doing-a-simple-two-stage-fanout

Orchestrate two-stage analysis of large data sets with Worker, Critic, and Summarizer subagents.

2|Updated Feb 16, 2026

Search Tags:#parallel processing #data processing #text analysis #failure recovery #analysis workflow

Ready to run

npx skills add https://github.com/vivshaw/nous --skill doing-a-simple-two-stage-fanout-vivshaw

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: doing-a-simple-two-stage-fanout
Source: https://github.com/vivshaw/nous/tree/main/plugins/morphe/skills/doing-a-simple-two-stage-fanout
Command: npx skills add https://github.com/vivshaw/nous --skill doing-a-simple-two-stage-fanout-vivshaw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

The Skill addresses the challenge of analyzing large text, code, or data sets that exceed a single agent's context capacity by orchestrating parallel processing across Worker, Critic, and Summarizer subagents.

Core Features & Use Cases

Parallel Worker Subagents: Process data segments in parallel for efficient handling of large volumes.
Critic Review Subagents: Provide comprehensive review with redundancy, catching gaps and inconsistencies.
Summarizer Subagent: Synthesize all reviews to produce a final comprehensive analysis report.
Task Tracking and Failure Recovery: Ensures reliability with built-in mechanisms for tracking progress and recovering from failures.

Quick Start

To analyze a corpus, activate the Skill and follow the steps to input your data and define the analysis parameters.

Frequently Asked Questions about doing-a-simple-two-stage-fanout

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

FAQPage Schema

How do I analyze large data sets that exceed a single agent's context capacity?▼

Analyzing large data sets that exceed a single context capacity requires distributing the corpus to parallel Worker subagents, reviewing with Critic subagents, and synthesizing with a Summarizer for a final report.

What is the best way to process large text corpora in parallel for analysis?▼

Processing large text corpora in parallel is best handled by a two-stage fanout workflow that distributes data segments to Workers, has Critics review the outputs, and uses a Summarizer to synthesize the final analysis.

Do I need specific computation resources to run parallel data processing workflows?▼

Yes, you need specific computation resources to run parallel data processing workflows because the system orchestrates multiple Worker, Critic, and Summarizer subagents simultaneously to handle large volumes of data.

How does failure recovery work in parallel text analysis workflows?▼

Failure recovery in parallel text analysis workflows works through built-in task tracking mechanisms that monitor the progress of distributed Worker and Critic subagents, ensuring reliable execution and resuming incomplete segments.

Can I use a two-stage fanout workflow for code analysis?▼

Yes, you can use a two-stage fanout workflow for code analysis because the parallel processing architecture supports large text, code, or data sets by distributing segments to subagents for comprehensive review.

What are the limitations of using parallel subagents for large scale data processing?▼

Limitations of using parallel subagents for large scale data processing include the requirement for sufficient computation resources to handle concurrent processes and dependencies on task tracking for failure recovery.