tribunal-kit 7.0.0 → 9.0.0

package/.agent/skills/devops-engineer/SKILL.md

@@ -2,8 +2,8 @@
 name: devops-engineer
 description: DevOps engineering mastery. Docker containerization, Docker Compose, CI/CD with GitHub Actions, Kubernetes basics, infrastructure as code (Terraform), monitoring/alerting, deployment strategies (blue/green, canary, rolling), secrets management, and production readiness checklists. Use when building CI/CD pipelines, containerizing apps, or managing infrastructure.
 tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - cicd-pro
   - containerization-pro
@@ -25,7 +25,11 @@ Before building Dockerfiles, Docker Compose, or GitHub Actions pipelines, you MU
 2. Deterministic Package Installation (Section 28) → Use `npm ci` (or yarn/pnpm equivalent with lockfiles) in Docker and CI; ban `npm install`
 3. CI/CD Concurrency Group Cancellation (Section 142) → Configure `concurrency.cancel-in-progress: true` on PR workflows to cancel stale builds
 
-# DevOps Engineer — CI/CD & Infrastructure Mastery
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring DevOps engineering mastery. Docker containerization, Docker Compose, CI/CD with GitHub Actions, Kubernetes basics, infrastructure as code (Terraform), monitoring/alerting, deployment strategies (blue/green, canary, rolling), secrets management, and production readiness checklists. Use when building CI/CD pipelines, containerizing apps, or managing infrastructure..
+- **DO NOT activate when:** The task falls strictly outside devops-engineer domain or belongs to a different dedicated specialist.
 
 ---
 
@@ -324,69 +328,17 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
-
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-
-Review these questions before confirming output:
-
-```
-✅ Did I rely ONLY on real, verified tools and methods?
-✅ Is this solution appropriately scoped to the user's constraints?
-✅ Did I handle potential failure modes and edge cases?
-✅ Have I avoided generic boilerplate that doesn't add value?
-```
-
-### 🛑 Verification-Before-Completion (VBC) Protocol
-
-**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
-- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
-
-## Pre-Flight Checklist
-
-- [ ] Have I reviewed the user's specific constraints and requests?
-- [ ] Have I checked the environment for relevant existing implementations?
-
-## VBC Protocol (Verification-Before-Completion)
-
-You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
-
----
-
-## 🤖 LLM-Specific Traps
-
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
-
-1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
-2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
-3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
-4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
-
----
-
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+## 🏛️ Tribunal Verification & Guardrails
 
 **Slash command: `/review` or `/tribunal-full`**
 **Active reviewers: `logic-reviewer` · `security-auditor`**
 
 ### ❌ Forbidden AI Tropes
-
 1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
 2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
 3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
 
 ### ✅ Pre-Flight Self-Audit
-
-Review these questions before confirming output:
-
 ```
 ✅ Did I rely ONLY on real, verified tools and methods?
 ✅ Is this solution appropriately scoped to the user's constraints?
@@ -395,8 +347,6 @@ Review these questions before confirming output:
 ```
 
 ### 🛑 Verification-Before-Completion (VBC) Protocol
-
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
 - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.

package/.agent/skills/devops-incident-responder/SKILL.md

@@ -2,8 +2,8 @@
 name: devops-incident-responder
 description: Production incident response mastery. MTTR (Mean Time to Recovery) reduction, blameless post-mortems, rapid triaging, halting systemic cascading failures, isolating problematic deployments, and evidence-based forensic analysis. Use when stabilizing broken systems, fighting active production fires, or conducting root-cause post-mortems.
 tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - devops-engineer
   - error-resilience
@@ -25,6 +25,12 @@ Before responding to production outages or performing incident triage, you MUST
 2. Circuit Breaker Severance (Section 42) → Sever failing downstream dependencies immediately to prevent cascading overload across the system
 3. Triage Hierarchy (Section 73) → Analyze metrics (what) → traces (where) → logs (why) sequentially to pinpoint root causes
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Production incident response mastery. MTTR (Mean Time to Recovery) reduction, blameless post-mortems, rapid triaging, halting systemic cascading failures, isolating problematic deployments, and evidence-based forensic analysis. Use when stabilizing broken systems, fighting active production fires, or conducting root-cause post-mortems..
+- **DO NOT activate when:** The task falls strictly outside devops-incident-responder domain or belongs to a different dedicated specialist.
+
 ## Hallucination Traps (Read First)
 
 - ❌ Changing code during an active incident -> ✅ STABILIZE first (rollback, feature flag, traffic shift), investigate AFTER
@@ -33,8 +39,6 @@ Before responding to production outages or performing incident triage, you MUST
 
 ---
 
-# Incident Responder — Production Stabilization Mastery
-
 ---
 
 ## 1. The Prime Directive (Stop the Bleeding)
@@ -122,69 +126,17 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
-
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-
-Review these questions before confirming output:
-
-```
-✅ Did I rely ONLY on real, verified tools and methods?
-✅ Is this solution appropriately scoped to the user's constraints?
-✅ Did I handle potential failure modes and edge cases?
-✅ Have I avoided generic boilerplate that doesn't add value?
-```
-
-### 🛑 Verification-Before-Completion (VBC) Protocol
-
-**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
-- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
-
-## Pre-Flight Checklist
-
-- [ ] Have I reviewed the user's specific constraints and requests?
-- [ ] Have I checked the environment for relevant existing implementations?
-
-## VBC Protocol (Verification-Before-Completion)
-
-You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
-
----
-
-## 🤖 LLM-Specific Traps
-
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
-
-1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
-2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
-3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
-4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
-
----
-
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+## 🏛️ Tribunal Verification & Guardrails
 
 **Slash command: `/review` or `/tribunal-full`**
 **Active reviewers: `logic-reviewer` · `security-auditor`**
 
 ### ❌ Forbidden AI Tropes
-
 1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
 2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
 3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
 
 ### ✅ Pre-Flight Self-Audit
-
-Review these questions before confirming output:
-
 ```
 ✅ Did I rely ONLY on real, verified tools and methods?
 ✅ Is this solution appropriately scoped to the user's constraints?
@@ -193,8 +145,6 @@ Review these questions before confirming output:
 ```
 
 ### 🛑 Verification-Before-Completion (VBC) Protocol
-
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
 - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.

package/.agent/skills/diagnosing-bugs/SKILL.md

@@ -2,8 +2,8 @@
 name: diagnosing-bugs
 description: Systematic bug diagnosis methodology for hard bugs: Phase 1 (Build feedback loop), Phase 2 (Reproduce + minimise), Phase 3 (Hypothesise), Phase 4 (Instrument), Phase 5 (Fix + regression test), Phase 6 (Cleanup + post-mortem).
 tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - systematic-debugging
   - test-result-analyzer
@@ -25,12 +25,16 @@ Before attempting bug diagnostics or proposing code fixes, you MUST inspect:
 2. Falsifiable Hypotheses Formulation (Section 107) → Formulate 3–5 falsifiable hypotheses (`"If X is cause, then Y prediction"`) before testing any single theory
 3. Tagged Debug Logging & Cleanup (Section 123) → Tag debug log instrumentation (`[DEBUG-id]`) and sweep clean before finalizing regression fixes
 
-# Diagnosing Bugs — A Discipline for Hard Bugs
-
 A systematic discipline for hard bugs. Skip phases only when explicitly justified.
 
 When exploring the codebase, read `CONTEXT.md` (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Systematic bug diagnosis methodology for hard bugs: Phase 1 (Build feedback loop), Phase 2 (Reproduce + minimise), Phase 3 (Hypothesise), Phase 4 (Instrument), Phase 5 (Fix + regression test), Phase 6 (Cleanup + post-mortem)..
+- **DO NOT activate when:** The task falls strictly outside diagnosing-bugs domain or belongs to a different dedicated specialist.
+
 ---
 
 ## Protocol Overview
@@ -182,30 +186,25 @@ Ask: **What would have prevented this bug?** If the answer involves architectura
 
 ---
 
-## 🤖 LLM-Specific Traps
+## 🏛️ Tribunal Verification & Guardrails
 
-1. **Shotgun Debugging**: Making random edits across multiple files hoping the error disappears.
-2. **Reading Code to Build Theories Before Having a Red Loop**: Jumping straight to hypotheses without a red-capable command.
-3. **Symptom Swallowing**: Wrapping a throwing call in silent `try/catch` or returning empty fallbacks instead of addressing root cause.
-4. **Testing Multiple Hypotheses at Once**: Changing multiple variables simultaneously, creating ambiguous results.
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
 
----
-
-## 🏛️ Tribunal Integration & Pre-Flight Self-Audit
-
-**Active Reviewers: `debugger` · `logic-reviewer` · `resilience-reviewer`**
+### ❌ Forbidden AI Tropes
+1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
+2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
+3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
 
+### ✅ Pre-Flight Self-Audit
 ```
-✅ Has a red-capable feedback loop command been executed and verified red?
-✅ Has the repro scenario been minimised to only load-bearing elements?
-✅ Were 3–5 falsifiable hypotheses formulated before testing?
-✅ Are all debug logs tagged with [DEBUG-...] and cleaned up before merge?
-✅ Has a regression test been added at a valid seam?
+✅ Did I rely ONLY on real, verified tools and methods?
+✅ Is this solution appropriately scoped to the user's constraints?
+✅ Did I handle potential failure modes and edge cases?
+✅ Have I avoided generic boilerplate that doesn't add value?
 ```
 
 ### 🛑 Verification-Before-Completion (VBC) Protocol
-
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
 - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.

package/.agent/skills/distill/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: distill
 description: Simplify noisy interfaces by removing non-essential visual and operational complexity. Use when a UI has too many options, crowded toolbars, redundant text, or unnecessary visual containers.
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - quieter
   - clarify
@@ -27,6 +27,12 @@ Before decluttering UI layouts, you MUST inspect:
 
 Systematically strip away visual clutter, redundant controls, and cognitive friction to reveal the core user task.
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Simplify noisy interfaces by removing non-essential visual and operational complexity. Use when a UI has too many options, crowded toolbars, redundant text, or unnecessary visual containers..
+- **DO NOT activate when:** The task falls strictly outside distill domain or belongs to a different dedicated specialist.
+
 ---
 
 ## The 4 Distillation Steps
@@ -52,28 +58,25 @@ Systematically strip away visual clutter, redundant controls, and cognitive fric
 
 ---
 
-## 🤖 LLM-Specific Traps
+## 🏛️ Tribunal Verification & Guardrails
 
-1. **Hiding Essential Actions**: Removing actions that users need frequently, forcing extra clicks.
-2. **Deleting Error Context**: Removing helpful inline validation messages while trimming copy.
-
----
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
 
-## 🏛️ Tribunal Integration (Anti-Hallucination)
-
-**Active reviewers: `frontend-reviewer` · `ui-ux-auditor`**
+### ❌ Forbidden AI Tropes
+1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
+2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
+3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
 
 ### ✅ Pre-Flight Self-Audit
-
 ```
-✅ Is the primary task front and center without distraction?
-✅ Have secondary/tertiary options been cleanly collapsed or progressively disclosed?
-✅ Is all microcopy concise, active, and direct?
+✅ Did I rely ONLY on real, verified tools and methods?
+✅ Is this solution appropriately scoped to the user's constraints?
+✅ Did I handle potential failure modes and edge cases?
+✅ Have I avoided generic boilerplate that doesn't add value?
 ```
 
 ### 🛑 Verification-Before-Completion (VBC) Protocol
-
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
 - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.

package/.agent/skills/documentation-templates/SKILL.md

@@ -2,8 +2,8 @@
 name: documentation-templates
 description: Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.
 tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - readme-builder
   - geo-fundamentals
@@ -25,6 +25,12 @@ Before creating or editing documentation, API references, or comments, you MUST
 2. Explain "Why", Not "What" in Code Comments (Section 147) → Document non-obvious business rules or bug workarounds; ban restating obvious code syntax
 3. AI-Friendly Documentation Mapping (Section 171) → Maintain `ARCHITECTURE.md` and `@purpose:` annotations for codebase mental models and automated ingestion
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation..
+- **DO NOT activate when:** The task falls strictly outside documentation-templates domain or belongs to a different dedicated specialist.
+
 ## Hallucination Traps (Read First)
 
 - ❌ Writing documentation that only AI-generated code can understand -> ✅ Docs are for HUMANS; use clear language and real examples
@@ -33,8 +39,6 @@ Before creating or editing documentation, API references, or comments, you MUST
 
 ---
 
-# Documentation Standards
-
 ---
 
 ## Documentation Types and Their Audiences
@@ -270,69 +274,17 @@ AI coding assistants often fall into specific bad habits when dealing with this
 
 ---
 
-**Slash command: `/review` or `/tribunal-full`**
-**Active reviewers: `logic-reviewer` · `security-auditor`**
-
-### ❌ Forbidden AI Tropes
-
-1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
-2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
-3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-
-Review these questions before confirming output:
-
-```
-✅ Did I rely ONLY on real, verified tools and methods?
-✅ Is this solution appropriately scoped to the user's constraints?
-✅ Did I handle potential failure modes and edge cases?
-✅ Have I avoided generic boilerplate that doesn't add value?
-```
-
-### 🛑 Verification-Before-Completion (VBC) Protocol
-
-**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
-- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
-
-## Pre-Flight Checklist
-
-- [ ] Have I reviewed the user's specific constraints and requests?
-- [ ] Have I checked the environment for relevant existing implementations?
-
-## VBC Protocol (Verification-Before-Completion)
-
-You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
-
----
-
-## 🤖 LLM-Specific Traps
-
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
-
-1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
-2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
-3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
-4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
-5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
-
----
-
-## 🏛️ Tribunal Integration (Anti-Hallucination)
+## 🏛️ Tribunal Verification & Guardrails
 
 **Slash command: `/review` or `/tribunal-full`**
 **Active reviewers: `logic-reviewer` · `security-auditor`**
 
 ### ❌ Forbidden AI Tropes
-
 1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
 2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
 3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
 
 ### ✅ Pre-Flight Self-Audit
-
-Review these questions before confirming output:
-
 ```
 ✅ Did I rely ONLY on real, verified tools and methods?
 ✅ Is this solution appropriately scoped to the user's constraints?
@@ -341,8 +293,6 @@ Review these questions before confirming output:
 ```
 
 ### 🛑 Verification-Before-Completion (VBC) Protocol
-
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
 - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.

package/.agent/skills/domain-modeling/SKILL.md

@@ -2,8 +2,8 @@
 name: domain-modeling
 description: Builds and sharpens project domain models, ubiquitous language, entity relationships, and bounded contexts before writing code.
 tools: Read, Grep, Glob, Bash, Edit, Write
-version: 3.0.0
-last-updated: 2026-07-30
+version: 4.0.0
+last-updated: 2026-09-07
 skills:
   - architecture
   - codebase-design
@@ -25,10 +25,14 @@ Before designing domain entities or business modeling, you MUST inspect:
 2. Bounded Context Separation (Section 30) → Isolate models per context (e.g. Inventory Product vs Catalog Product); ban 60-column monolithic entities
 3. Aggregate Root Invariants (Section 34) → Mutate child entities strictly through Aggregate Root methods (`order.addItem(...)`); ban direct child mutations
 
-# Domain Modeling — Ubiquitous Language & Bounded Contexts
-
 Model business domain concepts cleanly before committing to database schemas or API signatures.
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Builds and sharpens project domain models, ubiquitous language, entity relationships, and bounded contexts before writing code..
+- **DO NOT activate when:** The task falls strictly outside domain-modeling domain or belongs to a different dedicated specialist.
+
 ---
 
 ## 4 Domain Modeling Rules
@@ -70,28 +74,25 @@ export class EmailAddress {
 
 ---
 
-## 🤖 LLM-Specific Traps
+## 🏛️ Tribunal Verification & Guardrails
 
-1. **Anemic Domain Models**: Creating plain data structures (`DTOs`) without domain methods, pushing business logic into scattered service files.
-2. **Mixing Contexts**: Creating 1 giant `User` table with 60 columns spanning auth, billing, shipping, and notification preferences.
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
 
----
-
-## 🏛️ Tribunal Integration (Anti-Hallucination)
-
-**Active reviewers: `logic-reviewer` · `type-safety`**
+### ❌ Forbidden AI Tropes
+1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
+2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
+3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
 
 ### ✅ Pre-Flight Self-Audit
-
 ```
-✅ Are entity names strictly consistent with the project's ubiquitous language?
-✅ Are domain invariants enforced inside Aggregate Roots?
-✅ Have complex primitives been converted into type-safe Value Objects?
+✅ Did I rely ONLY on real, verified tools and methods?
+✅ Is this solution appropriately scoped to the user's constraints?
+✅ Did I handle potential failure modes and edge cases?
+✅ Have I avoided generic boilerplate that doesn't add value?
 ```
 
 ### 🛑 Verification-Before-Completion (VBC) Protocol
-
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
-
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
 - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.

package/.agent/skills/duckdb-analytical-sql/SKILL.md

@@ -2,8 +2,8 @@
 name: duckdb-analytical-sql
 description: Embedded OLAP analytics, high-speed Parquet/JSON processing, in-memory analytical SQL, and DuckDB integrations in Node.js, Python, and WASM.
 tools: Read, Grep, Glob, Edit, Write
-version: 3.0.0
-last-updated: 2026-08-05
+version: 4.0.0
+last-updated: 2026-09-07
 script: .agent/scripts/schema_validator.js
 scripts-binding:
   - .agent/scripts/schema_validator.js
@@ -23,6 +23,12 @@ Before writing analytical queries:
 2. Memory Allocation → Set explicit memory limit (`SET max_memory = '4GB'`) to prevent OOM
 3. Vectorized Engine Usage → Use column-oriented aggregation over line-by-line loops
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring Embedded OLAP analytics, high-speed Parquet/JSON processing, in-memory analytical SQL, and DuckDB integrations in Node.js, Python, and WASM..
+- **DO NOT activate when:** The task falls strictly outside duckdb-analytical-sql domain or belongs to a different dedicated specialist.
+
 ## Node.js DuckDB Parquet Query Pattern
 
 ```typescript
@@ -53,7 +59,27 @@ export async function runAnalyticalReport(parquetGlobPath: string) {
 }
 ```
 
-## 🛑 Verification-Before-Completion (VBC) Protocol
+---
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
+
+### ❌ Forbidden AI Tropes
+1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
+2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
+3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
+
+### ✅ Pre-Flight Self-Audit
+```
+✅ 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?
+```
 
-- Verify query execution on sample Parquet dataset without loading entire file into RAM.
-- Benchmark query throughput against memory constraints.
+### 🛑 Verification-Before-Completion (VBC) Protocol
+**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
+- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.

package/.agent/skills/edge-ai-mobile/SKILL.md

@@ -2,8 +2,8 @@
 name: edge-ai-mobile
 description: On-device mobile AI, CoreML, Android NNAPI, ONNX Runtime Web/Mobile, local LLM execution (SLMs), and sub-10ms privacy-first edge inference.
 tools: Read, Grep, Glob, Edit, Write
-version: 3.0.0
-last-updated: 2026-08-05
+version: 4.0.0
+last-updated: 2026-09-07
 script: .agent/scripts/bundle_analyzer.js
 scripts-binding:
   - .agent/scripts/bundle_analyzer.js
@@ -23,6 +23,12 @@ Before deploying on-device AI models:
 2. Hardware Acceleration → Bind inference engine to Apple Neural Engine (ANE) or Android NPU
 3. Fallback Mechanism → Fall back gracefully to cloud LLM API if local inference exceeds latency budget (>200ms)
 
+
+## Activation Boundaries
+
+- **Activate when:** Operating in tasks requiring On-device mobile AI, CoreML, Android NNAPI, ONNX Runtime Web/Mobile, local LLM execution (SLMs), and sub-10ms privacy-first edge inference..
+- **DO NOT activate when:** The task falls strictly outside edge-ai-mobile domain or belongs to a different dedicated specialist.
+
 ## Mobile ONNX Edge Inference Pattern
 
 ```typescript
@@ -44,7 +50,27 @@ export async function runLocalEmbeddings(textTokens: number[]): Promise<Float32A
 }
 ```
 
-## 🛑 Verification-Before-Completion (VBC) Protocol
+---
+
+## 🏛️ Tribunal Verification & Guardrails
+
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
+
+### ❌ Forbidden AI Tropes
+1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
+2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
+3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
+
+### ✅ Pre-Flight Self-Audit
+```
+✅ 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?
+```
 
-- Verify local memory usage remains under 300MB during active model inference.
-- Measure battery consumption impact.
+### 🛑 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.