ai-developer-skill-os 3.0.0 → 3.1.1

package/skills/qk-engineering-standard/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-engineering-standard
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Enforce SOLID, DRY, Clean Code, and Naming conventions.
 category: standard
+behavior: static-analysis
+intent: review-code
 priority: critical
 tags: [clean-code, architecture, refactoring, solid]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, review, implement, validate, complete]
 > **Goal:** Đóng vai trò là "Kiến trúc sư trưởng", rà soát và ép buộc mã nguồn phải tuân thủ chuẩn mực Clean Code, dễ đọc và dễ bảo trì.
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Context Review):**
    - Scan the target file(s) and determine their role (UI, Logic, API, Config).
 2. **Review (Smell Detection):**
@@ -32,12 +35,14 @@ pipeline: [analyze, review, implement, validate, complete]
 4. **Verify (Validation):**
    - Ensure the refactoring did NOT change the business logic or behavior of the app (Regression check).
 
-## 🛡️ 2. Constraints & Rules
+## 🛡️ 3. Constraints & Rules
+
 - **Code is for Humans:** Write code that junior developers can easily understand. Avoid overly clever or obscure syntax.
 - **Scope Limit:** Do NOT refactor the entire project if the user only asked to review one file. Limit the scope to the current task context.
 - **Preserve Behavior:** Refactoring must strictly preserve backward compatibility.
 
 ## 🌳 3. Decision Tree
+
 ```text
 Is the file larger than 300 lines?
   ├── YES → Propose splitting the file into sub-components or moving logic to hooks.
@@ -49,11 +54,14 @@ Does the React Component contain `fetch()` or heavy data mapping?
 ```
 
 ## 🤝 4. Handoff Pipeline
+
 1. `validate`: Run static analysis (Linters, TypeScript compiler) to ensure the refactored code has no syntax errors.
 2. `complete`: Generate the review report.
 
 ## 📝 5. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt. Cấu trúc báo cáo bao gồm:
+
 - **Tóm tắt (Summary):** File nào vừa được Refactor / Review.
 - **Chi tiết (Changes):** Các thay đổi cụ thể về Tên biến, Cấu trúc.
 - **Nguyên nhân (Reasoning):** Giải thích tại sao code cũ là "Bad Practice" và code mới tốt hơn thế nào.

package/skills/qk-feature-delivery/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-feature-delivery
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Develop new features end-to-end (Frontend & Backend).
 category: engineering
+behavior: development
+intent: implement-feature
 priority: high
 tags: [feature, development, e2e, ui, api]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, implement, engineering-standard, validate, complete]
 > **Goal:** Phát triển một tính năng mới hoàn chỉnh, từ giao diện (Frontend) đến API (Backend) và Cơ sở dữ liệu (nếu có).
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Requirements Gathering):**
    - Read the user's requirements.
    - Break down the feature into sub-tasks (e.g., Schema -> API -> UI Component -> Integration).
@@ -32,12 +35,14 @@ pipeline: [analyze, implement, engineering-standard, validate, complete]
    - Check if the UI is responsive.
    - Ensure the API handles edge cases (empty states, loading, error).
 
-## 🛡️ 2. Constraints & Rules
+## 🛡️ 3. Constraints & Rules
+
 - **Contract First:** Always define the Type/Interface contract before writing the implementation logic.
 - **Component Reusability:** Do not create a new Button or Input if a Shared Component already exists in `src/components/shared/`.
 - **DRY (Don't Repeat Yourself):** Extract inline styles or duplicate logic into hooks/utilities.
 
 ## 🌳 3. Decision Tree
+
 ```text
 Does the feature require Backend API changes?
   ├── YES → Start with Database Schema/Types -> API Route -> UI Integration.
@@ -47,14 +52,19 @@ Does the feature require Backend API changes?
 ```
 
 ## 🤝 4. Handoff Pipeline
+
 After implementing the feature, map to the pipeline:
+
 1. `engineering-standard`: Ensure naming conventions and file size limits are respected.
 2. `validate`: Run tests and format the code.
 3. `complete`: Output the final report.
 
 ## 📝 5. Output Format
+
 Vui lòng báo cáo lại bằng Tiếng Việt với cấu trúc tương tự `templates/bug-report.md` nhưng thay đổi tiêu đề thành:
+
 ### 🚀 Báo Cáo Triển Khai Tính Năng (Feature Report)
+
 - **Tóm tắt (Summary):** Tính năng gì đã được làm.
 - **Chi tiết (Changes):** Liệt kê các file tạo mới / chỉnh sửa.
 - **Kiến trúc (Reasoning):** Giải thích quyết định thiết kế State/API.

package/skills/qk-help/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-help
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Display the list of available skills and pro-tips.
 category: utilities
+behavior: static-analysis
+intent: review-code
 priority: low
 tags: [help, manual, list, tutorial]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,19 +21,24 @@ pipeline: [analyze, complete]
 > **Goal:** Bản đồ hướng dẫn sử dụng Agent Skills. Giúp User tra cứu nhanh lệnh.
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Scan):**
    - Read the skills directory to list all available tools.
 2. **Complete (Format):**
    - Format the skills into a neat Markdown table.
 
 ## 🛡️ 2. Constraints & Rules
+
 - **Keep it short:** Do not print the entire content of `SKILL.md`. Only print the Name and Description from the metadata.
 
 ## 🤝 3. Handoff Pipeline
+
 1. `complete`: Output the Help table.
 
 ## 📝 4. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt dạng Bảng (Table).
+
 - **Cột 1:** Tên Skill
 - **Cột 2:** Mô tả ngắn (Tiếng Việt)
 - **Cột 3:** Lệnh kích hoạt (Ví dụ: `@qk-bug-resolution`)

package/skills/qk-orchestrator/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-orchestrator
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Route user requests, parse intents, and delegate to the correct sub-skills.
 category: orchestration
+behavior: static-analysis
+intent: review-code
 priority: critical
 tags: [router, orchestrator, delegation, ai-manager]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, plan, delegate]
 > **Goal:** "Tổng tư lệnh" (Master Orchestrator). Phân tích ý đồ của người dùng và điều phối các kỹ năng (Skills) khác để giải quyết vấn đề thay vì làm mọi thứ một cách thủ công.
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Intent Parsing):**
    - Read the user's request. Determine the goal: Is it a Bug Fix, a New Feature, a Refactor, or just a Question?
 2. **Plan (Context Gathering & Skill Selection):**
@@ -28,10 +31,12 @@ pipeline: [analyze, plan, delegate]
    - Handoff the gathered context to the selected Skill.
 
 ## 🛡️ 2. Constraints & Rules
+
 - **Delegation First:** Do not write source code directly while acting as the Orchestrator. Delegate to the correct specialized Skill.
 - **Ambiguity Check:** If the user's intent is unclear, give them 2-3 Skill suggestions to choose from.
 
 ## 🌳 3. Decision Tree
+
 ```text
 Is the task a massive project (e.g., "Build an Admin Dashboard")?
   ├── YES → Break it down:
@@ -43,10 +48,13 @@ Is the task a massive project (e.g., "Build an Admin Dashboard")?
 ```
 
 ## 🤝 4. Handoff Pipeline
+
 1. `delegate`: Call the target Skill.
 
 ## 📝 5. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt.
+
 - **Tóm tắt (Summary):** Đã phân tích xong yêu cầu của User.
 - **Quyết định điều phối (Reasoning):** Giao việc cho Skill nào.
 - **Hành động tiếp (Next Action):** Tự động chuyển vai trò sang Skill được chọn.

package/skills/qk-policy-engine/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-policy-engine
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Policy evaluation engine to ensure actions are authorized and safe.
 category: security
+behavior: static-analysis
+intent: review-code
 priority: high
 tags: [security, policy, guardrails, authorization]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, evaluate, complete]
 > **Goal:** Đóng vai trò là "Bộ quy tắc thép" (Policy Enforcer). Ngăn chặn các lệnh sai lầm có thể phá hoại hệ thống.
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Risk Assessment):**
    - Classify the user's request (Low, Medium, High risk).
    - High Risk: Dropping databases, deleting multiple files, force-pushing to `main`.
@@ -29,10 +32,12 @@ pipeline: [analyze, evaluate, complete]
    - Approve (Allow execution) or Deny (Block execution) with explicit reasons.
 
 ## 🛡️ 2. Constraints & Rules
+
 - **Deny by Default:** If an action is highly destructive and no backup plan exists, DENY it.
 - **Override:** Only allow skipping the policy if the user explicitly passes an `--override` flag in their prompt.
 
 ## 🌳 3. Decision Tree
+
 ```text
 Does the action involve deleting data or resources in Production?
   ├── YES → Has the user provided a backup confirmation?
@@ -42,10 +47,13 @@ Does the action involve deleting data or resources in Production?
 ```
 
 ## 🤝 4. Handoff Pipeline
+
 1. `complete`: Generate the Policy Decision Report.
 
 ## 📝 5. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt.
+
 - **Tóm tắt (Summary):** Mức độ rủi ro (Risk Level).
 - **Phán quyết (Decision):** ✅ APPROVED hoặc ❌ DENIED.
 - **Nguyên nhân (Reasoning):** Vi phạm chính sách nào (nếu bị Deny).

package/skills/qk-production-release/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-production-release
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Prepare the codebase for a production release (Build, CI/CD, Security).
 category: operations
+behavior: validation
+intent: validate
 priority: high
 tags: [deploy, release, build, production]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, review, implement, validate, complete]
 > **Goal:** Chuẩn bị gói phần mềm để đẩy lên môi trường Production an toàn và tối ưu nhất (Minified, Tree-shaked).
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Pre-flight Checks):**
    - Check if the git branch is clean.
    - Verify environment variables are documented.
@@ -29,16 +32,20 @@ pipeline: [analyze, review, implement, validate, complete]
 4. **Complete (Deployment Plan):**
    - Provide a manual checklist for the user to execute the final deployment.
 
-## 🛡️ 2. Constraints & Rules
+## 🛡️ 3. Constraints & Rules
+
 - **No Rogue Deploys:** Never run commands like `firebase deploy` or `vercel --prod` without explicit, undeniable user approval.
 - **Secret Safety:** Never hardcode URLs. Ensure they are injected via ENV.
 
 ## 🤝 3. Handoff Pipeline
+
 1. `validate`: Run security sweep on the build output.
 2. `complete`: Output the Release Report.
 
 ## 📝 4. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt.
+
 - **Tóm tắt (Summary):** Trạng thái Build.
 - **Chi tiết (Changes):** Dung lượng Bundle (Bundle size optimization).
 - **Rủi ro (Risks):** Có lộ secret không.

package/skills/qk-project-bootstrap/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-project-bootstrap
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Initialize a new project with best practices, linters, and folder structures.
 category: setup
+behavior: development
+intent: implement-feature
 priority: high
 tags: [bootstrap, scaffolding, setup, init]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, implement, engineering-standard, validate, complete]
 > **Goal:** "Thợ xây móng". Khởi tạo một dự án mới hoàn toàn với các cấu hình chuẩn mực nhất từ Day 1.
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Requirements):**
    - Ask the user for their preferred stack (e.g., Next.js, Vite, NestJS).
 2. **Implement (Scaffolding):**
@@ -29,15 +32,19 @@ pipeline: [analyze, implement, engineering-standard, validate, complete]
    - Run `npm run dev` in a short background task to ensure it doesn't crash.
 
 ## 🛡️ 2. Constraints & Rules
+
 - **Strict Mode:** Always enable `strict: true` in TypeScript configurations.
 - **Package Manager Check:** If the user uses `pnpm`, do NOT run `npm install`. Stick to one package manager.
 
 ## 🤝 3. Handoff Pipeline
+
 1. `engineering-standard`: Verify the generated folder structure.
 2. `complete`: Output the Bootstrap Report.
 
 ## 📝 4. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt.
+
 - **Tóm tắt (Summary):** Dự án đã được khởi tạo với Stack nào.
 - **Chi tiết (Changes):** Cấu trúc thư mục mới và các file cấu hình.
 - **Xác thực (Verification):** Cách chạy dự án.

package/skills/qk-project-health/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-project-health
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Comprehensive audit of Code Smells, Tech Debt, and Architecture.
 category: architecture
+behavior: static-analysis
+intent: review-code
 priority: medium
 tags: [audit, architecture, tech-debt, code-smell]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, review, validate, complete]
 > **Goal:** "Khám sức khỏe" toàn diện cho Codebase. Tìm ra các Nợ Kỹ Thuật (Tech Debt), Mã Lỗi Thời (Code Smells), và các rủi ro cấu trúc dài hạn.
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Dependency Scan):**
    - Read `package.json` to identify outdated libraries, bloated dependencies, or unused packages.
 2. **Review (Architecture Scan):**
@@ -30,11 +33,13 @@ pipeline: [analyze, review, validate, complete]
 4. **Complete (Roadmap):**
    - Generate a prioritized Refactor Roadmap (High, Medium, Low).
 
-## 🛡️ 2. Constraints & Rules
+## 🛡️ 3. Constraints & Rules
+
 - **Audit Only - No Touch:** Do not modify any code. You are diagnosing, not performing surgery.
 - **Evidence Based:** Provide concrete metrics (e.g., "Folder `components` has 45 files, making it hard to navigate").
 
 ## 🌳 3. Decision Tree
+
 ```text
 Is the `src/components` folder bloated (>30 files)?
   ├── YES → Recommend migrating to a Feature-driven structure (e.g., `src/features/auth`).
@@ -46,10 +51,13 @@ Are there components exceeding 500 lines?
 ```
 
 ## 🤝 4. Handoff Pipeline
+
 1. `complete`: Output the Health Audit Report.
 
 ## 📝 5. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt.
+
 - **Tóm tắt (Summary):** Đánh giá tổng quan Sức Khỏe Dự Án (Điểm: X/100).
 - **Chi tiết (Changes):** Phân tích Dependencies, Architecture, Code Smells.
 - **Xác thực (Verification):** Các bằng chứng thu thập được từ code (dòng nào, file nào phình to).

package/skills/qk-project-memory/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-project-memory
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Store and retrieve long-term project context across sessions.
 category: utilities
+behavior: static-analysis
+intent: maintain
 priority: low
 tags: [memory, context, storage]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,17 +21,22 @@ pipeline: [analyze, implement, complete]
 > **Goal:** "Bộ nhớ dài hạn". Giúp Agent nhớ lại các cấu hình, đường dẫn API hoặc luật lệ riêng của dự án mà không cần User nhắc lại.
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Fact Extraction):**
    - Extract the core facts from the conversation (e.g., "The project uses pnpm, not npm").
 2. **Implement (Storage):**
    - Append the fact to `.ai-memory.md` or a similar configuration file.
 
 ## 🛡️ 2. Constraints & Rules
+
 - **Keep it small:** Do not write entire source files into memory. Only save abstract facts and rules.
 
 ## 🤝 3. Handoff Pipeline
+
 1. `complete`: Output confirmation.
 
 ## 📝 4. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt.
+
 - **Tóm tắt (Summary):** Đã ghi nhớ thông tin gì.

package/skills/qk-system-evolution/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-system-evolution
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Safely upgrade dependencies, migrate frameworks, and manage rollbacks.
 category: operations
+behavior: maintenance
+intent: maintain
 priority: high
 tags: [upgrade, migration, devops, dependencies]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, plan, implement, validate, complete]
 > **Goal:** Quản lý các thay đổi lớn cấp hệ thống (Major Updates) một cách an toàn, luôn có đường lui (Rollback) nếu xảy ra sự cố.
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Impact Analysis):**
    - Read the Changelog or Migration Guide for the new version.
    - Identify Breaking Changes and Deprecated APIs.
@@ -33,12 +36,14 @@ pipeline: [analyze, plan, implement, validate, complete]
    - Reinstall dependencies cleanly (`npm ci` or `yarn install`).
    - Run the build process to ensure the system compiles.
 
-## 🛡️ 2. Constraints & Rules
+## 🛡️ 3. Constraints & Rules
+
 - **Safety First:** Never run `npm update` blindly across all packages. Update only what was requested.
 - **Lockfiles:** Do not delete `package-lock.json` or `yarn.lock` unless resolving extreme merge conflicts.
 - **Always Rollback:** If the system produces >50 compilation errors after an upgrade and you cannot fix them in 1 turn, immediately trigger the Rollback Plan.
 
 ## 🌳 3. Decision Tree
+
 ```text
 Are there Breaking Changes in the target version?
   ├── YES → Create a migration checklist based on the official docs. Update code systematically.
@@ -52,11 +57,14 @@ Did the Build fail after the update?
 ```
 
 ## 🤝 4. Handoff Pipeline
+
 1. `validate`: Run the full test suite and `npm run build` via `qk-validation-gate`.
 2. `complete`: Generate the Evolution report.
 
 ## 📝 5. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt.
+
 - **Tóm tắt (Summary):** Đã nâng cấp package nào, từ vX lên vY.
 - **Chi tiết (Changes):** Số lượng file phải sửa do Breaking Changes.
 - **Kế hoạch lùi (Reasoning/Risks):** Ghi rõ lệnh Rollback để User copy-paste nếu cần.

package/skills/qk-ui-audit/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-ui-audit
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Audit UI for Consistency, Accessibility, Responsive, and Performance.
 category: validation
+behavior: static-analysis
+intent: review-code
 priority: medium
 tags: [ui, audit, frontend, a11y, responsive]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, review, validate, complete]
 > **Goal:** Kiểm toán chất lượng Giao diện Người dùng (UI QA). Tìm ra các lỗi hiển thị, sự thiếu đồng nhất và vi phạm Accessibility (a11y).
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Scan UI):**
    - Read the UI component's source code.
    - Look for inline styles (`style={{...}}`) and hardcoded magic numbers (e.g., `px`, `%` instead of standard tokens).
@@ -32,11 +35,13 @@ pipeline: [analyze, review, validate, complete]
 4. **Complete (Report):**
    - Calculate a rough score (0-100) based on violations.
 
-## 🛡️ 2. Constraints & Rules
+## 🛡️ 3. Constraints & Rules
+
 - **Audit Only:** Do not modify the code automatically unless the user explicitly requests you to apply the fixes.
 - **Evidence Based:** Point out the exact line number where the violation occurs.
 
 ## 🌳 3. Decision Tree
+
 ```text
 Does the component contain hardcoded `#hex` colors or `px` values?
   ├── YES → Deduct Consistency score. Recommend using Design Tokens.
@@ -48,10 +53,13 @@ Does the component have clickable `<div>` elements?
 ```
 
 ## 🤝 4. Handoff Pipeline
+
 1. `complete`: Generate the UI Audit Report.
 
 ## 📝 5. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt.
+
 - **Tóm tắt (Summary):** Chấm điểm Giao diện (Score: X/100).
 - **Chi tiết (Changes):** Liệt kê các lỗi Consistency, A11y, Responsive (ghi rõ dòng).
 - **Nguyên nhân (Reasoning):** Tại sao lại đánh lỗi điểm đó.

package/skills/qk-ui-system-builder/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-ui-system-builder
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Build and maintain Design Systems, Token extraction, and shared UI libraries.
 category: frontend
+behavior: development
+intent: implement-feature
 priority: medium
 tags: [design-system, tokens, shared-components, storybook]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, implement, engineering-standard, validate, complete]
 > **Goal:** Đảm bảo tính Nhất quán Giao diện (Consistency). Quản lý Design Tokens và xây dựng thư viện Shared Components.
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Token Extraction):**
    - Extract raw colors and typography into CSS Variables or Tailwind config.
 2. **Implement (Component Factory):**
@@ -27,14 +30,18 @@ pipeline: [analyze, implement, engineering-standard, validate, complete]
    - Ensure every variation (primary, secondary, disabled) is accounted for.
 
 ## 🛡️ 2. Constraints & Rules
+
 - **Stateless:** System UI components should NEVER have their own backend logic or hardcoded strings.
 - **Extendable:** Always allow users to pass `className` and `...props` to the base element.
 
 ## 🤝 3. Handoff Pipeline
+
 1. `engineering-standard`: Verify naming conventions.
 2. `complete`: Output the Design System Report.
 
 ## 📝 4. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt.
+
 - **Tóm tắt (Summary):** Thư viện Component vừa cập nhật.
 - **Chi tiết (Changes):** Liệt kê các variant (màu sắc, kích cỡ).

package/skills/qk-validation-gate/SKILL.md

@@ -1,9 +1,11 @@
 ---
 name: qk-validation-gate
-version: 3.0.0
+version: 3.1.0
 updated: 2026-07-02
 description: Mandatory Quality Gate (Test, Lint, Security).
 category: validation
+behavior: validation
+intent: validate
 priority: critical
 tags: [ci, testing, linting, security, gatekeeper]
 platforms: [claude-code, cursor, windsurf, gemini-cli]
@@ -19,6 +21,7 @@ pipeline: [analyze, validate, complete]
 > **Goal:** Hoạt động như một "Người Gác Cổng" (Gatekeeper). Đảm bảo không có lỗi cú pháp, vi phạm bảo mật, hoặc code rác nào lọt qua trước khi báo cáo hoàn thành.
 
 ## 🔄 1. Chain of Thought (SOP)
+
 1. **Analyze (Static Sweep):**
    - Use `grep_search` to scan modified files for garbage code: `console.log(`, `debugger;`, `// TODO`, `@ts-ignore`.
    - Scan for hardcoded secrets: `API_KEY=`, `Bearer ey...`.
@@ -30,12 +33,14 @@ pipeline: [analyze, validate, complete]
    - If minor lint errors exist, attempt an auto-fix (`npm run lint --fix`).
    - If tests fail, report the exact failure to the user. Do NOT pretend it passed.
 
-## 🛡️ 2. Constraints & Rules
+## 🛡️ 3. Constraints & Rules
+
 - **Zero Tolerance:** A failed test or a TypeScript error means the Gate is FAILED. Do not ignore errors.
 - **No Force:** Never use `--force` or `--no-verify` flags.
 - **Real Execution:** You MUST run the actual CLI commands using `run_command` and wait for the output.
 
 ## 🌳 3. Decision Tree
+
 ```text
 Did `npm run lint` return errors?
   ├── YES → Are they auto-fixable?
@@ -49,10 +54,13 @@ Did `tsc --noEmit` return errors?
 ```
 
 ## 🤝 4. Handoff Pipeline
+
 1. `complete`: Once all checks pass, output the Validation Report.
 
 ## 📝 5. Output Format
+
 Vui lòng trả kết quả bằng Tiếng Việt.
+
 - **Tóm tắt (Summary):** 🛡️ Đã chạy các cổng kiểm định (Lint, Test, Type).
 - **Chi tiết (Changes):** Liệt kê các lệnh đã chạy và kết quả.
 - **Xác thực (Verification):** Ghi rõ PASS (Xanh) hoặc FAIL (Đỏ).