--- name: think-cog description: "Collaborative thinking and iterative problem-solving. Brainstorm, evaluate strategies, then execute. Use when the task requires back-and-forth deliberation before delivery. Conversational — use send_message() for dialogue. Powered by CellCog." metadata: openclaw: emoji: "💭" os: [darwin, linux, windows] author: CellCog homepage: https://cellcog.ai dependencies: [cellcog] ---

Think Cog - Collaborative Thinking Partner

Brainstorm, reason through complex problems, evaluate strategies, then execute across all modalities.

---

Prerequisites

This skill requires the cellcog skill for SDK setup and API calls.

clawhub install cellcog

Read the cellcog skill first for SDK setup. This skill shows you what's possible.

OpenClaw agents (fire-and-forget — recommended for long tasks):

result = client.create_chat(
    prompt="[your task prompt]",
    notify_session_key="agent:main:main",  # OpenClaw only
    task_label="my-task",
    chat_mode="agent",  # See cellcog skill for all modes
)

All other agents (blocks until done):

result = client.create_chat(
    prompt="[your task prompt]",
    task_label="my-task",
    chat_mode="agent",
)

See the cellcog mothership skill for complete SDK API reference — delivery modes, timeouts, file handling, and more.

---

What CellCog Has Internally

1. Deep Reasoning Engine — Multi-step deliberation with self-review and iteration.
2. All Modalities — After thinking, CellCog can execute across research, documents, images, video, audio, dashboards, code — everything.
3. Conversational Threading — Designed for back-and-forth dialogue, not fire-and-forget.

---

How Think-Cog Works

Think-cog is conversational by design. Use send_message() for iterative dialogue:

1. Present a problem or challenge
2. CellCog thinks through it, proposes approaches
3. You refine, redirect, or approve
4. CellCog executes the agreed approach across any modality

---

What You Can Use It For

• Complex strategic decisions
• Brainstorming and creative ideation
• Problem-solving that requires exploration before execution
• Any task where iterative refinement produces better outcomes

---

Chat Mode

Use chat_mode="agent" — think-cog is conversational, use send_message() for back-and-forth.

---

Related Skills

• research-cog — When deep research is needed before or during thinking