tribunal-kit 4.2.0 → 4.3.1

package/.agent/skills/playwright-best-practices/SKILL.md

@@ -139,7 +139,7 @@ export default defineConfig({
 
 ---
 
-## 🤖 LLM-Specific Traps
+
 
 AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
 
@@ -151,7 +151,7 @@ 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`**
@@ -162,7 +162,7 @@ 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:
 ```
@@ -176,4 +176,12 @@ 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/powershell-windows/SKILL.md

@@ -114,7 +114,7 @@ Get-ChildItem -Path "Cert:\LocalMachine\My" | Where-Object Subject -match "examp
 
 ---
 
-## 🤖 LLM-Specific Traps
+
 
 AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
 
@@ -126,7 +126,7 @@ 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`**
@@ -137,7 +137,7 @@ 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:
 ```
@@ -151,4 +151,12 @@ 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/project-idioms/SKILL.md

@@ -89,7 +89,7 @@ Run `python .agent/scripts/skill_evolution.py status` to see full statistics.
 
 ---
 
-## 🤖 LLM-Specific Traps
+
 
 AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
 
@@ -101,7 +101,7 @@ 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`**
@@ -112,7 +112,7 @@ 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:
 ```
@@ -126,4 +126,12 @@ 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/python-patterns/SKILL.md

@@ -211,7 +211,7 @@ 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:
 
@@ -223,7 +223,7 @@ 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`**
@@ -234,7 +234,7 @@ 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:
 ```
@@ -248,4 +248,12 @@ 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.