ai-developer-skill-os 8.2.0 → 8.3.0

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

@@ -93,7 +93,7 @@ exit_codes: [SUCCESS, BLOCKED, FAILED, PARTIAL]
 
 # qk-ui-system-builder — Design System Constructor
 
-> **Language rule:** Code, identifiers, file names ? English. Explanations, summaries ? Vietnamese.
+> **Language rule:** Code, identifiers, file names → English. Explanations, summaries → Vietnamese.
 
 ---
 
@@ -193,17 +193,14 @@ IF some tokens inferred (MEDIUM confidence) → EXIT: PARTIAL, list them
 
 ---
 
-
 ---
 
 ## Priority Order
 
-
 ---
 
 ## Output Format
 
-
 ---
 ## Exit Codes
 | Code | Meaning | When |
@@ -287,4 +284,3 @@ Recommended Assumptions:
 
 ---
 
-

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

@@ -85,7 +85,6 @@ exit_codes: [SUCCESS, BLOCKED, FAILED, PARTIAL]
 
 > **Language rule:** Code, identifiers, file names → English. Explanations, summaries → Vietnamese.
 
-
 ## Preconditions
 - [ ] Project has `package.json` with lint/test scripts (or equivalent for other runtimes)
 - [ ] Target scope is specified (specific files, or whole project)
@@ -96,11 +95,6 @@ On missing precondition:
   Message: "Không tìm thấy script lint/test. Vui lòng chỉ định lệnh kiểm tra."
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Scope & V8.2 Eval Pipeline
 - ✅ Run lint, type-check, tests, and security audit in sequence
 - ✅ **Execute V8.2 Eval Pipeline:** Read `scorecard.yaml` (or inherited schemas) and compute quantitative scores for AI/Agent outputs.
@@ -113,11 +107,6 @@ schema_version: 2
 - ❌ Skip any gate check or eval scorecard unless user explicitly allows
 - ❌ Override failing thresholds with "ignore" flags or fabricated LLM scores without trace evidence
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Pass/Fail Thresholds (Non-Negotiable)
 
 ```yaml
@@ -149,11 +138,6 @@ eval_scorecard:
   zero_tolerance_hallucination: true
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Priority Order
 
 | Priority | Gate | Fail = Block? | Skip Allowed? |
@@ -167,11 +151,6 @@ schema_version: 2
 | P7 | Build | YES | Never |
 | P8 | Bundle size | WARN only | Budget < 80% |
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Workflow
 
 ### Phase 1 — Security Gate (P1)
@@ -190,11 +169,6 @@ ELSE IF critical or high found
   → Report: exact package name, CVE, severity
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ### Phase 2 — Type & Lint Gate (P2+P3)
 
 **Steps:**
@@ -214,11 +188,6 @@ ELSE IF lint errors > 0 (warnings OK)
   → EXIT: FAILED — list errors
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ### Phase 3 — Test Gate (P4+P5+P6)
 
 **Steps:**
@@ -245,11 +214,6 @@ Test fail
        └─ FAIL on retry → EXIT: FAILED — not flaky, real failure
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ### Phase 4 — Build Gate (P7)
 
 **Steps:**
@@ -268,11 +232,6 @@ ELSE IF warnings > 5
   → EXIT: PARTIAL — list warnings, continue to release if user confirms
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Confidence Model
 
 | Level | Condition | Action |
@@ -281,11 +240,6 @@ schema_version: 2
 | MEDIUM | Inferred from partial output (truncated logs) | Note potential missing info |
 | LOW | Script not found or output format unknown | EXIT: BLOCKED — clarify commands |
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Severity
 
 | Level | Definition | Example |
@@ -295,11 +249,6 @@ schema_version: 2
 | MEDIUM | Coverage below threshold | 67% coverage (threshold 80%) |
 | LOW | Build warning | Unused export |
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Evidence Format
 
 ```
@@ -321,11 +270,6 @@ Actual:     47/50 tests passed
 Fix:        See failing tests: auth.test.ts:L45, user.test.ts:L23, order.test.ts:L89
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Escalation Rules
 
 ```
@@ -341,11 +285,6 @@ Recommended Assumptions:
   - Standard: npm run lint + npm test + npm run build
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Handoff Contract
 
 ### Consumes
@@ -365,11 +304,6 @@ schema_version: 2
 }
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
 ## Output Format
 
 ```
@@ -392,17 +326,10 @@ Failures (action required):
 Exit Code:   [SUCCESS | PARTIAL | BLOCKED | FAILED]
 ```
 
-skill_version: 7.5.0
-runtime_version: 1
-schema_version: 2
----
-
-
 ---
 
 ## Retry Policy
 
-
 ---
 ## Exit Codes
 
@@ -415,4 +342,3 @@ schema_version: 2
 
 ---
 
-

package/.agents/skills/qk-web-quality-gate/SKILL.md

@@ -1,114 +1,232 @@
----
-# ── Identity ───────────────────────────────────────────────
-name: qk-web-quality-gate
-version: 8.1.0
-status: experimental
-description: "Kiểm toán tổng thể chất lượng Web: Accessibility (A11y), SEO, Web Performance, Security, UX Heuristics."
-platforms: [antigravity, claude-code, cursor, windsurf, kilo-code]
-
-# ── V8: Classification ─────────────────────────────────────
-type: capability
-
-intent:
-  - web-performance
-  - accessibility
-  - seo
-  - lighthouse
-  - ux-audit
-
-complexity:
-  level: high
-  criteria:
-    files_affected: "1-5"
-    has_behavior_change: false
-    has_external_dependency: true
-    has_breaking_change: false
-
-triggers:
-  - "kiểm tra web"
-  - "tối ưu web"
-  - "lighthouse"
-  - "audit ui"
-  - "core web vitals"
-
-# ── V8: References ─────────────────────────────────────────
-workflow: feature-delivery
-
-rules:
-  - global
-  - coding
-
-tools:
-  - filesystem
-  - terminal
-
-related_skills:
-  - qk-frontend-architecture
-
-knowledge_scope:
-  domain:
-    - web-performance
-    - web-accessibility
-  concepts:
-    - lighthouse
-    - seo
-    - ux-heuristics
-  references:
-    - architecture
-
-decision_boundary:
-  owns:
-    - lighthouse audit
-    - accessibility review
-    - performance audit
-    - seo audit
-  does_not_own:
-    - ui component implementation
-  conflicts_with: []
-
-# ── V8: Verification ───────────────────────────────────────
-verification:
-  required: true
-  strategy: 
-    - lighthouse
-    - accessibility
-    - performance
-
-selection:
-  priority: medium
-  confidence_threshold: 0.80
-
-examples: []
-learnings: []
-
-# ── V7 Runtime ─────────────────────────────────────────────
-execution_mode: deterministic
-cost: medium
-latency: slow
-risk: low
-side_effects: read_only
-produces: [report]
-consumes: [user-description]
-
-token_budget:
-  max_files_read: 5
-  max_lines_per_read: 150
-  max_shell_commands: 2
-  stop_early: false
-
-exit_codes: [SUCCESS, BLOCKED, FAILED, PARTIAL]
----
-
-# qk-web-quality-gate — Web Quality Auditor
-
-> **Language rule:** Code, identifiers, file names → English. Explanations, summaries → Vietnamese.
-
-## Preconditions
-- [ ] Ứng dụng web đã có thể chạy hoặc code đã được viết một phần.
-
-## Scope
-- Thực hiện kiểm toán A11y (Accessibility standards như WCAG).
-- Đánh giá Performance (Core Web Vitals, Bundle size, Lazy loading, Cache, Optimize images).
-- Kiểm tra SEO best practices (Meta tags, heading structure, semantic HTML).
-- Đánh giá UX Heuristics cơ bản.
-- Đưa ra khuyến nghị (Recommendation), không phải tự tay fix code nếu chưa được yêu cầu.
+---
+# ── Identity ───────────────────────────────────────────────
+name: qk-web-quality-gate
+version: 8.1.0
+status: experimental
+description: "Kiểm toán tổng thể chất lượng Web: Accessibility (A11y), SEO, Web Performance, Security, UX Heuristics."
+platforms: [antigravity, claude-code, cursor, windsurf, kilo-code]
+
+# ── V8: Classification ─────────────────────────────────────
+type: capability
+
+intent:
+  - web-performance
+  - accessibility
+  - seo
+  - lighthouse
+  - ux-audit
+
+complexity:
+  level: high
+  criteria:
+    files_affected: "1-5"
+    has_behavior_change: false
+    has_external_dependency: true
+    has_breaking_change: false
+
+triggers:
+  - "kiểm tra web"
+  - "tối ưu web"
+  - "lighthouse"
+  - "audit ui"
+  - "core web vitals"
+
+# ── V8: References ─────────────────────────────────────────
+workflow: feature-delivery
+
+rules:
+  - global
+  - coding
+
+tools:
+  - filesystem
+  - terminal
+
+related_skills:
+  - qk-frontend-architecture
+
+knowledge_scope:
+  domain:
+    - web-performance
+    - web-accessibility
+  concepts:
+    - lighthouse
+    - seo
+    - ux-heuristics
+  references:
+    - architecture
+
+decision_boundary:
+  owns:
+    - lighthouse audit
+    - accessibility review
+    - performance audit
+    - seo audit
+  does_not_own:
+    - ui component implementation
+  conflicts_with: []
+
+# ── V8: Verification ───────────────────────────────────────
+verification:
+  required: true
+  strategy: web-quality-review
+
+selection:
+  priority: medium
+  confidence_threshold: 0.80
+
+examples: []
+learnings: []
+
+# ── V7 Runtime ─────────────────────────────────────────────
+execution_mode: deterministic
+cost: medium
+latency: slow
+risk: low
+side_effects: read_only
+produces: [report]
+consumes: [user-description]
+
+token_budget:
+  max_files_read: 5
+  max_lines_per_read: 150
+  max_shell_commands: 2
+  stop_early: true
+
+exit_codes: [SUCCESS, BLOCKED, FAILED, PARTIAL]
+---
+
+# qk-web-quality-gate — Web Quality Auditor
+
+> **Language rule:** Code, identifiers, file names → English. Explanations, summaries → Vietnamese.
+
+## Preconditions
+- [ ] Ứng dụng web đã có thể chạy hoặc code đã được viết một phần.
+
+## Scope
+- Thực hiện kiểm toán A11y (Accessibility standards như WCAG).
+- Đánh giá Performance (Core Web Vitals, Bundle size, Lazy loading, Cache, Optimize images).
+- Kiểm tra SEO best practices (Meta tags, heading structure, semantic HTML).
+- Đánh giá UX Heuristics cơ bản.
+- Đưa ra khuyến nghị (Recommendation), không phải tự tay fix code nếu chưa được yêu cầu.
+
+## Non-Goals
+- ❌ Provide implementation outside of Web Performance & Accessibility scope
+- ❌ Override explicit user directives without explanation
+- ❌ Guess ambiguous requirements without asking
+
+## Priority Order
+
+| Priority | Task | Skip Threshold |
+|----------|------|----------------|
+| P1 | Core Web Performance & Accessibility 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 Web Performance & Accessibility.
+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 Web Performance & Accessibility 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 Web Performance & Accessibility 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 Web Performance & Accessibility
+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 | Web Performance & Accessibility 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 |