tribunal-kit 9.0.1 → 9.2.1

package/.agent/skills/advanced-rag-pipelines/SKILL.md

@@ -34,14 +34,14 @@ Before generating, refactoring, or reviewing code in the `advanced-rag-pipelines
 
 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       | 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. |
 
 ---
@@ -50,7 +50,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
 
 ---
 
-
 ## 2026 RAG Performance & Vector Invariants
 
 1. **Reciprocal Rank Fusion (RRF)**:
@@ -127,23 +126,23 @@ Before submitting code, ensure:
 
 ## 🚨 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 |
+| 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 |
+| 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         |
 
 ---
 
@@ -165,5 +164,6 @@ Before submitting code, ensure:
 ### 🛑 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/.agent/skills/agent-organizer/SKILL.md

@@ -35,14 +35,14 @@ Before generating, refactoring, or reviewing code in the `agent-organizer` domai
 
 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       | 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. |
 
 ---
@@ -51,7 +51,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
 
 ---
 
-
 ## Hallucination Traps (Read First)
 
 - ❌ Dispatching sub-agents without a context_summary -> ✅ Always send a trimmed context, never the full conversation
@@ -150,23 +149,23 @@ Automation without oversight is reckless. The Organizer manages when to pause an
 
 ## 🚨 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 |
+| 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 |
+| 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    |
 
 ---
 
@@ -188,5 +187,6 @@ Automation without oversight is reckless. The Organizer manages when to pause an
 ### 🛑 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/.agent/skills/agentic-patterns/SKILL.md

@@ -35,14 +35,14 @@ Before generating, refactoring, or reviewing code in the `agentic-patterns` doma
 
 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       | 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. |
 
 ---
@@ -51,7 +51,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
 
 ---
 
-
 ---
 
 ## The Agent Loop
@@ -314,23 +313,23 @@ Evidence:    [link to terminal output, test result, or file diff]
 
 ## 🚨 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 |
+| 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 |
+| 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    |
 
 ---
 
@@ -352,5 +351,6 @@ Evidence:    [link to terminal output, test result, or file diff]
 ### 🛑 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/.agent/skills/agentic-workflows-2026/SKILL.md

@@ -36,14 +36,14 @@ Before generating, refactoring, or reviewing code in the `agentic-workflows-2026
 
 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       | 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. |
 
 ---
@@ -115,23 +115,23 @@ export async function runAgentLoop(task: string, maxTurns = 10) {
 
 ## 🚨 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 |
+| 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 |
+| 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         |
 
 ---
 
@@ -153,5 +153,6 @@ export async function runAgentLoop(task: string, maxTurns = 10) {
 ### 🛑 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/.agent/skills/ai-app-hardening/SKILL.md

@@ -36,14 +36,14 @@ Before generating, refactoring, or reviewing code in the `ai-app-hardening` doma
 
 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       | 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. |
 
 ---
@@ -83,23 +83,23 @@ export function sanitizeRAGDocument(rawDocumentContent: string): string {
 
 ## 🚨 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 |
+| 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 |
+| 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  |
 
 ---
 
@@ -121,5 +121,6 @@ export function sanitizeRAGDocument(rawDocumentContent: string): string {
 ### 🛑 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/.agent/skills/ai-prompt-injection-defense/SKILL.md

@@ -34,14 +34,14 @@ Before generating, refactoring, or reviewing code in the `ai-prompt-injection-de
 
 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       | 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. |
 
 ---
@@ -50,7 +50,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
 
 ---
 
-
 ## 2026 AI Prompt Injection & Sandboxing Invariants
 
 1. **Dual-LLM Pattern (Privileged vs Untrusted)**:
@@ -195,23 +194,23 @@ Many injections occur because the LLM includes malicious data in its output, whi
 
 ## 🚨 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 |
+| 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 |
+| 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  |
 
 ---
 
@@ -233,5 +232,6 @@ Many injections occur because the LLM includes malicious data in its output, whi
 ### 🛑 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/.agent/skills/animation-on-scroll/SKILL.md

@@ -35,14 +35,14 @@ Before generating, refactoring, or reviewing code in the `animation-on-scroll` d
 
 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       | 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. |
 
 ---
@@ -53,25 +53,22 @@ Scroll motion connects physical gesture with dynamic interface reveals. Poorly e
 
 ---
 
-
 ---
 
-
 ---
 
-
 ---
 
 ## 🛠️ Technical Architecture & Reference Recipes
 
 ### 1. Engine Selection Matrix
 
-| Use Case | Recommended Engine | Rationale |
-|:---|:---|:---|
-| **Single-Element Entrance Wipe** | Pure CSS `animation-timeline: view()` | 0 KB JS overhead, executes on GPU compositor thread |
-| **Page-Top Progress Indicator** | Pure CSS `animation-timeline: scroll()` | Zero re-renders, zero layout shifts |
-| **Multi-Stage Pinned Scrollytelling** | GSAP `ScrollTrigger` | Pin spacer mechanics, scrubbing interpolation, timeline nesting |
-| **React Component State Scrubbing** | Framer Motion `useScroll` + `useTransform` | Declarative hook integration with React rendering lifecycle |
+| Use Case                              | Recommended Engine                         | Rationale                                                       |
+| :------------------------------------ | :----------------------------------------- | :-------------------------------------------------------------- |
+| **Single-Element Entrance Wipe**      | Pure CSS `animation-timeline: view()`      | 0 KB JS overhead, executes on GPU compositor thread             |
+| **Page-Top Progress Indicator**       | Pure CSS `animation-timeline: scroll()`    | Zero re-renders, zero layout shifts                             |
+| **Multi-Stage Pinned Scrollytelling** | GSAP `ScrollTrigger`                       | Pin spacer mechanics, scrubbing interpolation, timeline nesting |
+| **React Component State Scrubbing**   | Framer Motion `useScroll` + `useTransform` | Declarative hook integration with React rendering lifecycle     |
 
 ---
 
@@ -136,8 +133,12 @@ export function initScrollytelling(container: HTMLElement) {
 
   steps.forEach((step, index) => {
     if (index === 0) return;
-    tl.to(steps[index - 1], { opacity: 0, y: -30, duration: 0.4 })
-      .fromTo(step, { opacity: 0, y: 40 }, { opacity: 1, y: 0, duration: 0.6 }, '-=0.2');
+    tl.to(steps[index - 1], { opacity: 0, y: -30, duration: 0.4 }).fromTo(
+      step,
+      { opacity: 0, y: 40 },
+      { opacity: 1, y: 0, duration: 0.6 },
+      '-=0.2',
+    );
   });
 
   return () => {
@@ -181,7 +182,9 @@ export function ParallaxHeroCard() {
         className="sticky top-24 w-full max-w-2xl p-8 rounded-3xl bg-neutral-900 border border-neutral-800 shadow-2xl"
       >
         <h2 className="text-2xl font-semibold text-white">Fluid Reactive Scrubbing</h2>
-        <p className="mt-2 text-neutral-400">Zero unthrottled scroll listeners. Offloaded to motion GPU pipeline.</p>
+        <p className="mt-2 text-neutral-400">
+          Zero unthrottled scroll listeners. Offloaded to motion GPU pipeline.
+        </p>
       </motion.div>
     </div>
   );
@@ -225,23 +228,23 @@ export function ParallaxHeroCard() {
 
 ## 🚨 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 |
+| 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 |
-|:---|:---|:---|
-| **The Instant Pop Trap** | Conditionally unmounting elements without animated interpolation | Use AnimatePresence or coordinate morphs with continuous geometry |
-| **Layout Thrashing** | Animating width, height, top, or left inside animation loops | Animate composite-only transform (translate3d, scale) and opacity |
-| **Sluggish Duration** | Setting micro-interaction transitions to 600ms+ causing interface lag | Cap interactive feedback at 160ms–240ms with snappy ease-out curves |
+| Anti-Pattern             | What AI Commonly Does Wrong                                           | What Is Actually Correct                                            |
+| :----------------------- | :-------------------------------------------------------------------- | :------------------------------------------------------------------ |
+| **The Instant Pop Trap** | Conditionally unmounting elements without animated interpolation      | Use AnimatePresence or coordinate morphs with continuous geometry   |
+| **Layout Thrashing**     | Animating width, height, top, or left inside animation loops          | Animate composite-only transform (translate3d, scale) and opacity   |
+| **Sluggish Duration**    | Setting micro-interaction transitions to 600ms+ causing interface lag | Cap interactive feedback at 160ms–240ms with snappy ease-out curves |
 
 ---
 
@@ -263,5 +266,6 @@ export function ParallaxHeroCard() {
 ### 🛑 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.