intelligent-do

# Intelligent Do

## Purpose

Comprehensive intelligent task execution that automatically handles all scenarios: new projects, existing codebases, simple tasks, complex requirements, first-time work, and returning workflows - all with Serena MCP as the persistent context backend.

**Core Innovation**: One command that adapts to any scenario without configuration, learns from every execution, and gets faster on return visits.

---

## Workflow

### Step 1: Context Detection Using Serena

**Check if project exists in Serena memory**:

1. Determine project ID from current working directory:
   - Get current path: Use Bash tool to run `pwd`
   - Extract project name: Last component of path
   - Sanitize for memory key: Replace special characters with underscores

2. Check Serena for existing project memory:
   - Use Serena tool: `list_memories()`
   - Search for key: `"shannon_project_{project_id}"`
   - If key found → RETURNING_WORKFLOW
   - If key not found → FIRST_TIME_WORKFLOW

**Duration**: < 1 second

---

### Step 2a: FIRST_TIME_WORKFLOW

**For projects not yet in Serena**:

#### Sub-Step 1: Determine Project Type

Count files in current directory to determine if new or existing project:

```bash
# Use Bash tool
find . -type f \( -name "*.py" -o -name "*.js" -o -name "*.tsx" -o -name "*.java" -o -name "*.go" \) | wc -l
```

- If count < 3: NEW_PROJECT (greenfield)
- If count >= 3: EXISTING_PROJECT (has codebase)

#### Sub-Step 2: NEW_PROJECT Path

For greenfield projects (empty or minimal files):

1. **Assess Task Complexity**:
   - Count words in task description
   - Count requirements (lines starting with -)
   - If task has 20+ words OR 3+ requirements → Complex task
   - If task mentions "system", "platform", "integrate" → Complex task

2. **For Complex Tasks - Run Spec Analysis**:
   ```
   Invoke sub-skill:
   @skill spec-analysis
   Specification: {task_description}
   ```
   - This will analyze complexity (8D score)
   - Create phase plan
   - Save resul