ralphinho-rfc-pipeline

Orchestrate RFC-driven DAG workflows to decompose features into verifiable work units.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/devopstales/ai-workflow --skill ralphinho-rfc-pipeline-devopstales
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ralphinho-rfc-pipeline
Source: https://github.com/devopstales/ai-workflow/tree/main/skills/ralphinho-rfc-pipeline
Command: npx skills add https://github.com/devopstales/ai-workflow --skill ralphinho-rfc-pipeline-devopstales

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

RFC-driven multi-agent DAG orchestration that splits large features into independently verifiable work units to improve traceability and risk management.

Core Features & Use Cases

  • RFC intake and DAG decomposition
  • Unit assignment, implementation, and validation
  • Merge queue governance, recovery, and final system verification

Quick Start

Split a feature that is too large for a single pass into independently verifiable RFC work units and run the pipeline.

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 a large feature into independently verifiable work units?▼

To decompose a large feature into independently verifiable work units, you can use an RFC-driven orchestration pipeline that splits the feature into a DAG of staged work units. This approach applies quality gates to each unit to improve traceability and manage integration risk.

What is RFC-driven DAG orchestration for feature development?▼

RFC-driven DAG orchestration is a governance process that structures feature development into a directed acyclic graph of independently verifiable work units. It coordinates unit specification, assignment, and validation to ensure traceability across complex integration pipelines.

How do I implement quality gates in a multi-unit merge queue?▼

To implement quality gates in a multi-unit merge queue, the pipeline enforces validation checkpoints during unit assignment and integration. It uses merge-queue driven governance to verify each work unit independently before final system verification across the DAG.

When do I need to split large features into an RFC pipeline?▼

You need to split large features into an RFC pipeline when a feature is too large for a single implementation pass and requires staged decomposition. This process manages complexity tiers and tracks execution risk through an outputs catalog during recovery workflows.

Does this pipeline support recovery workflows for failed work units?▼

Yes, the pipeline supports recovery workflows for failed work units as part of its merge queue governance. It tracks execution and risk through an outputs catalog, allowing the DAG orchestration to recover and re-validate specific units before final system verification.