code-quality

# Code Quality Skill

## 🚨 MANDATORY 6-PHASE WORKFLOW

```
PHASE 1: Exploration (explore-codebase) → BLOCKER
PHASE 2: Documentation (research-expert) → BLOCKER
PHASE 3: Impact Analysis (Grep usages) → BLOCKER
PHASE 4: Error Detection (linters)
PHASE 5: Precision Correction (with docs + impact)
PHASE 6: Verification (re-run linters, tests)
```

**CRITICAL**: Phases 1-3 are BLOCKERS. Never skip them.

---

## PHASE 1: Architecture Exploration

**Launch explore-codebase agent FIRST**:
```
> Use Task tool with subagent_type="explore-codebase"
```

**Gather**:
1. Programming language(s) detected
2. Existing linter configs (.eslintrc, .prettierrc, pyproject.toml)
3. Package managers and installed linters
4. Project structure and conventions
5. Framework versions (package.json, go.mod, Cargo.toml)
6. Architecture patterns (Clean, Hexagonal, MVC)
7. State management (Zustand, Redux, Context)
8. Interface/types directories location

---

## PHASE 2: Documentation Research

**Launch research-expert agent**:
```
> Use Task tool with subagent_type="research-expert"
> Request: Verify [library/framework] documentation for [error type]
> Request: Find [language] best practices for [specific issue]
```

**Request for each error**:
- Official API documentation
- Current syntax and deprecations
- Best practices for error patterns
- Version-specific breaking changes
- Security advisories
- Language-specific SOLID patterns

---

## PHASE 3: Impact Analysis

**For EACH element to modify**:

### Step 1: Search Usages
```bash
# TypeScript/JavaScript
grep -r "functionName" --include="*.{ts,tsx,js,jsx}"

# Python
grep -r "function_name" --include="*.py"

# Go
grep -r "FunctionName" --include="*.go"
```

### Step 2: Risk Assessment
| Risk | Criteria | Action |
|------|----------|--------|
| 🟢 LOW | Internal, 0-1 usages | Proceed |
| 🟡 MEDIUM | 2-5 usages, compatible | Proceed with care |
| 🔴 HIGH | 5+ usages OR breaking | Flag to user FIRST |

### Step 3: Document Impact
```markdown
| El