ralphinho-rfc-pipeline

Decompose large features into dependency-tracked work units with quality gates.

1|Updated May 12, 2026
One-click install
npx skills add https://github.com/Manvendra08/TradingBot --skill ralphinho-rfc-pipeline-manvendra08
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralphinho-rfc-pipeline
Source: https://github.com/Manvendra08/TradingBot/tree/main/_agent/skills/ralphinho-rfc-pipeline
Command: npx skills add https://github.com/Manvendra08/TradingBot --skill ralphinho-rfc-pipeline-manvendra08

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Large, complex features that exceed the capacity of a single agent pass often lead to uncoordinated work, integration failures, and missed quality requirements. This Skill eliminates that risk by providing a structured, RFC-driven workflow to break down work into manageable, verifiable units.

Core Features & Use Cases

  • RFC-Driven DAG Decomposition: Break large feature requests into a directed acyclic graph of independent, dependency-tracked work units.
  • Quality Gate Enforcement: Each work unit undergoes research, implementation, testing, and review before merging to catch issues early.
  • Merge Queue & Recovery Management: Enforce merge rules to avoid dependency conflicts, and automatically recover stalled units by narrowing their scope and retrying with updated constraints.
  • Use Case: Use this Skill to build a new cross-service payment processing feature, splitting it into isolated units for API design, database schema changes, frontend integration, and testing, each with clear acceptance criteria and rollback plans.

Quick Start

Use the ralphinho-rfc-pipeline skill to decompose the new payment processing feature into independently verifiable work units with clear dependencies, acceptance criteria, and rollback plans.

Frequently Asked Questions about ralphinho-rfc-pipeline

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

FAQPage Schema
How do I decompose large features into manageable work units for multi-agent workflows?

Large features are decomposed into manageable work units using RFC-driven DAG decomposition, which breaks feature requests into a directed acyclic graph of independently verifiable, dependency-tracked tasks. This structured workflow ensures each unit has clear dependencies, acceptance criteria, and rollback plans.

What's the best way to enforce quality gates across cross-service feature builds?

Quality gates are enforced by requiring each work unit to undergo research, implementation, testing, and review phases before merging. This structured pipeline catches integration issues early and ensures delivery reliability for cross-service or cross-file feature builds.

How do I handle stalled work units and dependency conflicts in a merge queue?

Stalled work units are handled by automatically narrowing their scope and retrying with updated constraints. The merge queue enforces merge rules to avoid dependency conflicts, ensuring integration risk is reduced across the multi-agent workflow.

Can I use RFC-driven DAG execution for cross-file feature builds with complex dependencies?

Yes, RFC-driven DAG execution applies directly to cross-file feature builds requiring dependency tracking and quality gate enforcement. It orchestrates complex features by splitting them into isolated units for API design, database schema changes, and frontend integration.

When do I need multi-agent DAG execution instead of a single-agent pass?

Multi-agent DAG execution is needed when large, complex features exceed the capacity of a single agent pass, risking uncoordinated work and integration failures. It provides a structured workflow to break down work into verifiable units with rollback plans.