## 🚨 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
-
-| 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 Verification & Guardrails
-
-**Active Reviewers:** `frontend-reviewer` · `type-safety` · `ui-ux-auditor` · `complexity-reviewer`
-**Slash Command:** `/review` or `/tribunal-full`
-
-### ✅ Pre-Flight Self-Audit Checklist
-
-```
-✅ 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 test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agents/skills/intelligent-routing/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: intelligent-routing
-description: Use when LLM Intent Processing and Gateway Routing mastery. Request classification hierarchies, function routing, confidence scoring, fallback cascades, zero-shot vs few-shot classification patterns, and identifying specialized skills for delegation. Use when parsing raw user input to determine the architectural path of execution.
+description: "Use when LLM Intent Processing and Gateway Routing mastery. Request classification hierarchies, function routing, confidence scoring, fallback cascades, zero-shot vs few-shot classification patterns, and identifying specialized skills for delegation. Use when parsing raw user input to determine the architectural path of execution."
 version: 5.0.0
 last-updated: 2026-09-13
 skills:
@@ -9,42 +9,12 @@ skills:
   - behavioral-modes
 tools: Read, Grep, Glob, Bash, Edit, Write
 scripts-binding:
-  - .agent/scripts/compile_router.py
   - .agent/scripts/verify_all.js
   - .agent/scripts/lint_runner.js
 ---
 
 # Intelligent Routing v4 — Self-Describing Skill Graph
 
-## Mandatory Pre-Flight Context Inspection
-
-Before generating, refactoring, or reviewing code in the `intelligent-routing` 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 LLM Intent Processing and Gateway Routing mastery. Request classification hierarchies, function routing, confidence scoring, fallback cascades, zero-shot vs few-shot classification patterns, and identifying specialized skills for delegation. Use when parsing raw user input to determine the architectural path of execution.
-- **DO NOT activate when:** The task falls outside the `intelligent-routing` 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
@@ -225,59 +195,4 @@ When keywords belong to multiple domains, use these explicit rules:
 
 ## 6. Regenerating the Index
 
-When new skills are added or existing frontmatter is modified, regenerate the index:
-
-```bash
-python .agent/scripts/compile_router.py
-```
-
-This is idempotent — running it multiple times produces the same output. The index should be regenerated after:
-
-- Adding a new skill
-- Modifying a skill's `routing:` frontmatter
-- Removing a skill
-
----
-
-## 🚨 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
-
-| 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 Verification & Guardrails
-
-**Active Reviewers:** `orchestrator` · `agent-organizer` · `logic-reviewer`
-**Slash Command:** `/review` or `/tribunal-full`
-
-### ✅ Pre-Flight Self-Audit Checklist
-
-```
-✅ 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 test suites, compiler success, or equivalent operational proof) that your output works as intended.
+When new skills are added or existing frontmatter is modified, the index regenerates automatically.

package/.agents/skills/knowledge-graph/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: knowledge-graph
-description: Use when Understands the architecture, risk blast radius, and dependencies of the codebase without token bloat. Now includes Context Snapshots for 27x token reduction.
+description: "Use when Understands the architecture, risk blast radius, and dependencies of the codebase without token bloat. Now includes Context Snapshots for 27x token reduction."
 version: 5.0.0
 last-updated: 2026-09-13
 skills:
@@ -17,42 +17,12 @@ scripts-binding:
 
 # /graph — Knowledge Graph Skill v3.0
 
-## Mandatory Pre-Flight Context Inspection
-
-Before generating, refactoring, or reviewing code in the `knowledge-graph` 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 Understands the architecture, risk blast radius, and dependencies of the codebase without token bloat. Now includes Context Snapshots for 27x token reduction.
-- **DO NOT activate when:** The task falls outside the `knowledge-graph` 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
 
 ---
 
-
 ## The Token Reduction Protocol (Option C)
 
 **DO NOT READ RAW SOURCE FILES IF A SNAPSHOT EXISTS.**
@@ -99,48 +69,3 @@ Reading raw project files wastes up to 50,000 tokens per edit. You must use the
 ## VBC Protocol (Verification-Before-Completion)
 
 You are explicitly forbidden from guessing or "hallucinating" what functions, props, or variables exist inside a file. You MUST read the Context Snapshot (or use `graph_zoom.js`) to verify a component's exact signature before you attempt to call it, mock it, or rewrite it. Always respect the Blast Radius Risk Score before deleting or mutating files.
-
----
-
-## 🚨 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
-
-| 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 Verification & Guardrails
-
-**Active Reviewers:** `orchestrator` · `agent-organizer` · `logic-reviewer`
-**Slash Command:** `/review` or `/tribunal-full`
-
-### ✅ Pre-Flight Self-Audit Checklist
-
-```
-✅ 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 test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agents/skills/landing-page/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: landing-page
-description: Use when High-converting landing page structure, hero section layout variance, CTA hierarchy, visual pacing, feature grid storytelling, and social proof placement.
+description: "Use when High-converting landing page structure, hero section layout variance, CTA hierarchy, visual pacing, feature grid storytelling, and social proof placement."
 version: 5.0.0
 last-updated: 2026-09-13
 skills:
@@ -16,42 +16,12 @@ scripts-binding:
 
 # Landing Page — Conversion Architecture & Visual Pacing
 
-## Mandatory Pre-Flight Context Inspection
-
-Before generating, refactoring, or reviewing code in the `landing-page` 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-converting landing page structure, hero section layout variance, CTA hierarchy, visual pacing, feature grid storytelling, and social proof placement.
-- **DO NOT activate when:** The task falls outside the `landing-page` 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
 
 ---
 
-
 ---
 
 ## The 6-Section Landing Page Blueprint
@@ -93,48 +63,3 @@ Avoid standard left-text / right-image templates on every project. Choose based
   - 60% Left column (Heading, bullets, CTA) + 40% Right column (Interactive phone frame or live code preview).
 - **Model C: Full-Bleed Canvas (Best for Creative & AI Tools)**
   - Full-screen canvas visual background with floating frosted-glass prompt bar and primary CTA.
-
----
-
-## 🚨 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
-
-| 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 Verification & Guardrails
-
-**Active Reviewers:** `frontend-reviewer` · `type-safety` · `ui-ux-auditor` · `complexity-reviewer`
-**Slash Command:** `/review` or `/tribunal-full`
-
-### ✅ Pre-Flight Self-Audit Checklist
-
-```
-✅ 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 test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agents/skills/lint-and-validate/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: lint-and-validate
-description: Use when Linting and validation principles for code quality enforcement.
+description: "Use when Linting and validation principles for code quality enforcement."
 version: 5.0.0
 last-updated: 2026-09-13
 skills:
@@ -15,42 +15,12 @@ scripts-binding:
 
 # Linting & Validation
 
-## Mandatory Pre-Flight Context Inspection
-
-Before generating, refactoring, or reviewing code in the `lint-and-validate` 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 Linting and validation principles for code quality enforcement.
-- **DO NOT activate when:** The task falls outside the `lint-and-validate` 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
 
 ---
 
-
 ## Hallucination Traps (Read First)
 
 - ❌ Auto-fixing lint errors without reviewing the diff -> ✅ Some auto-fixes change logic (e.g., removing 'unused' variables that are side-effects)
@@ -252,48 +222,3 @@ Evidence:    [test output / lint pass / compile success]
 
 **VBC (Verification-Before-Completion) is mandatory.**
 Do not mark status as VERIFIED until concrete terminal evidence is provided.
-
----
-
-## 🚨 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
-
-| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
-|:---|:---|:---|
-| **Hardcoded Secret Pattern** | Committing API keys, tokens, or private salts into source code | Load credentials strictly via runtime environment variables and secret stores |
-| **Prompt Injection Surface** | Directly concatenating untrusted user input into LLM system prompts | Wrap user content in isolated delimiters and strip injection control sequences |
-| **Missing Authorization Check** | Relying only on authentication token presence without checking tenant/object RBAC | Verify user permissions against the specific target record ID before mutation |
-
----
-
-## 🏛️ Tribunal Verification & Guardrails
-
-**Active Reviewers:** `security-auditor` · `penetration-tester` · `backend-security-expert`
-**Slash Command:** `/review` or `/tribunal-full`
-
-### ✅ Pre-Flight Self-Audit Checklist
-
-```
-✅ Are user inputs sanitized and treated as untrusted at system boundaries?
-✅ Are secrets loaded strictly via environment variables with zero hardcoding?
-✅ Is least-privilege enforcement active on APIs, tokens, and storage buckets?
-✅ Are prompt-injection delimiters and sanitizers wrapped around LLM inputs?
-✅ Did I verify encryption in transit and at rest for sensitive customer data?
-```
-
-### 🛑 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 test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agents/skills/llm-engineering/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: llm-engineering
-description: Use when LLM engineering mastery for production AI systems. Prompt engineering, RAG pipeline design, vector store selection, embedding strategies, chunking, reranking, structured output, function calling, streaming, evals, guard-rails, cost optimization, and LLMOps. Use when building AI features, chat interfaces, semantic search, or any system calling an LLM API.
+description: "Use when LLM engineering mastery for production AI systems. Prompt engineering, RAG pipeline design, vector store selection, embedding strategies, chunking, reranking, structured output, function calling, streaming, evals, guard-rails, cost optimization, and LLMOps. Use when building AI features, chat interfaces, semantic search, or any system calling an LLM API."
 version: 5.0.0
 last-updated: 2026-09-13
 skills:
@@ -15,42 +15,12 @@ scripts-binding:
 
 # LLM Engineering — Production AI Systems Mastery
 
-## Mandatory Pre-Flight Context Inspection
-
-Before generating, refactoring, or reviewing code in the `llm-engineering` 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 LLM engineering mastery for production AI systems. Prompt engineering, RAG pipeline design, vector store selection, embedding strategies, chunking, reranking, structured output, function calling, streaming, evals, guard-rails, cost optimization, and LLMOps. Use when building AI features, chat interfaces, semantic search, or any system calling an LLM API.
-- **DO NOT activate when:** The task falls outside the `llm-engineering` 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
 
 ---
 
-
 ---
 
 ## Model Selection
@@ -388,48 +358,3 @@ eventSource.onmessage = event => {
 // GPT-4o-mini: ~$0.15/1M input, ~$0.60/1M output
 // 1M tokens ≈ 750,000 words ≈ 3,000 pages
 ```
-
----
-
-## 🚨 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
-
-| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
-|:---|:---|:---|
-| **Unchecked Payload Cast** | Casting request bodies to TypeScript types without runtime schema validation | Parse request payloads through Zod/Pydantic schemas before business logic |
-| **Silent Error Swallowing** | Catching errors with empty catch blocks or logging without rethrowing | Propagate structured errors with status codes and contextual stack traces |
-| **Unparameterized Query** | Concatenating user inputs into SQL/Prisma query strings | Always use parameterized bindings or type-safe ORM query builders |
-
----
-
-## 🏛️ Tribunal Verification & Guardrails
-
-**Active Reviewers:** `logic-reviewer` · `security-auditor` · `api-architect` · `resilience-reviewer`
-**Slash Command:** `/review` or `/tribunal-full`
-
-### ✅ Pre-Flight Self-Audit Checklist
-
-```
-✅ Are all inputs and boundary payloads validated against schemas (Zod/Pydantic)?
-✅ Are SQL and database queries parameterized with zero string concatenation?
-✅ Are error boundaries and timeout/retry policies explicitly declared?
-✅ Are authentication checks performed before business logic execution?
-✅ Did I verify that imported dependencies exist in package.json/requirements.txt?
-```
-
-### 🛑 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 test suites, compiler success, or equivalent operational proof) that your output works as intended.