cellcog

Generate coordinated multi-modal outputs from multiple attached files in one workflow.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/dingdyan/openclaw-workspace-v2 --skill cellcog-dingdyan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cellcog
Source: https://github.com/dingdyan/openclaw-workspace-v2/tree/main/skills/cellcog
Command: npx skills add https://github.com/dingdyan/openclaw-workspace-v2 --skill cellcog-dingdyan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It streamlines complex agent workflows by letting you request many different deliverables from one prompt, without manual tool chaining or orchestration work.

Core Features & Use Cases

  • Any input → any output in one request: Generate coordinated multi-modal results (text, PDFs, spreadsheets, dashboards, images, audio, video, and more) while keeping insights consistent across artifacts.
  • Multi-file analysis with one prompt: Reference multiple local files at once using SHOW_FILE tags to drive a unified analysis and set of outputs.
  • Session-based iterative refinement: Continue and improve outputs in follow-up messages while preserving chat context, files, and artifacts.
  • Use case: Provide earnings PDFs, competitor docs, spreadsheets, and customer audio to produce a comprehensive market positioning package including a report plus interactive dashboard and presentations.

Quick Start

Ask for a single set of deliverables from one prompt while attaching files using SHOW_FILE tags.

Frequently Asked Questions about cellcog

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate multiple document outputs from a single prompt?

To analyze multiple local files in one prompt, use SHOW_FILE tags to attach your documents, enabling a unified agent workflow that produces coordinated multi-modal deliverables from a single request.

Can I create multi-modal deliverables from multiple attached files at once?

Yes, you can create multi-modal deliverables from multiple attached files by using SHOW_FILE tags, enabling a unified agent workflow to generate coordinated text, spreadsheets, dashboards, and media outputs simultaneously.

Do I need an API key to automate document generation workflows?

Yes, automating document generation workflows requires an authenticated API usage via the CELLCOG_API_KEY environment variable and a YAML-defined skill entry to properly execute multi-modal agent workflows.

What is the best way to maintain consistency across generated reports and dashboards?

The best way to maintain consistency across generated reports and dashboards is to request any-to-any outputs in a single agent workflow, ensuring insights remain coordinated across all multi-modal artifacts.

How does session-based iterative refinement work for multi-file analysis?

Session-based iterative refinement allows you to continue and improve outputs in follow-up messages while preserving chat context, attached files, and previously generated artifacts for multi-file analysis.

Can I produce a market positioning package from earnings PDFs and customer audio?

Yes, you can produce a comprehensive market positioning package by attaching earnings PDFs, competitor docs, spreadsheets, and customer audio to generate a report, interactive dashboard, and presentations in one workflow.