think-cogComplex ideas need iteration, not conversation. Think → Do → Review → Repeat. CellCog completes the full loop — brainstorming, reasoning, problem-solving, strategic thinking, then executing across every modality: research, documents, visuals, data, prototypes. Like having an Alfred who doesn't just advise — he builds.
Install via ClawdBot CLI:
clawdbot install nitishgargiitd/think-cogComplex ideas need iteration, not conversation. Think → Do → Review → Repeat.
CellCog is the thinking partner that completes the full loop — reasons with you, then executes across every modality: research, documents, visuals, data, prototypes. Review real output, refine your thinking, iterate on substance. Like having an Alfred who doesn't just advise — he builds.
For problems where you don't know the answer upfront and the solution emerges through doing, not just discussing.
This skill requires the cellcog skill for SDK setup and API calls.
clawhub install cellcogRead the cellcog skill first for SDK setup. This skill shows you what's possible.
Most CellCog skills follow a pattern: you know what you want → CellCog delivers it.
But some problems don't work that way:
Think-cog is your worker agent for intellectual exploration. You're the manager agent providing direction. CellCog thinks and works alongside you.
Unlike fire-and-forget tasks, think-cog is conversational by design:
# Start a thinking session
result = client.create_chat(
prompt="I'm trying to figure out the best architecture for a real-time multiplayer game...",
notify_session_key="agent:main:main",
task_label="architecture-thinking",
chat_mode="agent" # Agent mode for iterative dialogue
)
# CellCog will think through the problem and may ask clarifying questions
# You respond, building on the ideas
# The solution emerges through dialogueThis is not fire-and-forget. Think-cog expects back-and-forth conversation. Each exchange deepens understanding.
When you're weighing tradeoffs:
"I'm building a notification system that needs to handle 10M daily users. I'm torn between:
1. WebSocket connections for all users
2. Server-sent events with polling fallback
3. Push notifications only
Help me think through the tradeoffs. My team is small (3 engineers) and we're on AWS."
When the path forward isn't clear:
"My SaaS is growing but I'm not sure whether to:
- Focus on enterprise sales (fewer customers, bigger deals)
- Double down on self-serve (more customers, smaller ARPU)
Current metrics: 500 customers, $50 ARPU, 2 enterprise deals in pipeline worth $50K each.
Let's think through this together."
When you're exploring possibilities:
"I want to create a video campaign for my coffee brand but I'm not sure what angle to take. The brand is:
- Specialty single-origin coffee
- Direct trade with farmers
- Premium pricing ($25/bag)
Target audience is 25-40 professionals who care about quality.
Help me brainstorm directions before we commit to production."
When you're stuck:
"My machine learning model keeps overfitting despite:
- Dropout layers
- Data augmentation
- Early stopping
Here's my architecture: [details]
Let's debug this together. What am I missing?"
When you need structured thinking:
"I have three job offers and I'm paralyzed by the decision:
- Startup (lower pay, more equity, more risk)
- Big tech (great pay, slower growth, stable)
- Mid-stage scaleup (balanced, interesting problem)
Help me build a framework to think through this."
"It's hard to know what's actually possible before you try it."
This is CellCog's core insight. Complex problems rarely have obvious solutions. The best work happens when two smart entities—you and CellCog—exchange ideas, challenge assumptions, and discover answers together.
Think of it as pair programming for thinking:
Use chat_mode="agent" for think-cog sessions.
Why not agent team? Agent team is designed for autonomous deep work with multiple internal passes. Think-cog is about collaborative iteration WITH you. Agent mode keeps the conversation flowing naturally.
The magic happens in the back-and-forth, not in autonomous processing.
| Skill | Pattern | You Know the Output? |
|-------|---------|---------------------|
| research-cog | Fire-and-forget | Yes - "Give me research on X" |
| video-cog | Fire-and-forget | Yes - "Create a video about X" |
| docs-cog | Fire-and-forget | Yes - "Create a document for X" |
| think-cog | Conversational | No - "Help me figure out X" |
Think-cog is for when you're in discovery mode. Other skills are for when you're in execution mode.
You:
"I'm building a two-sided marketplace for freelance designers. I'm stuck on the chicken-and-egg problem—how do I get designers without clients, and clients without designers?"
CellCog:
"This is the classic marketplace cold-start problem. Let me think through some approaches with you...
Option 1: Supply-first (designers)
- Pros: Designers are easier to acquire, content creates SEO value
- Cons: They'll leave if no jobs come
Option 2: Demand-first (clients)
- Pros: Revenue from day one, can manually fulfill initially
- Cons: Harder to acquire, need to deliver quality
Option 3: Constrain the market
- Focus on ONE design type (e.g., logo design only)
- Build liquidity in a narrow niche before expanding
What's your current thinking? And what resources do you have to invest in early growth?"
You:
"I have about $20K for initial marketing and can do some manual matching myself. The constrained market approach is interesting—I was thinking of going broad."
CellCog:
"That $20K + your time is actually a meaningful advantage. Let me build on the constrained market idea...
What if you started with:
- Niche: Startup logo design only
- Supply: Recruit 20-30 designers who specialize in startup branding (curated, not open signup)
- Demand: Target YC companies, indie hackers, ProductHunt launchers
The manual matching you'd do becomes a feature, not a bug—'curated matches by founders who understand startups.'
This gives you:
- Clear positioning
- Easier SEO/content ('startup logo design' vs 'design marketplace')
- Higher willingness to pay from funded startups
- Story for press/ProductHunt
Thoughts? Or should we explore other niches?"
The conversation continues, ideas refine, and eventually you arrive at a clear strategy to execute.
Generated Mar 1, 2026
When developers need to evaluate trade-offs for system designs, such as choosing between WebSocket connections, server-sent events, or push notifications for a notification system handling 10M daily users. This involves considering team size, cloud infrastructure like AWS, and scalability constraints.
For SaaS founders deciding between enterprise sales and self-serve models, analyzing metrics like customer count, ARPU, and pipeline deals. This helps in crafting growth strategies aligned with resource limitations and market opportunities.
When marketing teams explore video campaign angles for premium brands, such as a coffee company with direct trade and specialty products. It involves targeting professionals aged 25-40 and iterating on messaging before production.
For data scientists stuck with overfitting models despite techniques like dropout and early stopping. This scenario involves collaborative analysis of architecture details to identify missing elements and refine approaches.
Offering think-cog as part of a premium AI agent package for businesses, charging monthly or annual fees based on usage tiers. Revenue is generated from enterprises and startups needing iterative problem-solving tools.
Bundling think-cog with consulting services for architecture, strategy, or creative projects, where clients pay for collaborative sessions. Revenue comes from project-based fees and ongoing support contracts.
Licensing think-cog as an SDK or API for developers to embed in their applications, with pricing based on API calls or user seats. Revenue is driven by integration into third-party software and tools.
💬 Integration Tip
Ensure the cellcog skill is installed first for SDK setup, and use chat_mode='agent' to enable iterative dialogue rather than autonomous processing.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...
Collaborative thinking partner for exploring complex problems through questioning
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
根据用户的功能需求，完成与 VeADK 相关的功能。
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.