An advanced AI coding agent skill that generates complex, formula-heavy spreadsheets and financial models using Python-powered automation.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install sheet-cog
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install sheet-cog using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Sheet Cog is a specialized skill within the Openclaw Skills ecosystem designed to function as a professional spreadsheet programmer rather than a simple template filler. It leverages the same engineering intelligence that builds AI platforms to construct intricate workbooks, complete with complex Python-driven data manipulation, pivot tables, and financial projections.
By utilizing this skill, developers and analysts can transform natural language prompts into fully functional Excel/XLSX files or interactive HTML calculators. It integrates seamlessly with existing workflows to provide engineering-grade accuracy for spreadsheets that require deep logic and interconnected data structures.
To get started with Sheet Cog, you must first install the cellcog dependency from the Openclaw Skills directory:
clawhub install cellcog
Once installed, you can trigger spreadsheet generation via the SDK using this pattern:
# Initialize the agent to build your spreadsheet
result = client.create_chat(
prompt="Create a 3-year SaaS financial model with MRR growth and churn charts",
notify_session_key="agent:main:main",
task_label="spreadsheet-task",
chat_mode="agent"
)
Sheet Cog structures its output to ensure compatibility with major spreadsheet software. The data organization follows this taxonomy:
| Component | Metadata/Description |
|---|---|
| File Formats | Supports XLSX for Excel/Google Sheets and Interactive HTML for web views. |
| Sheet Structure | Organizes data into logical tabs (e.g., Assumptions, Data, Dashboard). |
| Logic Layer | Implements standard formulas (VLOOKUP, IF, SUM) and Named Ranges. |
| Visual Layer | Includes embedded charts and conditional formatting rules. |
| Validation | Uses data validation for dropdowns and input restrictions. |
Loading
A sophisticated image generation skill that brings Google DeepMind's Nano Banana model to AI agents for photorealistic creation and character consistency.

A secure, extraction-only skill for processing forwarded emails through a dedicated IMAP inbox with zero automatic background activity.

A unified benchmarking and implementation suite for eight leading vector database backends using a common interface.

A Notion-to-Twitter automation bridge that schedules and posts tweets directly from a content calendar.

An automated trading signal generator that analyzes technical indicators and broadcasts alerts to communication channels.

A lightweight, direct integration for managing Todoist tasks, projects, and sections using standard shell tools and API endpoints.








































