deepscan

Spawn eight parallel agents to analyze a project and produce AGENT_NOTES.md.

27|2|Updated Jan 15, 2024
One-click install
npx skills add https://github.com/erfanzar/Xerxes-Agents --skill deepscan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deepscan
Source: https://github.com/erfanzar/Xerxes-Agents/tree/main/src/python/xerxes/skills/deepscan
Command: npx skills add https://github.com/erfanzar/Xerxes-Agents --skill deepscan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

DeepScan addresses the need for rapid, comprehensive project analysis by coordinating a parallel swarm of eight specialized agents that generate a single, detailed report at tmp-files/AGENT_NOTES.md.

Core Features & Use Cases

  • Spawns eight agents in parallel to analyze project structure, technology stack, architecture, configuration, documentation, and security.
  • Produces a consolidated AGENT_NOTES.md report in tmp-files/ for quick decision making.
  • Ideal for onboarding, architecture reviews, and audits across medium to large codebases.

Quick Start

Spawn all eight agents in parallel to produce tmp-files/AGENT_NOTES.md for the current project.

Frequently Asked Questions about deepscan

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

FAQPage Schema
How do I analyze a codebase for architecture and security findings quickly?

To analyze a codebase quickly, spawn a parallel swarm of eight specialized agents to inspect project structure, tech stack, architecture, configuration, documentation, and security, generating a consolidated markdown report.

What is the best way to perform project analysis for onboarding and architecture reviews?

The best way to perform project analysis for onboarding and audits is deploying a multi-agent swarm that runs in parallel to evaluate the codebase and output a detailed AGENT_NOTES.md report for rapid decision making.

Can I use multi-agent parallel analysis for medium to large codebases?

Yes, you can use multi-agent parallel analysis for medium to large codebases. The parallel swarm is specifically ideal for rapidly generating in-depth insights across varying codebase sizes for onboarding and audits.

How does parallel multi-agent project analysis generate its report?

Parallel multi-agent project analysis works by spawning eight agents simultaneously to investigate different codebase aspects. They consolidate their findings into a single AGENT_NOTES.md file located in the tmp-files directory.

Do I need to create a tmp-files directory before running a codebase analysis?

No, you do not need to create the tmp-files directory beforehand. The project analysis process automatically creates the tmp-files directory if it does not exist before outputting the final AGENT_NOTES.md report.