skills.rest
hiranp
hiranpCOMMUNITY
Explore all skills by this author →
Website𝕏@hiranpGitHub

polyflow

Generate runnable JavaScript multi-agent workflows for Claude Code, Codex, Copilot, and Gemini.

Updated May 24, 2026
Search Tags:#automation#workflow#validation#multi-agent#orchestration#deterministic
One-click install
npx skills add https://github.com/hiranp/polyflow --skill polyflow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: polyflow
Source: https://github.com/hiranp/polyflow/tree/main
Command: npx skills add https://github.com/hiranp/polyflow --skill polyflow

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates turning high-level goals into runnable deterministic multi-agent workflows that orchestrate leaf agent calls across Claude Code, Codex, Copilot, and Gemini.

Core Features & Use Cases

  • Topology design: choose fan-out, pipeline, or loop patterns and export a runnable workflow scaffold.
  • Portable memory contracts and file-backed persistence to enable replay, resume, and audit.
  • Cross-platform adapters: portable spec, runtime adapters, and tooling for validation and evaluation.

Quick Start

Provide a goal and receive a ready-to-run deterministic workflow file.

Frequently Asked Questions about polyflow

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

FAQPage Schema
How do I generate a deterministic multi-agent workflow that works across Claude Code, Codex, Copilot, and Gemini?▼

To generate a deterministic multi-agent workflow, provide a high-level goal and receive a runnable JavaScript workflow file with cross-platform adapters for Claude Code, Codex, Copilot, and Gemini.

What is the best way to design multi-agent orchestration patterns like fan-out or pipeline topologies?▼

Designing multi-agent orchestration patterns like fan-out, pipeline, or loop topologies is handled by framing your goal into a portable spec that exports a ready-to-run workflow scaffold.

Can I add memory contracts and validation tooling to a multi-agent workflow for replay and audit?▼

Yes, you can add portable memory contracts and file-backed persistence to your multi-agent workflow, enabling replay, resume, audit, and validation tooling across supported platforms.

Does multi-agent workflow orchestration require manual orchestration code for different coding assistants?▼

No, multi-agent workflow orchestration does not require manual orchestration code because cross-platform runtime adapters automatically translate the portable spec for Claude Code, Codex, Copilot, and Gemini.

Why use deterministic workflow authoring instead of ad-hoc multi-agent orchestration?▼

Deterministic workflow authoring ensures consistent multi-agent execution by replacing ad-hoc orchestration with a portable spec, preventing unpredictable agent behavior and enabling cross-platform validation.

Related Skills

Explore More Software Engineering Skills→
oci-ai-architectsoci-ai-architects
1

oracle-agent-spec

Define portable AI agents using Oracle's Open Agent Specification.

Official
Advanced
PeterFilePeterFile
4

codeagent

Automate multi-backend AI code tasks across Codex, Claude, and Gemini backends.

Community
Advanced
multicammulticam

database

Store PostgreSQL-backed event streams with agent registry and session management.

Community
Advanced
Kushal9889Kushal9889

ai-agent-development

Automate building and managing AI agents with CrewAI and LangGraph.

Community
Advanced