Any to Any AI sub-agent. Generate images, videos, PDFs, presentations, research reports, music, spreadsheets, 3D models, memes, diagrams, prototypes, game assets, stickers, and more — from natural language prompts. Any input, any deliverable.
Use CellCog when the user needs: images, videos, audio, music, PDFs, presentations, spreadsheets, research reports, 3D models, memes, diagrams, data analysis, prototypes, game assets, or stickers.
Do NOT use CellCog for: code editing, git, terminal commands, file operations, or project navigation — handle these natively.
If the CellCog Python SDK is not installed, run `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool) to install and authenticate.
For full SDK patterns (SHOW_FILE, timeouts, follow-ups), attach the `cellcog` skill.
Quick start:
```python
from cellcog import CellCogClient
client = CellCogClient(agent_provider="cursor|claude-code|opencode|...")
result = client.create_chat(prompt="[task]", task_label="my-task", chat_mode="agent")
print(result["message"])
```