What is an RFC-driven pipeline?

It is a workflow where development starts with a Request for Comments (RFC) document, which is then decomposed into a structured Directed Acyclic Graph (DAG) of work units for systematic execution.

What happens if a work unit stalls or fails?

The recovery logic evicts the unit from the active queue, snapshots the current findings, and regenerates a narrowed scope to retry the task with updated constraints.

How does the quality pipeline per unit work?

Each work unit passes through six distinct stages: research, implementation planning, implementation, testing, review, and a final merge-ready report to ensure zero-defect integration.

When should I use the Ralphinho RFC Pipeline skill?

Use this skill when a feature is too large for a single AI agent pass and requires splitting into multiple, independently verifiable tasks with complex dependencies.

How does it handle merge conflicts or dependency failures?

The skill includes strict merge queue rules that prevent merging units with unresolved dependency failures and requires rebasing on the latest integration branch before final verification.

Ralphinho RFC Pipeline

Name: Ralphinho RFC Pipeline
Author: oabdelmaksoud

byoabdelmaksoud

0•

Collaboration Tools

Orchestrates complex development cycles by decomposing high-level features into verifiable work units using an RFC-driven multi-agent DAG execution pattern.

The Ralphinho RFC Pipeline is a sophisticated orchestration skill designed for managing large-scale software features that are too complex for a single agent pass. By leveraging a Directed Acyclic Graph (DAG) decomposition strategy, it breaks down architectural requirements into granular, independently verifiable work units equipped with built-in quality gates and risk assessments. This skill ensures systematic implementation through a multi-stage pipeline—from research and planning to automated testing and merge queue management—making it essential for teams executing high-risk schema changes, security updates, or multi-file refactors within the Claude Code environment.

Key Features

010 GitHub stars

02Multi-agent DAG decomposition for complex feature orchestration

03Standardized unit spec templates with acceptance tests and risk levels

04Dynamic recovery protocols to rescope and retry stalled work units

05Automated merge queue logic with dependency failure protection

06Tiered complexity management for isolated vs. system-wide changes

Use Cases

01Managing high-risk system changes like schema migrations or auth updates

02Breaking down massive architectural features into manageable, testable sub-tasks

03Standardizing the implementation workflow for distributed AI agent teams

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add oabdelmaksoud/superclaw ralphinho-rfc-pipeline

For use in Claude.ai and ChatGPT

Key Features

010 GitHub stars

02Multi-agent DAG decomposition for complex feature orchestration

03Standardized unit spec templates with acceptance tests and risk levels

04Dynamic recovery protocols to rescope and retry stalled work units

05Automated merge queue logic with dependency failure protection

06Tiered complexity management for isolated vs. system-wide changes

Use Cases

01Managing high-risk system changes like schema migrations or auth updates

02Breaking down massive architectural features into manageable, testable sub-tasks

03Standardizing the implementation workflow for distributed AI agent teams