skills.rest
dsifry
dsifryCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

external-tools

Delegate coding and review tasks to external AI CLI tools.

379|51|Updated Feb 2, 2026
Search Tags:#automation#code review#code generation#codex#ai tools#gemini#cross-model
One-click install
npx skills add https://github.com/dsifry/metaswarm --skill external-tools
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: external-tools
Source: https://github.com/dsifry/metaswarm/tree/main/skills/external-tools
Command: npx skills add https://github.com/dsifry/metaswarm --skill external-tools

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables the use of external AI CLI tools like OpenAI Codex and Google Gemini to perform coding and review tasks, offering cost savings and cross-model adversarial review to improve code quality.

Core Features & Use Cases

  • Delegated Implementation: Offload coding tasks to specialized AI models.
  • Cross-Model Review: Use different AI models to review code written by another, catching unique blind spots.
  • Cost Optimization: Utilize cheaper external models for certain tasks.
  • Use Case: When implementing a new feature, delegate the initial coding to Gemini, then have Codex review the code against project standards before final human review.

Quick Start

Use the external-tools skill to delegate the implementation of the 'add user authentication' task to Codex.

Frequently Asked Questions about external-tools

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

FAQPage Schema
How do I use external AI tools for code generation and review?▼

Cross-model adversarial review works by delegating coding tasks to one AI model, such as Google Gemini, and having a different model, like OpenAI Codex, review the generated code against project standards to catch unique blind spots.

How do I route coding tasks to different AI models based on cost?▼

Yes, external AI tools support robust error handling for network, authentication, and rate-limiting issues, ensuring reliable delegation of implementation and review tasks to external CLI tools.

What is cross-model adversarial code review?▼

Cross-model adversarial code review uses different AI models to review code written by another model, catching unique blind spots and improving overall code quality through diverse perspectives.

How do I optimize AI coding costs using external models?▼

You can optimize AI coding costs by delegating specific implementation and review tasks to cheaper external AI models like Codex and Gemini through configurable routing logic based on task requirements and model availability.

How does this Skill handle API rate limits and network errors?▼

This Skill handles API rate limits and network errors through robust error handling mechanisms designed for network, authentication, and rate-limiting issues when delegating tasks to external AI CLI tools.

Related Skills

Explore More Software Engineering Skills→
jpeggdevjpeggdev

external-tools

Delegate coding tasks to OpenAI Codex and Google Gemini for implementation and review.

Community
Advanced
arch-teamarch-team
73

/pace-test

Execute automated tests, analyze coverage, and validate acceptance criteria.

Community
Advanced
pegasus-isipegasus-isi

ship

Orchestrate the software development lifecycle from testing to pull request.

Official
Advanced
rongarederongarede
4

collaborating-with-codex

Delegate coding tasks to Codex CLI via a Python bridge with JSON outputs.

Community
Intermediate