ralphinho-rfc-pipeline

Decompose RFCs into DAG work units with quality gates and merge queues.

1|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/xxih/ai-harness-zh --skill ralphinho-rfc-pipeline-xxih
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralphinho-rfc-pipeline
Source: https://github.com/xxih/ai-harness-zh/tree/main/references/translations/everything-claude-code/docs/zh-CN/skills/ralphinho-rfc-pipeline
Command: npx skills add https://github.com/xxih/ai-harness-zh --skill ralphinho-rfc-pipeline-xxih

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the need to manage large, complex feature development that exceeds a single AI agent’s capacity by breaking it into verifiable, orchestrated work units governed by quality checks and merge queues.

Core Features & Use Cases

  • RFC Reception & DAG Decomposition: Converts incoming RFCs into a directed acyclic graph of independent work units.
  • Work Unit Lifecycle Management: Guides each unit through research, implementation, testing, review, and merge‑ready reporting.
  • Quality Gates & Merge Queue : Enforces dependency resolution, rebasing, and continuous integration testing before integration.
  • Recovery Protocols: Provides automated handling for stalled units, including snapshotting and regeneration. Use case example: When a product team proposes a major architectural change, this skill can split the change into scoped units, validate each unit, and safely integrate them into the main codebase.

Quick Start

Ask the agent to process a new RFC by invoking the ralphinho‑rfc‑pipeline skill with the RFC document attached.

Frequently Asked Questions about ralphinho-rfc-pipeline

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

FAQPage Schema
How do I automate multi-agent pipelines for large RFC processing?

Automate multi-agent pipelines by breaking RFCs into a directed acyclic graph of independent work units. Each unit passes through research, implementation, testing, and review stages before reaching merge-ready status.

What is DAG decomposition for multi-agent software development?

DAG decomposition splits incoming RFCs into a directed acyclic graph of independent work units. This allows multiple agents to handle verifiable tasks governed by dependency tracking and quality gating.

How do I manage merge queues and quality gates for multi-agent workflows?

Manage merge queues by enforcing dependency resolution, rebasing, and continuous integration testing before integration. Quality gates ensure each work unit passes CI checks before merging into the main codebase.

Can I use quality gating for complex feature development that exceeds a single AI agent?

Yes, quality gating handles complex feature development by orchestrating verifiable work units across multiple agents. The pipeline enforces CI testing and dependency resolution to ensure safe integration.

How do I recover stalled work units in an automated pipeline?

Recover stalled work units using automated recovery protocols that include snapshotting and regeneration. The pipeline detects stalled units and automatically regenerates them to continue the workflow.

What is the best way to orchestrate RFC pipelines with dependency tracking?

Orchestrate RFC pipelines by converting RFCs into a directed acyclic graph and tracking dependencies across work units. The pipeline manages the full lifecycle from research to merge-ready reporting with continuous integration testing.