tribunal-kit 4.2.0 → 4.3.1

package/.agent/skills/gsap-timeline/SKILL.md

@@ -105,51 +105,57 @@ master.to(".c", { opacity: 0 }, "+=0.2");
 - ❌ Forget to pass **defaults** (e.g. `defaults: { duration: 0.5, ease: "power2.out" }`) when many child tweens share the same duration or ease.
 - ❌ Forget that **duration** on the timeline constructor is not the same as tween duration; timeline “duration” is determined by its children.
 - ❌ Nest animations that contain a ScrollTrigger; ScrollTriggers should only be on top-level Tweens/Timelines.
-
----
-
-## 🏛️ Tribunal Integration (Anti-Hallucination)
-
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
-
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-
----
-
-## 🚨 LLM Trap Table
-
-|Pattern|What AI Does Wrong|What Is Actually Correct|
-|:---|:---|:---|
-|gsap-timeline|Position parameter as 2nd arg|Position parameter is the 3rd arg: tl.to(el, {x: 100}, "<")|
-|gsap-timeline|tl.add(gsap.to(...))|tl.to(...) (just chain the tween directly)|
-|gsap-timeline|Hardcoded delays (delay: 1)|Use position parameter (<, >, +=1) for relative timing|
-
----
-
-## ✅ Pre-Flight Self-Audit
-
-Before producing any output, verify:
-```
-✅ Did I read the actual files before making claims about them?
-✅ Did I verify all method names against official GSAP documentation?
-✅ Did I add // VERIFY: on any uncertain API calls?
-✅ Are all imports from packages that actually exist in package.json?
-✅ Did I test my logic with edge cases (null, empty, 0, max)?
-✅ Did I avoid generating code for more than one module at a time?
-✅ Am I working from evidence, not assumption?
-```
-
----
-
-## 🔁 VBC Protocol (Verify → Build → Confirm)
-
-```
-VERIFY:  Read the actual codebase before writing anything
-BUILD:   Generate the smallest meaningful unit of code
-CONFIRM: Verify the output is correct before presenting
-```
+
+---
+
+**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 Trap Table
+
+|Pattern|What AI Does Wrong|What Is Actually Correct|
+|:---|:---|:---|
+|gsap-timeline|Position parameter as 2nd arg|Position parameter is the 3rd arg: tl.to(el, {x: 100}, "<")|
+|gsap-timeline|tl.add(gsap.to(...))|tl.to(...) (just chain the tween directly)|
+|gsap-timeline|Hardcoded delays (delay: 1)|Use position parameter (<, >, +=1) for relative timing|
+
+---
+
+## ✅ Pre-Flight Self-Audit
+
+Before producing any output, verify:
+```
+✅ Did I read the actual files before making claims about them?
+✅ Did I verify all method names against official GSAP documentation?
+✅ Did I add // VERIFY: on any uncertain API calls?
+✅ Are all imports from packages that actually exist in package.json?
+✅ Did I test my logic with edge cases (null, empty, 0, max)?
+✅ Did I avoid generating code for more than one module at a time?
+✅ Am I working from evidence, not assumption?
+```
+
+---
+
+## 🔁 VBC Protocol (Verify → Build → Confirm)
+
+```
+VERIFY:  Read the actual codebase before writing anything
+BUILD:   Generate the smallest meaningful unit of code
+CONFIRM: Verify the output is correct before presenting
+```
+
+
+## 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.

package/.agent/skills/gsap-utils/SKILL.md

@@ -282,51 +282,57 @@ wrapY(150); // 50
 ### Learn More
 
 https://gsap.com/docs/v3/HelperFunctions
-
----
-
-## 🏛️ Tribunal Integration (Anti-Hallucination)
-
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
-
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-
----
-
-## 🚨 LLM Trap Table
-
-|Pattern|What AI Does Wrong|What Is Actually Correct|
-|:---|:---|:---|
-|gsap-utils|Using mapRange on units like "100px"|mapRange works only on pure numbers. Use getUnit/unitize|
-|gsap-utils|Re-creating random per frame|Pass true as 4th param: random(-10, 10, 1, true) for a reusable fn|
-|gsap-utils|Scoping global .box|Use gsap.utils.selector(container) inside components|
-
----
-
-## ✅ Pre-Flight Self-Audit
-
-Before producing any output, verify:
-```
-✅ Did I read the actual files before making claims about them?
-✅ Did I verify all method names against official GSAP documentation?
-✅ Did I add // VERIFY: on any uncertain API calls?
-✅ Are all imports from packages that actually exist in package.json?
-✅ Did I test my logic with edge cases (null, empty, 0, max)?
-✅ Did I avoid generating code for more than one module at a time?
-✅ Am I working from evidence, not assumption?
-```
-
----
-
-## 🔁 VBC Protocol (Verify → Build → Confirm)
-
-```
-VERIFY:  Read the actual codebase before writing anything
-BUILD:   Generate the smallest meaningful unit of code
-CONFIRM: Verify the output is correct before presenting
-```
+
+---
+
+**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 Trap Table
+
+|Pattern|What AI Does Wrong|What Is Actually Correct|
+|:---|:---|:---|
+|gsap-utils|Using mapRange on units like "100px"|mapRange works only on pure numbers. Use getUnit/unitize|
+|gsap-utils|Re-creating random per frame|Pass true as 4th param: random(-10, 10, 1, true) for a reusable fn|
+|gsap-utils|Scoping global .box|Use gsap.utils.selector(container) inside components|
+
+---
+
+## ✅ Pre-Flight Self-Audit
+
+Before producing any output, verify:
+```
+✅ Did I read the actual files before making claims about them?
+✅ Did I verify all method names against official GSAP documentation?
+✅ Did I add // VERIFY: on any uncertain API calls?
+✅ Are all imports from packages that actually exist in package.json?
+✅ Did I test my logic with edge cases (null, empty, 0, max)?
+✅ Did I avoid generating code for more than one module at a time?
+✅ Am I working from evidence, not assumption?
+```
+
+---
+
+## 🔁 VBC Protocol (Verify → Build → Confirm)
+
+```
+VERIFY:  Read the actual codebase before writing anything
+BUILD:   Generate the smallest meaningful unit of code
+CONFIRM: Verify the output is correct before presenting
+```
+
+
+## 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.

package/.agent/skills/i18n-localization/SKILL.md

@@ -115,7 +115,7 @@ In Next.js Middleware:
 
 ---
 
-## 🤖 LLM-Specific Traps
+
 
 AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
 
@@ -127,7 +127,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+
 
 **Slash command: `/review` or `/tribunal-full`**
 **Active reviewers: `logic-reviewer` · `security-auditor`**
@@ -138,7 +138,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 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:
 ```
@@ -152,4 +152,12 @@ Review these questions before confirming output:
 
 **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 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.

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

@@ -164,41 +164,41 @@ This file contains all available skills and workflows as a condensed index for t
 |`web-design-guidelines`|Review UI code for Next-Generation Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".|
 |`webapp-testing`|Web application testing principles. E2E, Playwright, deep audit strategies.|
 |`whimsy-injector`|Micro-delight generator for frontend interfaces. Suggests and implements subtle animations, playful transitions, and interaction polish across any frontend stack.|
-|`workflow-optimizer`|Analyzes agent tool-calling patterns and task execution efficiency to suggest process improvements.|
-|`api-architect`|API contract design agent. Builds robust REST/GraphQL/tRPC endpoints with RFC 9457 error formats, idempotency, pagination, and versioning. Use when designing new API routes or reviewing API contracts.|
-|`resilience-reviewer`|Fault tolerance reviewer. Audits for swallowed errors, naked Promises, missing retries/timeouts, absent circuit breakers, and missing React error boundaries. Use when reviewing backend or full-stack code for reliability.|
-|`schema-reviewer`|Input validation reviewer. Enforces strict Zod/Pydantic validation at all trust boundaries (API, env, query params). Catches `z.any()`, missing `.parse()`, and unvalidated external data. Use when reviewing data ingestion or API input handling.|
-|`gsap-core`|GSAP core animation API — gsap.to(), from(), fromTo(), easing, stagger, defaults, matchMedia(). Use for JavaScript animation with GSAP.|
-|`gsap-scrolltrigger`|GSAP ScrollTrigger plugin — scroll-driven animations, pinning, snapping. Use when building scroll-linked animation.|
-|`gsap-timeline`|GSAP timeline sequencing — Timeline API, position parameters, labels, nesting. Use for multi-step animation choreography.|
-|`gsap-react`|GSAP in React — useGSAP hook, ref-based targeting, cleanup, context scoping. Use when animating React components with GSAP.|
-|`gsap-plugins`|GSAP plugins — Flip, Draggable, MorphSVG, SplitText, MotionPath, DrawSVG. Use for advanced GSAP effects.|
-|`gsap-performance`|GSAP performance — will-change, GPU compositing, lazy MediaQuery, reduced motion. Use when optimizing GSAP animations.|
-|`gsap-utils`|GSAP utility methods — toArray, clamp, mapRange, interpolate, distribute. Use for GSAP helper functions.|
-|`gsap-frameworks`|GSAP framework integration — Vue, Svelte, Astro, Angular, Webflow. Use when integrating GSAP outside React.|
-|`error-resilience`|Error resilience patterns. Retry strategies, circuit breakers, graceful degradation, timeout policies.|
-|`data-validation-schemas`|Data validation with Zod, Pydantic, and JSON Schema. Use when building validation layers.|
-|`monorepo-management`|Monorepo tooling and workspace management. Turborepo, Nx, pnpm workspaces.|
-|`typescript-advanced`|Advanced TypeScript patterns. Generics, conditional types, template literals, discriminated unions.|
-|`game-developer`|Game development orchestrator. Routes to platform-specific skills (Unity/C#, Godot/GDScript, WebGL). Use when building games or game engines.|
-|`documentation-writer`|Technical documentation specialist. README files, API docs, code comments, architecture docs, and AI-friendly documentation. Use when writing or reviewing documentation.|
-|`test-engineer`|Test generation and strategy specialist. Creates tests using the Testing Trophy (unit → integration → E2E). Use when generating tests or designing test architecture.|
-|`qa-automation-engineer`|QA automation specialist. End-to-end testing pipelines, Playwright/Cypress configuration, CI test integration, visual regression. Use when building automated QA systems.|
-|`code-archaeologist`|Legacy code exploration specialist. Navigates unfamiliar codebases, identifies patterns, maps dependencies, documents tribal knowledge. Use when exploring or understanding legacy code.|
-|`project-planner`|Project planning specialist. 4-phase methodology (Analyze → Plan → Solution → Implement). Use when planning features, roadmaps, or multi-step implementations.|
-|`product-manager`|Product strategy specialist. Feature prioritization, roadmap planning, stakeholder alignment, competitive analysis. Use when making product decisions or prioritizing features.|
-|`product-owner`|User story and backlog management specialist. Writing acceptance criteria, sprint planning, backlog grooming. Use when defining user stories or managing backlogs.|
-|`seo-specialist`|SEO optimization specialist. Technical SEO, meta tags, structured data (JSON-LD), Core Web Vitals impact on search ranking, sitemap/robots configuration. Use when optimizing search visibility.|
-|`throughput-optimizer`|Throughput and latency optimization specialist. Load testing, connection pooling, queue management, batch processing, caching strategies. Use when optimizing system throughput or reducing latency.|
-|`vitals-reviewer`|Core Web Vitals specialist. LCP, CLS, INP measurement and optimization, Lighthouse auditing, real user monitoring. Use when auditing or improving web performance metrics.|
-|`penetration-tester`|Penetration testing and red team specialist. MITRE ATT&CK mapping, attack surface analysis, exploitation paths, vulnerability chaining. Use when pen testing applications or assessing attack surfaces.|
-|`db-latency-auditor`|Database performance specialist. Slow query analysis, EXPLAIN ANALYZE, index optimization, N+1 detection, connection pool tuning. Use when debugging database performance issues.|
+|`workflow-optimizer`|Analyzes agent tool-calling patterns and task execution efficiency to suggest process improvements.|
+|`api-architect`|API contract design agent. Builds robust REST/GraphQL/tRPC endpoints with RFC 9457 error formats, idempotency, pagination, and versioning. Use when designing new API routes or reviewing API contracts.|
+|`resilience-reviewer`|Fault tolerance reviewer. Audits for swallowed errors, naked Promises, missing retries/timeouts, absent circuit breakers, and missing React error boundaries. Use when reviewing backend or full-stack code for reliability.|
+|`schema-reviewer`|Input validation reviewer. Enforces strict Zod/Pydantic validation at all trust boundaries (API, env, query params). Catches `z.any()`, missing `.parse()`, and unvalidated external data. Use when reviewing data ingestion or API input handling.|
+|`gsap-core`|GSAP core animation API — gsap.to(), from(), fromTo(), easing, stagger, defaults, matchMedia(). Use for JavaScript animation with GSAP.|
+|`gsap-scrolltrigger`|GSAP ScrollTrigger plugin — scroll-driven animations, pinning, snapping. Use when building scroll-linked animation.|
+|`gsap-timeline`|GSAP timeline sequencing — Timeline API, position parameters, labels, nesting. Use for multi-step animation choreography.|
+|`gsap-react`|GSAP in React — useGSAP hook, ref-based targeting, cleanup, context scoping. Use when animating React components with GSAP.|
+|`gsap-plugins`|GSAP plugins — Flip, Draggable, MorphSVG, SplitText, MotionPath, DrawSVG. Use for advanced GSAP effects.|
+|`gsap-performance`|GSAP performance — will-change, GPU compositing, lazy MediaQuery, reduced motion. Use when optimizing GSAP animations.|
+|`gsap-utils`|GSAP utility methods — toArray, clamp, mapRange, interpolate, distribute. Use for GSAP helper functions.|
+|`gsap-frameworks`|GSAP framework integration — Vue, Svelte, Astro, Angular, Webflow. Use when integrating GSAP outside React.|
+|`error-resilience`|Error resilience patterns. Retry strategies, circuit breakers, graceful degradation, timeout policies.|
+|`data-validation-schemas`|Data validation with Zod, Pydantic, and JSON Schema. Use when building validation layers.|
+|`monorepo-management`|Monorepo tooling and workspace management. Turborepo, Nx, pnpm workspaces.|
+|`typescript-advanced`|Advanced TypeScript patterns. Generics, conditional types, template literals, discriminated unions.|
+|`game-developer`|Game development orchestrator. Routes to platform-specific skills (Unity/C#, Godot/GDScript, WebGL). Use when building games or game engines.|
+|`documentation-writer`|Technical documentation specialist. README files, API docs, code comments, architecture docs, and AI-friendly documentation. Use when writing or reviewing documentation.|
+|`test-engineer`|Test generation and strategy specialist. Creates tests using the Testing Trophy (unit → integration → E2E). Use when generating tests or designing test architecture.|
+|`qa-automation-engineer`|QA automation specialist. End-to-end testing pipelines, Playwright/Cypress configuration, CI test integration, visual regression. Use when building automated QA systems.|
+|`code-archaeologist`|Legacy code exploration specialist. Navigates unfamiliar codebases, identifies patterns, maps dependencies, documents tribal knowledge. Use when exploring or understanding legacy code.|
+|`project-planner`|Project planning specialist. 4-phase methodology (Analyze → Plan → Solution → Implement). Use when planning features, roadmaps, or multi-step implementations.|
+|`product-manager`|Product strategy specialist. Feature prioritization, roadmap planning, stakeholder alignment, competitive analysis. Use when making product decisions or prioritizing features.|
+|`product-owner`|User story and backlog management specialist. Writing acceptance criteria, sprint planning, backlog grooming. Use when defining user stories or managing backlogs.|
+|`seo-specialist`|SEO optimization specialist. Technical SEO, meta tags, structured data (JSON-LD), Core Web Vitals impact on search ranking, sitemap/robots configuration. Use when optimizing search visibility.|
+|`throughput-optimizer`|Throughput and latency optimization specialist. Load testing, connection pooling, queue management, batch processing, caching strategies. Use when optimizing system throughput or reducing latency.|
+|`vitals-reviewer`|Core Web Vitals specialist. LCP, CLS, INP measurement and optimization, Lighthouse auditing, real user monitoring. Use when auditing or improving web performance metrics.|
+|`penetration-tester`|Penetration testing and red team specialist. MITRE ATT&CK mapping, attack surface analysis, exploitation paths, vulnerability chaining. Use when pen testing applications or assessing attack surfaces.|
+|`db-latency-auditor`|Database performance specialist. Slow query analysis, EXPLAIN ANALYZE, index optimization, N+1 detection, connection pool tuning. Use when debugging database performance issues.|
 |`ai-code-reviewer`|AI/LLM integration code reviewer. Hallucinated model names, invented API parameters, prompt injection vulnerabilities, missing rate limits, streaming error handling. Use when reviewing code that calls LLM APIs.|
 
 
 ---
 
-## 🤖 LLM-Specific Traps
+
 
 AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
 
@@ -210,7 +210,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+
 
 **Slash command: `/review` or `/tribunal-full`**
 **Active reviewers: `logic-reviewer` · `security-auditor`**
@@ -221,7 +221,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 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:
 ```
@@ -235,4 +235,12 @@ Review these questions before confirming output:
 
 **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 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.

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

@@ -0,0 +1,36 @@
+---
+name: Knowledge Graph Analyzer
+description: Understands the architecture and dependencies of the codebase without token bloat.
+version: 1.0.0
+---
+
+# /graph — Knowledge Graph Skill
+
+Use this skill when the user types `/graph` or when you need to deeply understand the architecture of an unfamiliar codebase without suffering from context-window bloat.
+
+## Pre-Flight Checklist
+Before answering architectural questions or making broad code changes, you must understand the environment.
+- [ ] Have I run the Macro Mapper to get the high-level architecture?
+- [ ] Have I used the Micro Zoomer on the specific files related to the user's request to see their exact signatures?
+
+## Execution Protocol
+
+1. **Step 1: The Macro Map (World View)**
+   Execute the graph builder to map module boundaries. This runs incrementally and respects `.gitignore`.
+   ```bash
+   node .agent/scripts/graph_builder.js
+   ```
+   Read the output file at `.agent/history/architecture-graph.yaml`. **Do NOT try to read every file in the project.** Use this map to identify which files export the functions or components you need.
+
+2. **Step 2: The Micro Zoom (Street View)**
+   Once you know which file to investigate, use the zoomer to get its structural skeleton. This strips out the internal logic and returns only imports, exports, class signatures, and function parameters.
+   ```bash
+   node .agent/scripts/graph_zoom.js --focus <path_to_file>
+   ```
+   *Example: `node .agent/scripts/graph_zoom.js --focus src/components/Button.tsx`*
+
+3. **Step 3: Analyze and Advise**
+   Present the user with your findings. Highlight hidden dependencies, circular imports, or structural insights based on what you discovered in the graphs.
+
+## VBC Protocol (Verification-Before-Completion)
+You are explicitly forbidden from guessing or "hallucinating" what functions, props, or variables exist inside a file. You MUST use the `graph_zoom.js` script to verify a component's exact signature before you attempt to call it, mock it, or rewrite it.

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

@@ -213,7 +213,7 @@ Do not mark status as VERIFIED until concrete terminal evidence is provided.
 
 ---
 
-## 🤖 LLM-Specific Traps
+
 
 AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
 
@@ -225,7 +225,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+
 
 **Slash command: `/review` or `/tribunal-full`**
 **Active reviewers: `logic-reviewer` · `security-auditor`**
@@ -236,7 +236,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 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:
 ```
@@ -250,4 +250,12 @@ Review these questions before confirming output:
 
 **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 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.

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

@@ -346,7 +346,7 @@ eventSource.onmessage = (event) => {
 
 ---
 
-## 🤖 LLM-Specific Traps
+
 
 AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
 
@@ -358,7 +358,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+
 
 **Slash command: `/review` or `/tribunal-full`**
 **Active reviewers: `logic-reviewer` · `security-auditor`**
@@ -369,7 +369,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 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:
 ```
@@ -383,4 +383,12 @@ Review these questions before confirming output:
 
 **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 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.

package/.agent/skills/local-first/SKILL.md

@@ -130,7 +130,7 @@ const friends = useLiveQuery(() => db.friends.where('age').above(21).toArray());
 
 ---
 
-## 🤖 LLM-Specific Traps
+
 
 AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
 
@@ -142,7 +142,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+
 
 **Slash command: `/review` or `/tribunal-full`**
 **Active reviewers: `logic-reviewer` · `security-auditor`**
@@ -153,7 +153,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 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:
 ```
@@ -167,4 +167,12 @@ Review these questions before confirming output:
 
 **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 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.

package/.agent/skills/mcp-builder/SKILL.md

@@ -94,7 +94,7 @@ An MCP Server gives an external AI execution capability over your shell or datab
 
 ---
 
-## 🤖 LLM-Specific Traps
+
 
 AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
 
@@ -106,7 +106,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+
 
 **Slash command: `/review` or `/tribunal-full`**
 **Active reviewers: `logic-reviewer` · `security-auditor`**
@@ -117,7 +117,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
 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:
 ```
@@ -131,4 +131,12 @@ Review these questions before confirming output:
 
 **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 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.