feature-dev-enhancement

# Feature-Dev Enhancement

This Skill enhances the feature-dev plugin workflow by applying PROMPTCONVERTER methodology to structure feature requests into unambiguous pseudo-code directives.

## Memory Integration (START - MANDATORY)

Before enhancing feature-dev workflows, load session memory:

```
# Step 1: Create memory directory (permission-free)
Bash(command="mkdir -p .claude/pseudo-code-prompting")

# Step 2: Load memory files (permission-free)
Read(file_path=".claude/pseudo-code-prompting/patterns.md")
```

**Memory is used for**:
- Check patterns.md for feature-specific patterns (OAuth, caching, etc.)
- Apply learned structuring patterns from previous feature requests
- Ensure consistency with previously implemented features

## Instructions

When working with feature-dev requests, apply structuring at each phase:

### Phase 1: Discovery (Structurize Input)
Convert the user's `/feature-dev` request into structured pseudo-code:
- Extract the core feature request
- Identify all explicit requirements
- Flag implicit constraints
- Output function-like pseudo-code

**Example:**
- User: `/feature-dev Add OAuth support for Google and GitHub`
- Structured: `implement_oauth(providers=["google", "github"], preserve_existing_auth=true)`

### Phase 2: Exploration (Use Structured Directives)
The structured pseudo-code becomes search and research directives:
- `providers=["google", "github"]` → Search for OAuth implementations for these specific providers
- `preserve_existing_auth=true` → Find patterns that maintain backward compatibility
- Agents receive explicit, unambiguous search targets

### Phase 3: Questions (Extract from Parameters)
Clarification questions are derived from pseudo-code parameters:
- Missing parameters indicate ambiguities that need clarification
- Questions become precise and actionable
- Example: If `ttl` parameter is missing from caching request, ask specifically about cache duration

### Phase 4: Architecture (Build from Requirements)
Design opti