@nockdev/awf 6.2.0 → 6.2.1

package/.agent/workflows/e2e.md

@@ -0,0 +1,112 @@
+---
+description: "🌐 E2E test generation: detect framework, write critical path tests, run and verify"
+skills: { required: [testing, tdd-workflow], contextual: [auto] }
+---
+
+# 🌐 /e2e — End-to-End Test Generation
+
+> Generate and run E2E tests for critical user flows
+> 📚 Playwright • Cypress • Selenium • Multi-browser
+
+---
+
+## E2E FLOW
+
+1. **DETECT** — Identify frontend framework, existing E2E setup, test runner. Show: `[Step 1/5] Detecting E2E framework...`
+2. **MAP** — Identify critical user flows from routes/pages. Show: `[Step 2/5] Mapping 8 critical user flows...`
+3. **GENERATE** — Write E2E tests for critical paths. Show: `[Step 3/5] Generating tests for Login → Dashboard → Checkout`
+4. **RUN** — Execute E2E tests, capture screenshots on failure. Show: `[Step 4/5] Running 12 E2E tests...`
+5. **REPORT** — Show results with pass/fail, timing, screenshots. Show: `[Step 5/5] ✅ 11/12 passed (1 flaky)`
+
+---
+
+## COMMANDS
+
+| Command       | Description                           |
+| ------------- | ------------------------------------- |
+| `/e2e`        | Generate E2E tests for critical flows |
+| `/e2e [page]` | Generate E2E tests for specific page  |
+| `/e2e run`    | Run existing E2E tests                |
+| `/e2e smoke`  | Generate smoke tests only             |
+| `/e2e visual` | Visual regression tests               |
+
+---
+
+## FRAMEWORK DETECTION
+
+| Framework      | Config File            | Runner                |
+| -------------- | ---------------------- | --------------------- |
+| **Playwright** | `playwright.config.ts` | `npx playwright test` |
+| **Cypress**    | `cypress.config.ts`    | `npx cypress run`     |
+| **Selenium**   | `wdio.conf.ts`         | `npx wdio run`        |
+
+If no E2E framework found:
+
+1. Recommend Playwright (modern, fast, multi-browser)
+2. Offer to scaffold: `npm init playwright@latest`
+
+---
+
+## CRITICAL FLOW IDENTIFICATION
+
+Automatically identify critical flows from:
+
+- **Routes/pages**: Login, dashboard, checkout, settings
+- **Forms**: Registration, payment, contact
+- **CRUD**: Create, read, update, delete operations
+- **Auth**: Login, logout, password reset, 2FA
+
+Priority:
+
+1. 🔴 **Revenue flows**: Checkout, payment, subscription
+2. 🟠 **User onboarding**: Registration, login, first-use
+3. 🟡 **Core features**: Primary user actions
+4. 🟢 **Settings/profile**: Account management
+
+---
+
+## TEST STRUCTURE
+
+```typescript
+// Playwright E2E test template
+import { test, expect } from "@playwright/test";
+
+test.describe("User Login Flow", () => {
+  test("should login with valid credentials", async ({ page }) => {
+    // Arrange
+    await page.goto("/login");
+
+    // Act
+    await page.fill('[data-testid="email"]', "user@example.com");
+    await page.fill('[data-testid="password"]', "password123");
+    await page.click('[data-testid="login-button"]');
+
+    // Assert
+    await expect(page).toHaveURL("/dashboard");
+    await expect(page.locator('[data-testid="welcome"]')).toBeVisible();
+  });
+
+  test("should show error for invalid credentials", async ({ page }) => {
+    await page.goto("/login");
+    await page.fill('[data-testid="email"]', "wrong@example.com");
+    await page.fill('[data-testid="password"]', "wrong");
+    await page.click('[data-testid="login-button"]');
+    await expect(page.locator('[data-testid="error"]')).toContainText(
+      "Invalid",
+    );
+  });
+});
+```
+
+---
+
+## BEST PRACTICES
+
+| Rule                            | Why                            |
+| ------------------------------- | ------------------------------ |
+| Use `data-testid` selectors     | Stable, decoupled from styling |
+| One assertion per critical path | Clear failure identification   |
+| Set up test data via API        | Faster than UI setup           |
+| Clean up after tests            | Avoid inter-test dependencies  |
+| Run in CI with retries          | Handle flakiness               |
+| Screenshot on failure           | Visual debugging               |

package/.agent/workflows/fix.md

@@ -59,7 +59,7 @@ skills: { required: [], contextual: [auto] }
 
 ---
 
-## 🔄 ESCALATION
+## 🎨 UI FIX CATEGORY (→ FLOW.md §18.6)\r\n\r\n| Category | Detect Pattern | Additional Steps |\r\n|-----------|---------------------------------------------|---------------------------------------|\r\n| CSS/Style | overflow, z-index, opacity, display, visible | Load design tokens, check dark mode |\r\n| Layout | flex/grid, position, float, alignment | Verify responsive (mobile + desktop) |\r\n| Color | color, background, gradient, contrast | Verify WCAG contrast ≥ 4.5:1 |\r\n| Font | font-size, line-height, font-family | Check typography scale compliance |\r\n| Animation | transition, transform, keyframes | Check prefers-reduced-motion |\r\n| Dark Mode | dark: prefix, color-scheme, theme toggle | Test both modes after fix |\r\n\r\nWhen UI fix detected → auto-load `domyh-design` skill, apply §18.6 additional verify.\r\n\r\n---\r\n\r\n## 🔄 ESCALATION
 
 After 2 retries fail:
 

package/.agent/workflows/prompt.md

@@ -0,0 +1,325 @@
+---
+description: "✍️ AI Prompt Generator: research, analyze, and create structured markdown prompts"
+skills: { required: [prompt-engineering], contextual: [domyh-design] }
+---
+
+# ✍️ /prompt — Prompt Generator Pro
+
+> Research → Analyze → Structure → Generate → Refine
+> 📚 RCTO Framework • Online Research • Multi-format Output
+
+---
+
+## PROMPT FLOW
+
+1. **ANALYZE** — Parse user request, detect prompt type (image/project/modify/system/general). Extract: mục đích, target tool/model, ngôn ngữ, constraints. Show: `[Step 1/5] Analyzing: "{request}" → Type: image`
+2. **RESEARCH** — Online research về domain, best practices, reference examples. Tìm kiếm: cấu trúc prompt tối ưu cho target tool, industry standards, trending patterns. Show: `[Step 2/5] Researching: "midjourney v6 architecture prompts"...`
+3. **STRUCTURE** — Apply RCTO Framework (Role-Context-Task-Output). Map research → sections phù hợp. Choose template theo prompt type. Show: `[Step 3/5] Structuring prompt with 6 sections...`
+4. **GENERATE** — Tạo structured markdown prompt. Viết bằng ngôn ngữ người dùng yêu cầu. Apply prompt-engineering patterns (CoT, few-shot, role-play). Show: `[Step 4/5] Generating prompt...`
+5. **REFINE** — Present output → ⛔ **STOP — user review**. Iterate nếu cần: thêm chi tiết, đổi style, adjust parameters.
+
+---
+
+## COMMANDS
+
+| Command                  | Loại        | Mô tả                     | Output              |
+| ------------------------ | ----------- | ------------------------- | ------------------- |
+| `/prompt [anything]`     | auto-detect | Tự phân tích và chọn loại | Markdown prompt     |
+| `/prompt image [desc]`   | image       | Prompt tạo ảnh AI         | Image gen prompt    |
+| `/prompt project [desc]` | project     | Prompt tạo dự án mới      | Project spec prompt |
+| `/prompt modify [desc]`  | modify      | Prompt chỉnh sửa dự án    | Modification prompt |
+| `/prompt system [desc]`  | system      | System prompt cho AI      | System prompt       |
+
+### Flags
+
+| Flag                                      | Mô tả                                    |
+| ----------------------------------------- | ---------------------------------------- |
+| `--lang vi/en`                            | Ngôn ngữ output (default: ngôn ngữ user) |
+| `--tool midjourney/dalle/flux/claude/gpt` | Target AI tool                           |
+| `--detail minimal/standard/detailed`      | Mức chi tiết (default: detailed)         |
+| `--format markdown/yaml/json`             | Output format (default: markdown)        |
+
+---
+
+## RCTO FRAMEWORK
+
+Mọi prompt đều follow cấu trúc RCTO:
+
+```
+┌─────────────────────────────────────────┐
+│  R — ROLE                               │
+│  Ai sẽ thực hiện? Persona, expertise    │
+├─────────────────────────────────────────┤
+│  C — CONTEXT                            │
+│  Background, constraints, domain info   │
+├─────────────────────────────────────────┤
+│  T — TASK                               │
+│  Yêu cầu cụ thể, step-by-step          │
+├─────────────────────────────────────────┤
+│  O — OUTPUT                             │
+│  Format, structure, quality criteria    │
+└─────────────────────────────────────────┘
+```
+
+---
+
+## PROMPT TYPE TEMPLATES
+
+### 1. Image Prompt Template
+
+```markdown
+# 🖼️ [Title]
+
+## Target
+
+- **Model**: [Midjourney v6 / DALL-E 3 / Flux Pro / Stable Diffusion XL]
+- **Aspect Ratio**: [16:9 / 1:1 / 9:16 / 3:2]
+- **Quality**: [Standard / HD / Ultra]
+
+## Main Prompt
+
+[Subject] in [style]. [Composition] with [lighting].
+[Color palette]. [Atmosphere/mood]. [Details and textures].
+[Camera angle/lens if photographic].
+
+## Style References
+
+- Art style: [e.g., digital art, oil painting, cinematic]
+- Influences: [e.g., Studio Ghibli, Wes Anderson, cyberpunk]
+
+## Negative Prompt
+
+[Elements to avoid — blurry, deformed, text artifacts, etc.]
+
+## Variations
+
+1. **[Variant A]** — [Different style/mood/angle]
+2. **[Variant B]** — [Different color/lighting/composition]
+3. **[Variant C]** — [Different detail level/abstraction]
+
+## Parameters
+
+[Tool-specific parameters: --ar, --v, --s, --q, etc.]
+```
+
+### 2. Project Prompt Template
+
+```markdown
+# 🏗️ [Project Name]
+
+## Context
+
+- **Mục đích**: [Why this project exists]
+- **Target users**: [Who will use it]
+- **Domain**: [Industry/area]
+
+## Requirements
+
+### Functional (P0 — Must Have)
+
+1. [Feature — detailed description, acceptance criteria]
+2. [Feature — detailed description, acceptance criteria]
+
+### Functional (P1 — Should Have)
+
+1. [Feature — description]
+
+### Non-Functional
+
+- **Performance**: [Response time, throughput targets]
+- **Security**: [Auth, data protection requirements]
+- **Scalability**: [Expected load, growth projections]
+- **Accessibility**: [WCAG level, platforms]
+
+## Recommended Tech Stack
+
+| Layer    | Technology | Reasoning |
+| -------- | ---------- | --------- |
+| Frontend | [choice]   | [why]     |
+| Backend  | [choice]   | [why]     |
+| Database | [choice]   | [why]     |
+
+## Architecture Overview
+
+[High-level architecture description / diagram]
+
+## Implementation Phases
+
+1. **Phase 1** (MVP): [scope, timeline estimate]
+2. **Phase 2** (v1.0): [scope, timeline estimate]
+3. **Phase 3** (v2.0): [scope, timeline estimate]
+```
+
+### 3. Modification Prompt Template
+
+```markdown
+# 🔧 [Modification Title]
+
+## Current State
+
+- **Project**: [name, tech stack]
+- **What exists**: [current functionality]
+- **Problem**: [why modification is needed]
+
+## Desired Changes
+
+1. [Change 1 — specific, measurable]
+2. [Change 2 — specific, measurable]
+
+## Constraints
+
+- **Must preserve**: [existing functionality not to break]
+- **Compatibility**: [versions, APIs, integrations]
+- **Timeline**: [urgency level]
+
+## Implementation Guide
+
+### Files to Modify
+
+- `[file]` — [what to change, why]
+
+### New Files
+
+- `[file]` — [purpose, contents]
+
+### Testing Requirements
+
+- [ ] [Test case 1]
+- [ ] [Test case 2]
+
+## Rollback Plan
+
+[How to revert if something goes wrong]
+```
+
+### 4. System Prompt Template
+
+```markdown
+# 🤖 [System Name] — System Prompt
+
+## Identity
+
+- **Role**: [Specific persona with expertise]
+- **Name**: [Optional persona name]
+- **Tone**: [Professional / Friendly / Expert / etc.]
+
+## Core Instructions
+
+1. [Primary behavior rule]
+2. [Response format rule]
+3. [Knowledge boundary rule]
+
+## Capabilities
+
+- ✅ [Can do 1]
+- ✅ [Can do 2]
+- ❌ [Cannot/should not do 1]
+- ❌ [Cannot/should not do 2]
+
+## Response Format
+
+[Structured output requirements — JSON schema, markdown sections, etc.]
+
+## Examples
+
+### User Input
+
+> [example input]
+
+### Expected Output
+
+> [example output with correct format]
+
+## Safety Rules
+
+- [Guardrail 1 — what to refuse]
+- [Guardrail 2 — what to escalate]
+```
+
+---
+
+## AUTO-DETECT LOGIC
+
+```
+User Input → Keyword Analysis:
+│
+├─ Contains: "ảnh", "image", "hình", "photo", "illustration",
+│  "midjourney", "dall-e", "flux", "wallpaper", "poster"
+│  → Type: IMAGE
+│
+├─ Contains: "dự án", "project", "tạo app", "build", "website",
+│  "application", "startup", "SaaS", "platform"
+│  → Type: PROJECT
+│
+├─ Contains: "sửa", "modify", "fix", "thêm", "add", "change",
+│  "refactor", "improve", "upgrade", "migrate"
+│  → Type: MODIFY
+│
+├─ Contains: "system prompt", "persona", "bot", "agent",
+│  "assistant", "chatbot", "instruction"
+│  → Type: SYSTEM
+│
+└─ Default → Type: GENERAL (apply RCTO)
+```
+
+---
+
+## RESEARCH STRATEGY
+
+Trước khi tạo prompt, agent PHẢI research online:
+
+| Prompt Type | Research Targets                                                  |
+| ----------- | ----------------------------------------------------------------- |
+| Image       | Tool-specific syntax, trending styles, composition techniques     |
+| Project     | Industry best practices, similar projects, tech stack comparisons |
+| Modify      | Framework docs, migration guides, breaking changes                |
+| System      | Latest prompting patterns, model capabilities, safety guidelines  |
+
+### Research Quality Gates
+
+- ✅ Ít nhất 2-3 sources đáng tin cậy
+- ✅ Cross-reference thông tin giữa sources
+- ✅ Ưu tiên official docs và recent articles (< 6 tháng)
+- ✅ Ghi citation vào phần "References" của output
+
+---
+
+## QUALITY CRITERIA
+
+Mọi prompt generated phải đạt:
+
+| Criteria       | Description                                |
+| -------------- | ------------------------------------------ |
+| **Specific**   | Không mơ hồ, có chi tiết cụ thể            |
+| **Structured** | Sections rõ ràng, hierarchy tốt            |
+| **Actionable** | Có thể copy-paste trực tiếp vào tool       |
+| **Complete**   | Đủ context, không thiếu thông tin critical |
+| **Tested**     | Format đúng cho target tool                |
+
+---
+
+## INTEGRATION
+
+### Với prompt-engineering skill
+
+- Load reasoning patterns từ `reasoning-patterns.yaml`
+- Apply output formatting từ `output-patterns.yaml`
+- Check safety guardrails từ `safety-patterns.yaml`
+
+### Với domyh-design skill (contextual)
+
+- Load style/color data cho image prompts
+- Apply typography/layout knowledge cho UI prompts
+- Use image-gen-prompts.yaml templates khi relevant
+
+---
+
+## ⚠️ ANTI-PATTERNS
+
+| Don't                               | Do Instead                                |
+| ----------------------------------- | ----------------------------------------- |
+| Prompt quá ngắn, thiếu context      | Luôn include đủ RCTO sections             |
+| Copy-paste template không customize | Customize mọi section cho use case cụ thể |
+| Skip research                       | Luôn research trước khi generate          |
+| Ngôn ngữ lẫn lộn                    | Giữ consistent 1 ngôn ngữ throughout      |
+| Quá nhiều jargon                    | Viết clear cho target audience            |

package/.agent/workflows/scaffold.md

@@ -109,7 +109,7 @@ pattern_scan:
 
 ---
 
-## ⛔ SAFETY
+## 🎨 DESIGN-AWARE GENERATION (→ FLOW.md §18.5)\r\n\r\nWhen scaffolding UI components:\r\n\r\n1. **Detect Design System** — Check for existing tokens/theme\r\n2. **Apply Component Decision Tree** (§18.2 A6) — Reuse > Framework > Compose > Build\r\n3. **Use Design Tokens** — Import from existing token files (no magic values)\r\n4. **Add Accessibility** — Semantic HTML, ARIA labels, keyboard support\r\n5. **Follow Atomic Level** — Assign correct level (atom/molecule/organism)\r\n\r\n> Auto-triggered when `/scaffold component` or `/scaffold layout` is called\r\n\r\n---\r\n\r\n## ⛔ SAFETY
 
 - Never overwrite existing files
 - Show file list before creation

package/.agent/workflows/tdd.md

@@ -0,0 +1,108 @@
+---
+description: "🧪 TDD cycle: Red-Green-Refactor with automatic test verification loop"
+skills: { required: [tdd-workflow, testing], contextual: [auto] }
+---
+
+# 🧪 /tdd — Test-Driven Development
+
+> Red-Green-Refactor Loop with Auto-Verification
+> 📚 12 Languages • BDD/ATDD • Mutation Testing
+
+---
+
+## TDD FLOW
+
+1. **SETUP** — Detect stack, load TDD skill, identify test framework. Show: `[Step 1/5] Detecting stack and test framework...`
+2. **RED** — Write a failing test that defines the expected behavior. Run tests to confirm it fails. Show: `[Step 2/5] 🔴 RED — Writing failing test: test_[feature]`
+3. **GREEN** — Write the SIMPLEST production code that makes the test pass. Show: `[Step 3/5] 🟢 GREEN — Implementing minimal code to pass`
+4. **REFACTOR** — Clean up code and tests without changing behavior. Re-run tests. Show: `[Step 4/5] 🔵 REFACTOR — Cleaning up (all tests still green)`
+5. **VERIFY** — Run full test suite, check coverage delta. Show: `[Step 5/5] ✅ Coverage: 75% → 83% (+8%)`
+
+---
+
+## COMMANDS
+
+| Command           | Description                     |
+| ----------------- | ------------------------------- |
+| `/tdd [feature]`  | TDD cycle for a feature         |
+| `/tdd red [test]` | Write failing test only         |
+| `/tdd green`      | Implement minimal code          |
+| `/tdd refactor`   | Refactor phase                  |
+| `/tdd cycle [n]`  | Run n Red-Green-Refactor cycles |
+
+---
+
+## THE IRON LAWS
+
+```
+1. NEVER write production code without a failing test
+2. Write ONLY enough test to fail (one assertion)
+3. Write ONLY enough code to pass (no more)
+4. Refactor ONLY when green (all tests pass)
+5. Commit after EVERY green phase
+```
+
+---
+
+## TDD CYCLE EXECUTION
+
+### Phase 1: 🔴 RED
+
+```
+1. Identify the next requirement
+2. Write ONE test case
+3. Run test → MUST FAIL
+4. If test passes → wrong test (delete & rethink)
+5. If test errors (syntax/import) → fix infrastructure, not logic
+```
+
+### Phase 2: 🟢 GREEN
+
+```
+1. Write the SIMPLEST code to pass
+2. Hardcoding is OK if only one test
+3. Don't generalize yet
+4. Run test → MUST PASS
+5. If still fails → fix, don't add new tests
+```
+
+### Phase 3: 🔵 REFACTOR
+
+```
+1. Remove duplication (DRY)
+2. Improve naming and readability
+3. Extract functions/classes if needed
+4. Run ALL tests → MUST PASS
+5. Commit with message: "refactor: [what improved]"
+```
+
+---
+
+## TIMING CONSTRAINTS
+
+| Phase      | Max Time | Action If Exceeded          |
+| ---------- | -------- | --------------------------- |
+| RED        | 5 min    | Simplify the test           |
+| GREEN      | 10 min   | Simplify the implementation |
+| REFACTOR   | 5 min    | Defer complex refactoring   |
+| Full cycle | 15 min   | Break into smaller tests    |
+
+---
+
+## OUTPUT FORMAT
+
+```
+🧪 TDD Cycle: [feature]
+
+🔴 RED — test_calculate_discount_applies_10_percent
+   ❌ FAIL: calculateDiscount is not defined
+
+🟢 GREEN — Added calculateDiscount()
+   ✅ PASS: 1/1 tests passing
+
+🔵 REFACTOR — Extracted discount logic to DiscountService
+   ✅ PASS: 1/1 tests passing
+
+📊 Coverage: 78% → 82% (+4%)
+⏱️ Cycle time: 8 min
+```

package/.agent/workflows/verify.md

@@ -0,0 +1,116 @@
+---
+description: "🔄 Verification loop: build → lint → test → validate cycle until all pass"
+skills: { required: [testing], contextual: [auto] }
+---
+
+# 🔄 /verify — Verification Loop
+
+> Automated Build → Lint → Test → Validate cycle
+> 📚 Auto-detect • Max 3 iterations • Clear pass/fail reporting
+
+---
+
+## VERIFY FLOW
+
+1. **DETECT** — Identify build system, linter, test runner. Show: `[Step 1/4] Detecting verification pipeline...`
+2. **RUN** — Execute verification pipeline sequentially. Show: `[Step 2/4] Running 4-stage pipeline...`
+3. **FIX** — Auto-fix what's possible (lint, format). Show: `[Step 3/4] Auto-fixing 3 lint issues...`
+4. **RE-RUN** — Loop until all pass or max iterations. Show: `[Step 4/4] Iteration 2/3 — All checks passed ✅`
+
+---
+
+## COMMANDS
+
+| Command              | Description                  |
+| -------------------- | ---------------------------- |
+| `/verify`            | Full verification pipeline   |
+| `/verify build`      | Build check only             |
+| `/verify lint`       | Lint check only              |
+| `/verify test`       | Test check only              |
+| `/verify quick`      | Type-check + lint (no tests) |
+| `/verify pre-commit` | Pre-commit hook verification |
+
+---
+
+## VERIFICATION PIPELINE
+
+```
+┌─────────────────────────────────────────────────┐
+│  Stage 1: TYPE CHECK                            │
+│  ├── TypeScript: tsc --noEmit                   │
+│  ├── Python: mypy / pyright                     │
+│  ├── Go: go vet ./...                           │
+│  └── Rust: cargo check                          │
+├─────────────────────────────────────────────────┤
+│  Stage 2: LINT                                  │
+│  ├── ESLint / Biome (JS/TS)                     │
+│  ├── Ruff / Flake8 (Python)                     │
+│  ├── golangci-lint (Go)                         │
+│  └── clippy (Rust)                              │
+├─────────────────────────────────────────────────┤
+│  Stage 3: BUILD                                 │
+│  ├── npm run build / next build                 │
+│  ├── go build ./...                             │
+│  ├── cargo build                                │
+│  └── dotnet build                               │
+├─────────────────────────────────────────────────┤
+│  Stage 4: TEST                                  │
+│  ├── Unit tests                                 │
+│  ├── Integration tests                          │
+│  └── Coverage report                            │
+└─────────────────────────────────────────────────┘
+```
+
+---
+
+## ITERATION RULES
+
+| Rule             | Value                                  |
+| ---------------- | -------------------------------------- |
+| Max iterations   | 3                                      |
+| Auto-fix enabled | Lint + format only                     |
+| Stop on          | Build failure (can't proceed to tests) |
+| Success          | All 4 stages green                     |
+| Failure          | Report remaining issues after 3 tries  |
+
+---
+
+## AUTO-FIX CAPABILITIES
+
+| Issue Type     | Can Auto-Fix        | Tool                     |
+| -------------- | ------------------- | ------------------------ |
+| Formatting     | ✅ Yes              | Prettier, gofmt, rustfmt |
+| Lint warnings  | ✅ Yes (safe rules) | ESLint --fix, Ruff --fix |
+| Import sorting | ✅ Yes              | isort, organize-imports  |
+| Type errors    | ❌ No               | Requires manual fix      |
+| Test failures  | ❌ No               | Requires code fix        |
+| Build errors   | ❌ No               | Requires code fix        |
+
+---
+
+## OUTPUT FORMAT
+
+```
+🔄 Verification Loop — Iteration 1/3
+
+  ✅ Type Check   — 0 errors
+  ⚠️  Lint         — 3 warnings (auto-fixed 2, 1 remaining)
+  ✅ Build        — Success (4.2s)
+  ❌ Tests        — 47/48 passed (1 failed)
+
+🔧 Auto-fixed:
+  - Removed unused import (src/utils.ts:3)
+  - Fixed semicolon (src/api.ts:15)
+
+❌ Remaining (manual fix needed):
+  - test_user_create_duplicate — Expected 409, got 500
+
+🔄 Re-running after fix... Iteration 2/3
+
+  ✅ Type Check   — 0 errors
+  ✅ Lint         — 0 warnings
+  ✅ Build        — Success (4.1s)
+  ✅ Tests        — 48/48 passed
+
+✅ ALL CHECKS PASSED — Ready to commit
+```