ralphinho-rfc-pipeline

Decompose oversized features into independently verifiable work units across multiple agents.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/sakamoto-family-smile/agent_monorepo --skill ralphinho-rfc-pipeline-sakamoto-family-smile
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralphinho-rfc-pipeline
Source: https://github.com/sakamoto-family-smile/agent_monorepo/tree/main/.claude/skills/ecc/ralphinho-rfc-pipeline
Command: npx skills add https://github.com/sakamoto-family-smile/agent_monorepo --skill ralphinho-rfc-pipeline-sakamoto-family-smile

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Decompose oversized features into independently verifiable work units across multiple agents.

Core Features & Use Cases

  • RFC-style decomposition into a DAG of work units
  • Quality gates, unit-level validation, and a merge queue for integration
  • Clear unit spec templates and recovery paths for stalled work

Quick Start

Decompose a large feature into discrete work units and begin implementing them through the RFC 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?

Feature decomposition breaks oversized requirements into discrete work units using an RFC-style template. The pipeline structures these units into a directed acyclic graph (DAG) so multiple agents can execute and validate them independently before integration.

What is an RFC-driven multi-agent workflow pipeline?

An RFC-driven workflow pipeline orchestrates multi-agent development by enforcing unit specifications, dependency management, and quality gates. It ensures each work unit passes validation through a merge queue before final integration.

How do I manage dependencies and rollback plans in a multi-agent DAG execution?

Multi-agent DAG execution manages dependencies by mapping work units in a directed acyclic graph. The pipeline enforces risk assessment and rollback plans at each node, ensuring stalled work has clear recovery paths without blocking the entire queue.

Can I use quality gates and a merge queue for multi-team feature integration?

Quality gates and merge queues are designed for multi-team environments to validate integration readiness. The pipeline applies unit-level checks before merging, ensuring independently developed features meet specifications without breaking the main branch.

When should I not use RFC-style decomposition for my workflow?

RFC-style decomposition is not suited for small, isolated tasks that do not require multi-agent coordination. If a feature lacks complex interdependencies or risk factors requiring rollback plans, the overhead of unit specs and DAG execution outweighs the benefits.

What's the best way to handle stalled work units in a multi-agent pipeline?

Handling stalled work units involves triggering predefined recovery paths within the pipeline. The RFC framework enforces clear unit specs and rollback plans, allowing agents to assess integration readiness and bypass or retry failed nodes without disrupting the merge queue.