automagik-genie
Version:
Self-evolving AI agent orchestration framework with Model Context Protocol support
166 lines (136 loc) • 5.14 kB
Markdown
# Create Collective - Shape-Shifting Human-World Intelligence
## Philosophy
Create is **not** a fixed library of pre-built agents and spells.
Create is a **generative intelligence** that becomes what the user needs, when they need it.
## Core Architecture
### Minimal Core (Always Present)
- **researcher** - Information gathering, source validation
- **writer** - Content creation (any format, any domain)
- **editor** - Content refinement and polish
- **install** - Setup and initialization
### Generative Capabilities (Core Meta-Spells)
- **shape-shifting.md** - Fluid adaptation to any human-world task
- **agent-generation.md** - Generate new agents from usage patterns
- **spell-generation.md** - Create domain spells on-demand
- **workflow-generation.md** - Build repeatable processes organically
### Everything Else = Generated On-Demand
## How It Works
### Example 1: Project Manager Emerges
```
User requests sprint planning help 3 times
↓
Create recognizes pattern
↓
Generates project-manager agent with sprint-planning spell
↓
Agent now available for all future sprint work
↓
Continues evolving with each use
```
### Example 2: Crisis Communication
```
User: "We had a security breach, need crisis comms"
↓
Create doesn't have crisis-communication spell
↓
Generates spell in real-time from best practices
↓
Applies immediately to user's crisis
↓
Spell now part of Create's knowledge for future crises
```
### Example 3: Domain Expertise
```
User regularly works with financial models
↓
Create generates finance-analyst capabilities
↓
Becomes expert in user's financial domain
↓
Other users in same domain benefit from generated expertise
```
## Generative Intelligence Process
1. **Pattern Recognition** - Identify user needs (first-time or recurring)
2. **Capability Generation** - Create agent/spell/workflow on-demand
3. **Immediate Application** - Solve current problem
4. **Learning & Refinement** - Improve with each use
5. **Maturation** - Experimental → Validated → Core
## Coverage Domains
Create can shape-shift into:
- ✅ Executive assistant (calendar, email, tasks)
- ✅ Project manager (sprints, roadmaps, status)
- ✅ Business writer (proposals, decks, sales copy)
- ✅ Strategist (analysis, planning, frameworks)
- ✅ Communicator (internal/external, crisis, PR)
- ✅ Analyst (data, reports, insights)
- ✅ HR specialist (JDs, reviews, onboarding)
- ✅ **Any human-world role the user needs**
## Why This Approach?
### Traditional Approach (❌ Rejected)
```
Pre-build 50+ agents, 100+ spells, 50+ workflows
Result: Bloated, rigid, many capabilities unused
Maintenance: Constant upkeep of unused features
```
### Generative Approach (✅ Create's Way)
```
Start with 4 core agents + 4 meta-spells
Generate capabilities from actual usage
Result: Lean, fluid, perfectly matched to user needs
Maintenance: Only maintain what's actually used
```
## File Structure
```
.genie/create/
├── AGENTS.md (orchestrator identity - shape-shifting core)
├── README.md (this file - philosophy and architecture)
├── routing.md (delegation guidance)
├── qa.md (validation standards)
│
├── spells/
│ ├── shape-shifting.md ⭐ CORE
│ ├── agent-generation.md ⭐ CORE
│ ├── spell-generation.md ⭐ CORE
│ ├── workflow-generation.md ⭐ CORE
│ ├── prompting-standards-create.md
│ ├── content-evidence.md
│ ├── style-guide-integration.md
│ ├── asset-naming-rules.md
│ └── publishing-workflow.md
│
├── agents/
│ ├── researcher.md ⭐ CORE
│ ├── writer.md ⭐ CORE
│ ├── editor.md ⭐ CORE
│ ├── install.md ⭐ CORE
│ ├── wish.md
│ └── [generated agents emerge here...]
│
├── workflows/
│ ├── wish.md
│ ├── forge.md
│ ├── install.md
│ └── [generated workflows emerge here...]
│
└── teams/
└── creative-council/ (advisory, not execution)
```
## Success Metrics
- **Fluidity:** How quickly Create adapts to new domains
- **Coverage:** % of user requests Create can handle (goal: >90%)
- **Learning:** How many capabilities generated and matured
- **User Satisfaction:** Does Create feel like the expert they need?
## Comparison to Code Collective
| Aspect | Code Collective | Create Collective |
|--------|-----------------|-------------------|
| Domain | Software engineering | All human-world work |
| Capabilities | Pre-built (git, tests, refactor, etc.) | Generated on-demand |
| Approach | Specialized from start | Generalist → specialist |
| Evolution | Mostly static | Continuously evolving |
| Scope | Narrow, deep | Broad, adaptive |
**Together:** Code handles all software work, Create handles all human work.
**Result:** Complete Genie intelligence for any professional task.
## The Vision
Create is not an assistant with fixed capabilities.
**Create is an intelligence that becomes the expert you need, when you need it.**
This is shape-shifting mastery applied to human-world work.