ai-developer-skill-os 8.2.1 → 8.3.1

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

@@ -1,7 +1,7 @@
 ---
 # ── Identity ───────────────────────────────────────────────
 name: qk-system-evolution
-version: 8.0.0
+version: 8.3.1
 status: stable
 description: "Nâng cấp thư viện/framework an toàn với rollback plan bắt buộc — incremental, không big-bang."
 platforms: [antigravity, claude-code, cursor, windsurf, kilo-code]
@@ -50,6 +50,8 @@ knowledge_scope:
   references:
     - testing
     - architecture
+    - security
+    - anti-patterns
 
 # ── V8: Verification ───────────────────────────────────────
 verification:
@@ -96,11 +98,6 @@ On missing precondition:
   Message: "Rollback plan required before any major upgrade. Specify: target version + rollback method."
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Scope
 - ✅ Read official Changelog/Migration Guide for breaking changes
 - ✅ Apply incremental upgrades (not big-bang)
@@ -112,11 +109,6 @@ schema_version: 2
 - ❌ Skip reading Changelog for major version bumps
 - ❌ Upgrade multiple major versions at once (one at a time)
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Priority Order
 
 | Priority | Check | Skip Threshold |
@@ -128,19 +120,15 @@ schema_version: 2
 | P5 | Fix breaking changes if minor (< 3 files affected) | Budget < 40% |
 | P6 | Update documentation/README | Budget < 70% |
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Workflow
 
 ### Phase 1 — Breaking Change Analysis
 
 **Steps:**
-1. `view_file` or `read_url` — read official Changelog for target version
+1. `view_file` or `read_url` — read official Changelog for target version. **Đồng thời kiểm tra Security Advisory (CVEs) của version cũ.**
 2. List all `BREAKING CHANGE` entries
 3. Map each breaking change to affected files in current codebase (`grep_search`)
+4. *Lưu ý:* Nếu đây là bản vá bảo mật khẩn cấp (Security Patch), phải ưu tiên nâng cấp ngay cả khi có minor breaking changes, nhưng vẫn tuân thủ rollback plan.
 
 **Decision:**
 ```
@@ -155,11 +143,6 @@ IF > 3 breaking changes OR affects core files
   → Recommend: plan as a dedicated migration project
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ### Phase 2 — Rollback Snapshot
 
 **Steps:**
@@ -173,11 +156,6 @@ schema_version: 2
 
 **Exit When:** Rollback procedure documented → go to Phase 3
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ### Phase 3 — Incremental Upgrade
 
 **Steps:**
@@ -194,11 +172,6 @@ IF install fails (peer dep conflict)
   → EXIT: PARTIAL — report conflict, suggest resolution
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ### Phase 4 — Verification
 
 **Steps:**
@@ -219,11 +192,6 @@ IF > 3 tests fail OR core tests fail
   → Provide exact rollback command
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Confidence Model
 
 | Level | Condition | Action |
@@ -232,11 +200,6 @@ schema_version: 2
 | MEDIUM | Changelog read, some uncertainties remain | Proceed with caution, note risks |
 | LOW | Cannot access Changelog or no tests available | EXIT: BLOCKED |
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Severity
 
 | Level | Definition |
@@ -246,11 +209,6 @@ schema_version: 2
 | MEDIUM | Utility library, build tool upgrade |
 | LOW | Dev dependency, formatter upgrade |
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Evidence Format
 
 ```
@@ -261,11 +219,6 @@ Confidence:       [HIGH|MEDIUM|LOW]
 Rollback:         git checkout [tag] OR npm install [name]@[old-version]
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Rollback Procedure (Required Output)
 
 Every upgrade must document:
@@ -277,11 +230,6 @@ Method 2 (npm):  npm install [package]@[previous-version]
 Snapshot tag:    [pre-upgrade-[package]-[date]]
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Handoff Contract
 
 ### Consumes
@@ -301,22 +249,25 @@ schema_version: 2
 }
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
-
 ---
 
 ## Escalation Rules
-
-
+```
+BLOCKED: Missing rollback plan
+Questions:
+  1. Bạn muốn rollback bằng git tag hay snapshot?
+  2. Có test suite nào để chạy sau khi upgrade không?
+Recommended Assumptions: none
+```
 ---
 
 ## Retry Policy
-
-
+```
+Install fails due to peer conflict
+  └─ run with --legacy-peer-deps
+       ├─ PASS → log as PARTIAL
+       └─ FAIL → DO NOT retry again
+```
 ---
 ## Exit Codes
 
@@ -329,4 +280,3 @@ schema_version: 2
 
 ---
 
-

package/.agents/skills/qk-system-evolution/capability.yaml

@@ -0,0 +1,24 @@
+# Auto-generated from SKILL.md frontmatter
+schema_version: 1
+id: "qk-system-evolution"
+version: "8.3.1"
+description: "Nâng cấp thư viện/framework an toàn với rollback plan bắt buộc — incremental, không big-bang."
+tools:
+  - "filesystem"
+  - "terminal"
+knowledge:
+  owns:
+    - "upgrade-strategy"
+    - "rollback-plan"
+  references:
+    - "testing"
+    - "architecture"
+    - "security"
+    - "anti-patterns"
+eval:
+  scorecard: "evals/scorecard.yaml"
+decision_boundary:
+  owns:
+    - "qk-system-evolution"
+  does_not_own: []
+  conflicts_with: []

package/.agents/skills/qk-system-evolution/evals/scorecard.yaml

@@ -0,0 +1,26 @@
+name: qk-system-evolution-eval
+description: Đánh giá độ an toàn của quy trình nâng cấp System & Framework
+version: 8.3.1
+threshold: 90 # Việc nâng cấp framework mang rủi ro sập hệ thống rất cao
+
+metrics:
+  - id: rollback_safety
+    name: Cơ chế Rollback bắt buộc
+    description: Agent có thiết lập và ghi chép lại lệnh rollback trước khi nâng cấp không?
+    weight: 40
+    criteria:
+      - Phải yêu cầu/lưu lại Rollback command (git tag / version trước đó) trước khi sửa code (40đ)
+
+  - id: changelog_awareness
+    name: Phân tích Breaking Changes
+    description: Agent có đọc Changelog thay vì nhắm mắt upgrade không?
+    weight: 35
+    criteria:
+      - Quét và liệt kê các Breaking Changes từ Changelog/Migration Guide trước khi chạy (35đ)
+
+  - id: incremental_upgrade
+    name: Nâng cấp gia tăng (Incremental)
+    description: Có nâng cấp từng phần và chạy test xác minh thay vì Big-bang không?
+    weight: 25
+    criteria:
+      - Chạy test ngay sau khi nâng cấp 1 package thay vì update hàng loạt (25đ)

package/.agents/skills/qk-test-engineering/SKILL.md

@@ -1,139 +1,262 @@
----
-# ── Identity ───────────────────────────────────────────────
-name: qk-test-engineering
-version: 8.1.0
-status: experimental
-description: "Công cụ quyết định chiến lược kiểm thử (Unit, Integration, E2E, Coverage, Regression, Mock)."
-platforms: [antigravity, claude-code, cursor, windsurf, kilo-code]
-
-# ── V8: Classification ─────────────────────────────────────
-type: capability
-
-intent:
-  - testing-strategy
-  - unit-test
-  - integration-test
-  - e2e-test
-  - mock-strategy
-  - test-coverage
-
-complexity:
-  level: high
-  criteria:
-    files_affected: "1-5"
-    has_behavior_change: true
-    has_external_dependency: true
-    has_breaking_change: false
-
-triggers:
-  - "chiến lược test"
-  - "viết test"
-  - "mock data"
-  - "test coverage"
-
-# ── V8: References ─────────────────────────────────────────
-workflow: feature-delivery
-
-rules:
-  - global
-  - coding
-
-tools:
-  - filesystem
-  - terminal
-
-related_skills:
-  - qk-engineering-standard
-
-knowledge_scope:
-  domain:
-    - testing-strategy
-    - quality-assurance
-    - unit-testing
-    - integration-testing
-    - e2e-testing
-    - visual-regression
-  concepts:
-    - test-pyramid
-    - mock-strategy
-  references:
-    - architecture
-    - playwright
-    - vitest
-    - storybook-testing
-
-decision_boundary:
-  owns:
-    - test pyramid
-    - coverage strategy
-    - regression planning
-  does_not_own:
-    - business logic implementation
-    - writing tests
-  conflicts_with: []
-
-# ── V8: Verification ───────────────────────────────────────
-verification:
-  required: true
-  strategy: feature
-
-lifecycle:
-  promotion_gate:
-    requirements:
-      tests:
-        minimum_pass_rate: 0.95
-      usage:
-        minimum_runs: 20
-      conflicts:
-        zero_boundary_violation: true
-      evidence:
-        required:
-          - evaluation_report
-          - usage_history
-          - boundary_audit
-  demotion_gate:
-    triggers:
-      - repeated_failure
-      - boundary_violation
-      - outdated_reference
-    action:
-      change_status: "stable -> experimental"
-
-selection:
-  priority: medium
-  confidence_threshold: 0.80
-
-examples: []
-learnings: []
-
-# ── V7 Runtime ─────────────────────────────────────────────
-execution_mode: deterministic
-cost: medium
-latency: medium
-risk: low
-side_effects: read_only
-produces: [report, test_plan]
-consumes: [user-description]
-
-token_budget:
-  max_files_read: 5
-  max_lines_per_read: 150
-  max_shell_commands: 0
-  stop_early: true
-
-exit_codes: [SUCCESS, BLOCKED, FAILED, PARTIAL]
----
-
-# qk-test-engineering — Test Engineering Strategist
-
-> **Language rule:** Code, identifiers, file names → English. Explanations, summaries → Vietnamese.
-
-## Preconditions
-- [ ] Có code hoặc requirement rõ ràng cần kiểm thử.
-
-## Scope
-- Đưa ra quyết định chọn loại test (Unit, Integration, E2E) theo Test Pyramid.
-- Thiết kế chiến lược Mock (Mocking vs Stubbing vs Faking).
-- Đánh giá Test Coverage hiện tại và đưa ra target.
-- Quyết định Regression analysis (những phần nào cần test lại khi file A thay đổi).
-- Không tự động sinh test trừ khi user yêu cầu implement, skill này chủ yếu tư vấn architecture và strategy cho QA/Testing.
+---
+# ── Identity ───────────────────────────────────────────────
+name: qk-test-engineering
+version: 8.3.1
+status: experimental
+description: "Công cụ quyết định chiến lược kiểm thử (Unit, Integration, E2E, Coverage, Regression, Mock)."
+platforms: [antigravity, claude-code, cursor, windsurf, kilo-code]
+
+# ── V8: Classification ─────────────────────────────────────
+type: capability
+
+intent:
+  - testing-strategy
+  - unit-test-strategy
+  - integration-test-strategy
+  - e2e-test-strategy
+  - mock-strategy
+  - test-coverage-planning
+
+complexity:
+  level: high
+  criteria:
+    files_affected: "1-5"
+    has_behavior_change: true
+    has_external_dependency: true
+    has_breaking_change: false
+
+triggers:
+  - "chiến lược test"
+  - "viết test"
+  - "mock data"
+  - "test coverage"
+
+# ── V8: References ─────────────────────────────────────────
+workflow: feature-delivery
+
+rules:
+  - global
+  - coding
+
+tools:
+  - filesystem
+  - terminal
+
+related_skills:
+  - qk-engineering-standard
+
+knowledge_scope:
+  domain:
+    - testing-strategy
+    - quality-assurance
+    - unit-testing
+    - integration-testing
+    - e2e-testing
+    - visual-regression
+  concepts:
+    - test-pyramid
+    - mock-strategy
+  references:
+    - architecture
+    - anti-patterns
+    - playwright
+    - vitest
+    - storybook-testing
+
+decision_boundary:
+  owns:
+    - test pyramid
+    - coverage strategy
+    - regression planning
+  does_not_own:
+    - business logic implementation
+    - writing tests
+  conflicts_with: []
+
+# ── V8: Verification ───────────────────────────────────────
+verification:
+  required: true
+  strategy: feature
+
+lifecycle:
+  promotion_gate:
+    requirements:
+      tests:
+        minimum_pass_rate: 0.95
+      usage:
+        minimum_runs: 20
+      conflicts:
+        zero_boundary_violation: true
+      evidence:
+        required:
+          - evaluation_report
+          - usage_history
+          - boundary_audit
+  demotion_gate:
+    triggers:
+      - repeated_failure
+      - boundary_violation
+      - outdated_reference
+    action:
+      change_status: "stable -> experimental"
+
+selection:
+  priority: medium
+  confidence_threshold: 0.80
+
+examples: []
+learnings: []
+
+# ── V7 Runtime ─────────────────────────────────────────────
+execution_mode: deterministic
+cost: medium
+latency: medium
+risk: low
+side_effects: read_only
+produces: [report, test_plan]
+consumes: [user-description]
+
+token_budget:
+  max_files_read: 5
+  max_lines_per_read: 150
+  max_shell_commands: 0
+  stop_early: true
+
+exit_codes: [SUCCESS, BLOCKED, FAILED, PARTIAL]
+---
+
+# qk-test-engineering — Test Engineering Strategist
+
+> **Language rule:** Code, identifiers, file names → English. Explanations, summaries → Vietnamese.
+
+## Preconditions
+- [ ] Có code hoặc requirement rõ ràng cần kiểm thử.
+
+## Scope
+- Đưa ra quyết định chọn loại test (Unit, Integration, E2E) theo Test Pyramid.
+- Thiết kế chiến lược Mock (Mocking vs Stubbing vs Faking).
+- Đánh giá Test Coverage hiện tại và đưa ra target.
+- Quyết định Regression analysis (những phần nào cần test lại khi file A thay đổi).
+- **Bắt buộc thiết kế test case cho ranh giới dữ liệu (Negative Testing / Boundary Testing) để đảm bảo tuân thủ R-SEC-04.**
+- Không tự động sinh test trừ khi user yêu cầu implement, skill này chủ yếu tư vấn architecture và strategy cho QA/Testing.
+
+## Non-Goals
+- ❌ Provide implementation outside of Testing Strategy scope
+- ❌ Override explicit user directives without explanation
+- ❌ Guess ambiguous requirements without asking
+
+## Priority Order
+
+| Priority | Task | Skip Threshold |
+|----------|------|----------------|
+| P1 | Core Testing Strategy analysis and decision making | Never |
+| P2 | Validation of existing patterns | Budget < 30% |
+| P3 | Detailed documentation generation | Budget < 50% |
+| P4 | Edge case exploration | Budget < 70% |
+
+## Workflow
+
+### Phase 1 — Context Loading
+**Steps:**
+1. Read existing configuration and requirements related to Testing Strategy.
+2. Check for missing preconditions.
+
+**Decision:**
+```
+IF context is clear
+  → Confidence: HIGH → go to Phase 2
+ELSE
+  → EXIT: BLOCKED — ask user
+```
+
+### Phase 2 — Analysis & Strategy
+**Steps:**
+1. Analyze the current state against Testing Strategy best practices.
+2. Formulate strategy or audit report based on findings.
+
+**Decision:**
+```
+IF strategy/audit is complete
+  → Confidence: HIGH → go to Phase 3
+ELSE IF minor gaps exist
+  → Confidence: MEDIUM → proceed with assumptions noted
+```
+
+### Phase 3 — Finalization
+**Steps:**
+1. Generate final report or configuration.
+2. Prepare handoff data for subsequent skills.
+
+## Confidence Model
+
+| Level | Condition | Action |
+|-------|-----------|--------|
+| HIGH | All preconditions met, context fully understood | Proceed directly |
+| MEDIUM | Some context missing but safe defaults exist | Proceed and note assumptions |
+| LOW | Core requirements missing | EXIT: BLOCKED |
+
+## Severity (for findings)
+
+| Level | Definition |
+|-------|-----------|
+| CRITICAL | Severe violation of Testing Strategy principles |
+| HIGH | Significant risk or technical debt |
+| MEDIUM | Suboptimal pattern but functional |
+| LOW | Minor style or documentation issue |
+
+## Evidence Format
+
+```
+[SEVERITY] Context/File
+Issue:      [what was found]
+Confidence: HIGH
+Recommendation: [actionable advice]
+```
+
+## Retry Policy
+```
+Task fails due to missing context
+  └─ Ask user for clarification
+       ├─ Provided → Retry Phase 1
+       └─ Not provided → EXIT: BLOCKED
+```
+
+## Escalation Rules
+
+```
+BLOCKED: Missing critical context for Testing Strategy
+Missing:
+  - [Specific requirement]
+Questions:
+  1. Bạn có thể cung cấp thêm thông tin về yêu cầu này không?
+  2. Mục tiêu chính của bạn là gì?
+Recommended Assumptions: none
+```
+
+## Handoff Contract
+
+### Consumes
+```json
+{
+  "from": "user or qk-orchestrator",
+  "required_fields": ["context"],
+  "optional_fields": ["existing_config"]
+}
+```
+
+### Produces
+```json
+{
+  "to": "user or downstream skill",
+  "output_fields": ["strategy_report", "exit_code"]
+}
+```
+
+## Exit Codes
+
+| Code | Meaning | When |
+|------|---------|------|
+| SUCCESS | Testing Strategy task completed successfully | Strategy/audit generated |
+| PARTIAL | Task completed with assumptions | Medium confidence |
+| BLOCKED | Missing context | Cannot proceed |
+| FAILED | Critical conflict or error | Unresolvable constraint |

package/.agents/skills/qk-test-engineering/capability.yaml

@@ -0,0 +1,28 @@
+# Auto-generated from SKILL.md frontmatter
+schema_version: 1
+id: "qk-test-engineering"
+version: "8.3.1"
+description: "Công cụ quyết định chiến lược kiểm thử (Unit, Integration, E2E, Coverage, Regression, Mock)."
+tools:
+  - "filesystem"
+  - "terminal"
+knowledge:
+  owns:
+    - "qk-test-engineering"
+  references:
+    - "architecture"
+    - "anti-patterns"
+    - "playwright"
+    - "vitest"
+    - "storybook-testing"
+eval:
+  scorecard: "evals/scorecard.yaml"
+decision_boundary:
+  owns:
+    - "test pyramid"
+    - "coverage strategy"
+    - "regression planning"
+  does_not_own:
+    - "business logic implementation"
+    - "writing tests"
+  conflicts_with: []