ai-developer-skill-os 5.0.0 → 6.0.1

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

@@ -1,56 +1,35 @@
 ---
 name: qk-production-release
-version: 5.0.0
-updated: 2026-07-03
-description: Chuẩn bị codebase để phát hành lên production (Build, CI/CD, Security).
 category: devops
-tags: [devops, ci-cd, release, deployment]
-platforms: [claude-code, cursor, windsurf, gemini-cli]
+version: 6.0.0
 ---
 
-# 🛠️ qk-production-release
+# qk-production-release
 
-> **Inheritance:** Kỹ năng này tuân thủ Kiến trúc v5.0 của `framework/KERNEL.md`.
-> Output bắt buộc là Decision Summary.
+## Scope
+- Preparing codebase for production release including Build, CI/CD, and Security checks (Plan & Govern)
 
----
-
-## 🎯 Mission (Scope)
-- ✅ Chạy kiểm tra chất lượng cuối cùng trước khi build.
-- ❌ Do NOT tự tay deploy lên Production server mà không hỏi ý kiến.
-
----
-
-## ⚙️ Capabilities (Cognitive Pipeline)
+## Constraints
 ```yaml
-Pipeline:
-  - inference
-  - planning
-  - execution
-  - bias-review
-  - ship-check
+must:
+  - Verify that all tests pass and linters are clean
+  - Check for exposed secrets or misconfigurations
+must_not:
+  - Deploy code that fails security audits
 ```
 
----
-
-## 🎛️ Dials (Hành vi)
+## Policies
 ```yaml
-Dials:
-  - id: strictness
+prefer:
+  - Immutable artifacts and deterministic builds
 ```
 
----
-
-## 🛡️ Biases (Sửa lỗi mặc định)
+## Escalation
 ```yaml
-Biases:
-  - id: hallucinated-tools # (Tự chạy lệnh deploy không tồn tại)
+stop:
+  - Security vulnerabilities or critical test failures are detected
 ```
 
----
-
-## 🛫 Ship Criteria
-```yaml
-Rules:
-  - id: end-to-end-validation
+## Output
+- Release checklist and deployment readiness status
 ```

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

@@ -1,57 +1,36 @@
 ---
 name: qk-project-bootstrap
-version: 5.0.0
-updated: 2026-07-03
-description: Khởi tạo dự án mới với các best practices, linters, và cấu trúc thư mục chuẩn.
-category: setup
-tags: [bootstrap, scaffolding, setup, init]
-platforms: [claude-code, cursor, windsurf, gemini-cli]
+category: fullstack
+version: 6.0.0
 ---
 
-# 🛠️ qk-project-bootstrap
+# qk-project-bootstrap
 
-> **Inheritance:** Kỹ năng này tuân thủ Kiến trúc v5.0 của `framework/KERNEL.md`.
-> Output bắt buộc là Decision Summary.
+## Scope
+- Initializing new projects with best practices (Execute)
 
----
-
-## 🎯 Mission (Scope)
-- ✅ Setup dự án mới từ đầu.
-- ❌ Do NOT khởi tạo với cấu hình lỏng lẻo (Linter tắt).
-
----
-
-## ⚙️ Capabilities (Cognitive Pipeline)
+## Constraints
 ```yaml
-Pipeline:
-  - inference
-  - planning
-  - execution
-  - bias-review
-  - ship-check
+must:
+  - Setup linters, formatters, and standard directory structures
+  - Follow the organization's existing templates if available
+must_not:
+  - Hardcode outdated dependency versions
+  - Skip adding basic README instructions
 ```
 
----
-
-## 🎛️ Dials (Hành vi)
+## Policies
 ```yaml
-Dials:
-  - id: strictness
-  - id: complexity-budget
+prefer:
+  - Standard tooling over custom scripts
 ```
 
----
-
-## 🛡️ Biases (Sửa lỗi mặc định)
+## Escalation
 ```yaml
-Biases:
-  - id: enterprise-crud
+ask:
+  - To clarify preferred framework/language if not specified
 ```
 
----
-
-## 🛫 Ship Criteria
-```yaml
-Rules:
-  - id: no-unnecessary-dependencies
+## Output
+- Bootstrapped repository structure
 ```

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

@@ -1,56 +1,36 @@
 ---
 name: qk-project-health
-version: 5.0.0
-updated: 2026-07-03
-description: Kiểm toán toàn diện về Code Smells, Tech Debt, và Architecture.
-category: architecture
-tags: [audit, architecture, tech-debt, code-smell]
-platforms: [claude-code, cursor, windsurf, gemini-cli]
+category: maintenance
+version: 6.0.0
 ---
 
-# 🛠️ qk-project-health
+# qk-project-health
 
-> **Inheritance:** Kỹ năng này tuân thủ Kiến trúc v5.0 của `framework/KERNEL.md`.
-> Output bắt buộc là Decision Summary.
+## Scope
+- Comprehensive auditing of Code Smells, Tech Debt, and Architecture (Diagnose & Evaluate)
 
----
-
-## 🎯 Mission (Scope)
-- ✅ Phân tích tech debt và code smells.
-- ❌ Do NOT bắt lỗi thụt lề, khoảng trắng (Việc của linter).
-
----
-
-## ⚙️ Capabilities (Cognitive Pipeline)
+## Constraints
 ```yaml
-Pipeline:
-  - inference
-  - planning
-  - execution
-  - bias-review
-  - ship-check
+must:
+  - Analyze dependency graphs and code complexity metrics
+  - Highlight architectural anti-patterns
+must_not:
+  - Rewrite major components without user consent
+  - Focus purely on stylistic lints (leave that to linter)
 ```
 
----
-
-## 🎛️ Dials (Hành vi)
+## Policies
 ```yaml
-Dials:
-  - id: strictness
+prefer:
+  - Structural and performance improvements over minor refactors
 ```
 
----
-
-## 🛡️ Biases (Sửa lỗi mặc định)
+## Escalation
 ```yaml
-Biases:
-  - id: cosmetic-refactor
+stop:
+  - The project lacks basic structure making analysis impossible
 ```
 
----
-
-## 🛫 Ship Criteria
-```yaml
-Rules:
-  - id: delegation-only # (Chỉ đọc và tư vấn, cấm tự ý đổi code)
+## Output
+- Health report and refactoring plan
 ```

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

@@ -1,56 +1,35 @@
 ---
 name: qk-project-memory
-version: 5.0.0
-updated: 2026-07-03
-description: Lưu trữ và truy xuất ngữ cảnh dự án dài hạn qua các phiên làm việc.
-category: utilities
-tags: [memory, context, storage]
-platforms: [claude-code, cursor, windsurf, gemini-cli]
+category: core
+version: 6.0.0
 ---
 
-# 🛠️ qk-project-memory
+# qk-project-memory
 
-> **Inheritance:** Kỹ năng này tuân thủ Kiến trúc v5.0 của `framework/KERNEL.md`.
-> Output bắt buộc là Decision Summary.
+## Scope
+- Storing and retrieving long-term project context across sessions (Collect)
 
----
-
-## 🎯 Mission (Scope)
-- ✅ Lưu trữ các Rule, ADR, và cấu hình bất biến vào memory.
-- ❌ Do NOT dump toàn bộ file mã nguồn hoặc hội thoại vào memory gây phình to token.
-
----
-
-## ⚙️ Capabilities (Cognitive Pipeline)
+## Constraints
 ```yaml
-Pipeline:
-  - inference
-  - planning
-  - execution
-  - bias-review
-  - ship-check
+must:
+  - Organize context logically so it can be retrieved efficiently
+  - Update memory artifacts when major architectural decisions are made
+must_not:
+  - Store sensitive user data or secrets in project memory
 ```
 
----
-
-## 🎛️ Dials (Hành vi)
+## Policies
 ```yaml
-Dials:
-  - id: strictness
+prefer:
+  - Concise summaries over verbose logs for long-term memory
 ```
 
----
-
-## 🛡️ Biases (Sửa lỗi mặc định)
+## Escalation
 ```yaml
-Biases:
-  - id: hallucinated-tools
+ask:
+  - To clarify contradictory information found in the project memory
 ```
 
----
-
-## 🛫 Ship Criteria
-```yaml
-Rules:
-  - id: minimal-diff
+## Output
+- Updated memory artifacts
 ```

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

@@ -1,56 +1,35 @@
 ---
 name: qk-system-evolution
-version: 5.0.0
-updated: 2026-07-03
-description: Cập nhật an toàn các thư viện dependencies, di chuyển frameworks và quản lý quá trình rollback.
-category: operations
-tags: [upgrade, migration, devops, dependencies]
-platforms: [claude-code, cursor, windsurf, gemini-cli]
+category: infrastructure
+version: 6.0.0
 ---
 
-# 🛠️ qk-system-evolution
+# qk-system-evolution
 
-> **Inheritance:** Kỹ năng này tuân thủ Kiến trúc v5.0 của `framework/KERNEL.md`.
-> Output bắt buộc là Decision Summary.
+## Scope
+- Safely updating dependencies, migrating frameworks, and managing rollbacks (Plan & Execute)
 
----
-
-## 🎯 Mission (Scope)
-- ✅ Nâng cấp dependencies và xử lý breaking changes.
-- ❌ Do NOT xóa file lock tuỳ tiện hoặc cập nhật `latest` mù quáng.
-
----
-
-## ⚙️ Capabilities (Cognitive Pipeline)
+## Constraints
 ```yaml
-Pipeline:
-  - inference
-  - planning
-  - execution
-  - bias-review
-  - ship-check
+must:
+  - Check compatibility matrices before upgrading dependencies
+  - Provide a rollback plan for major framework updates
+must_not:
+  - Perform destructive migrations without a backup strategy
 ```
 
----
-
-## 🎛️ Dials (Hành vi)
+## Policies
 ```yaml
-Dials:
-  - id: strictness
+prefer:
+  - Incremental updates over 'big bang' migrations
 ```
 
----
-
-## 🛡️ Biases (Sửa lỗi mặc định)
+## Escalation
 ```yaml
-Biases:
-  - id: swallow-errors
+stop:
+  - Critical dependencies are completely incompatible with the target framework version
 ```
 
----
-
-## 🛫 Ship Criteria
-```yaml
-Rules:
-  - id: end-to-end-validation
+## Output
+- Migration scripts, updated package files, and rollback plans
 ```

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

@@ -1,57 +1,35 @@
 ---
 name: qk-ui-audit
-version: 5.0.0
-updated: 2026-07-03
-description: Kiểm toán giao diện (UI) để đảm bảo tính nhất quán, khả năng truy cập (A11y), độ phản hồi (Responsive) và hiệu suất.
-category: validation
-tags: [ui, audit, frontend, a11y, responsive]
-platforms: [claude-code, cursor, windsurf, gemini-cli]
+category: qa
+version: 6.0.0
 ---
 
-# 🛠️ qk-ui-audit
+# qk-ui-audit
 
-> **Inheritance:** Kỹ năng này tuân thủ Kiến trúc v5.0 của `framework/KERNEL.md`.
-> Output bắt buộc là Decision Summary.
+## Scope
+- UI consistency, accessibility (A11y), responsiveness, and performance auditing (Evaluate)
 
----
-
-## 🎯 Mission (Scope)
-- ✅ Audit UI/UX, rà soát Design Tokens, A11y, và Responsive.
-- ❌ Do NOT tự tiện sửa code trừ khi user ra lệnh.
-
----
-
-## ⚙️ Capabilities (Cognitive Pipeline)
+## Constraints
 ```yaml
-Pipeline:
-  - inference
-  - planning
-  - execution
-  - bias-review
-  - ship-check
+must:
+  - Check UI against established design tokens and guidelines
+  - Verify ARIA roles and contrast ratios
+must_not:
+  - Ignore mobile viewport constraints
 ```
 
----
-
-## 🎛️ Dials (Hành vi)
+## Policies
 ```yaml
-Dials:
-  - id: aesthetic-vibe
-  - id: strictness
+prefer:
+  - Identifying systemic UI issues over isolated pixel tweaks
 ```
 
----
-
-## 🛡️ Biases (Sửa lỗi mặc định)
+## Escalation
 ```yaml
-Biases:
-  - id: cosmetic-refactor # (Audit format code thay vì audit UX/Tokens)
+stop:
+  - UI components completely lack semantic structure
 ```
 
----
-
-## 🛫 Ship Criteria
-```yaml
-Rules:
-  - id: delegation-only # (Chỉ đọc và Report)
+## Output
+- UI audit report with actionable fixes
 ```

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

@@ -1,56 +1,35 @@
 ---
 name: qk-ui-system-builder
-version: 5.0.0
-updated: 2026-07-03
-description: Xây dựng và duy trì Design Systems, Token extraction, và các thư viện UI dùng chung.
 category: frontend
-tags: [design-system, tokens, shared-components, storybook]
-platforms: [claude-code, cursor, windsurf, gemini-cli]
+version: 6.0.0
 ---
 
-# 🛠️ qk-ui-system-builder
+# qk-ui-system-builder
 
-> **Inheritance:** Kỹ năng này tuân thủ Kiến trúc v5.0 của `framework/KERNEL.md`.
-> Output bắt buộc là Decision Summary.
+## Scope
+- Building and maintaining Design Systems and shared UI tokens (Plan & Execute)
 
----
-
-## 🎯 Mission (Scope)
-- ✅ Xây dựng Shared Components (Dumb components).
-- ❌ Do NOT nhét logic API hoặc Fetch data vào core component.
-
----
-
-## ⚙️ Capabilities (Cognitive Pipeline)
+## Constraints
 ```yaml
-Pipeline:
-  - inference
-  - planning
-  - execution
-  - bias-review
-  - ship-check
+must:
+  - Extract reusable design tokens (colors, spacing, typography)
+  - Ensure components are accessible (A11y)
+must_not:
+  - Create duplicate tokens for the same visual value
 ```
 
----
-
-## 🎛️ Dials (Hành vi)
+## Policies
 ```yaml
-Dials:
-  - id: strictness
+prefer:
+  - Composable components over rigid layouts
 ```
 
----
-
-## 🛡️ Biases (Sửa lỗi mặc định)
+## Escalation
 ```yaml
-Biases:
-  - id: missing-ui-states
+stop:
+  - Design tokens conflict with existing design guidelines
 ```
 
----
-
-## 🛫 Ship Criteria
-```yaml
-Rules:
-  - id: end-to-end-validation
+## Output
+- UI component library or Design System tokens
 ```

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

@@ -1,54 +1,36 @@
 ---
 name: qk-validation-gate
-version: 5.0.0
-updated: 2026-07-03
-description: Cổng kiểm tra chất lượng bắt buộc (Test, Lint, Security).
-category: validation
-tags: [ci, testing, linting, security, gatekeeper]
-platforms: [claude-code, cursor, windsurf, gemini-cli]
+category: qa
+version: 6.0.0
 ---
 
-# 🛠️ qk-validation-gate
+# qk-validation-gate
 
-> **Inheritance:** Kỹ năng này tuân thủ Kiến trúc v5.0 của `framework/KERNEL.md`.
-> Output bắt buộc là Decision Summary.
+## Scope
+- Mandatory quality checks (Test, Lint, Security) before merge/commit (Evaluate)
 
----
-
-## 🎯 Mission (Scope)
-- ✅ Chạy các lệnh kiểm định (Test, Lint) thực tế.
-- ❌ Do NOT giả vờ là test đã pass mà không gọi tool CLI.
-
----
-
-## ⚙️ Capabilities (Cognitive Pipeline)
+## Constraints
 ```yaml
-Pipeline:
-  - inference
-  - execution
-  - ship-check
+must:
+  - Verify acceptance criteria and test coverage
+  - Fail early if critical errors or lint violations are found
+must_not:
+  - Approve incomplete work or failing tests
+  - Bypass security scans
 ```
 
----
-
-## 🎛️ Dials (Hành vi)
+## Policies
 ```yaml
-Dials:
-  - id: strictness
+prefer:
+  - Automated testing over manual verification
 ```
 
----
-
-## 🛡️ Biases (Sửa lỗi mặc định)
+## Escalation
 ```yaml
-Biases:
-  - id: hallucinated-tools
+stop:
+  - Artifact is absent or tests are failing
 ```
 
----
-
-## 🛫 Ship Criteria
-```yaml
-Rules:
-  - id: end-to-end-validation
+## Output
+- Pass/Fail decision and validation report
 ```

package/specs/contracts/behavior-contract.yaml

@@ -0,0 +1,40 @@
+# Tập hợp tất cả các Behavior Contracts của hệ thống
+# Đây là "Source of Truth" để các bài test đối chiếu.
+
+bug-resolution:
+  must:
+    - ask_for_logs_when_missing
+    - avoid_large_refactor
+    - preserve_api
+  prefer:
+    - smallest_change
+    - deterministic_fix
+  never:
+    - invent_root_cause
+    - fabricate_test_result
+
+feature-delivery:
+  must:
+    - minimize_scope
+    - preserve_behavior
+    - verify_regression
+    - handle_ui_states
+  prefer:
+    - clean_code
+  never:
+    - redesign_architecture
+    - rewrite_core_module
+
+access-policy:
+  must:
+    - block_api
+    - enforce_rbac
+  never:
+    - ui_only_security
+
+engineering-standard:
+  must:
+    - maintain_readability
+    - pass_linter
+  never:
+    - change_business_logic

package/specs/expectations/qk-bug-resolution.yaml

@@ -0,0 +1,35 @@
+behavior: qk-bug-resolution
+
+must:
+  - gather_context_before_proposing
+  - require_stack_trace
+  - minimize_scope
+  - preserve_public_api
+  - evaluate_regression_risk
+  - communicate_user_intent
+  - ask_only_necessary_questions
+  - explain_decisions_in_user_language
+
+prefer:
+  - write_reproduction_steps
+  - identify_root_cause
+  - add_regression_test
+
+must_not:
+  - rewrite_module
+  - refactor_unrelated_code
+  - change_architecture
+  - guess_cause_without_evidence
+  - expose_internal_contract
+  - expose_internal_policy
+  - expose_internal_reasoning
+  - quote_yaml_sections
+
+evidence:
+  - stack_trace_or_log
+  - related_source_code
+
+completion:
+  - patch_provided
+  - risk_summary_provided
+  - verification_checklist_provided