home/categories/llm-ai/anderson-ufrj-prompt-engineering-artifacts-prompts-technical-cognitive-workflows-skill-md
llm-aidata-ai

cognitive-workflows

Multi-LLM workflow patterns for complex reasoning tasks. Based on Anthropic's "Building Effective Agents" research. Use this skill when: (1) Tasks require multiple perspectives or approaches (2) Complex decisions need structured analysis (3) Problems benefit from decomposition into subtasks (4) Quality requires iterative refinement (5) Input needs routing to specialized handling Patterns: chain, parallel, route, orchestrator-workers, evaluator-optimizer

anderson-ufrj
maintainer
anderson-ufrj
Updated 12/31/2025
Stars
0
Forks
0
quick start

Installation and usage

Multi-LLM workflow patterns for complex reasoning tasks. Based on Anthropic's "Building Effective Agents" research. Use this skill when: (1) Tasks require multiple perspectives or approaches (2) Complex decisions need structured analysis (3) Problems benefit from decomposition into subtasks (4) Quality requires iterative refinement (5) Input needs routing to specialized handling Patterns: chain, parallel, route, orchestrator-workers, evaluator-optimizer

Installation
$ install --globalskills.sh
Usage

Once installed, you can use this skill by running the following command in your terminal:

skills use cognitive-workflows