ralphinho-rfc-pipeline

Automate RFC-driven feature decomposition into DAG work units with quality gates.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/robinxin/AIFlomo --skill ralphinho-rfc-pipeline-robinxin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ralphinho-rfc-pipeline
Source: https://github.com/robinxin/AIFlomo/tree/main/.claude/skills/ralphinho-rfc-pipeline
Command: npx skills add https://github.com/robinxin/AIFlomo --skill ralphinho-rfc-pipeline-robinxin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

RFC-driven approach to decompose large features into independently verifiable work units, enabling safe, auditable collaboration across agents.

Core Features & Use Cases

  • RFC intake, DAG decomposition, unit assignment, unit implementation, unit validation, merge queue and integration, final system verification
  • Unit Spec Template: each work unit includes id, depends_on, scope, acceptance_tests, risk_level, rollback_plan
  • Complexity Tiers: Tier 1: isolated file edits, Tier 2: multi-file behavior changes, Tier 3: schema/auth/perf/security changes
  • Quality Pipeline per Unit: research, implementation plan, implementation, tests, review, merge-ready report
  • Merge Queue Rules: never merge a unit with unresolved dependency failures; always rebase unit branches on latest integration branch; re-run integration tests after each queued merge
  • Recovery: if a unit stalls, evict from active queue, snapshot findings, regenerate narrowed unit scope, retry with updated constraints
  • Outputs: RFC execution log, unit scorecards, dependency graph snapshot, integration risk summary

Quick Start

Provide an RFC for a feature, break it into work units, and run through the quality gates.

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 independently verifiable work units for multi-agent development?▼

Large features can be decomposed into independently verifiable work units by applying RFC intake, DAG decomposition, and unit assignment to enable safe, auditable collaboration across multiple agents.

What is the best way to manage a merge queue for multi-unit feature development?▼

The best way to manage a merge queue is to enforce rules that never merge units with unresolved dependency failures, always rebase on the latest integration branch, and re-run integration tests after each queued merge.

How does DAG decomposition handle work unit dependencies during feature implementation?▼

DAG decomposition handles dependencies by mapping each work unit's dependencies in a structured spec template, ensuring units are assigned and validated only after their prerequisite dependency units are successfully merged.

When do I need quality gates for multi-agent feature development?▼

You need quality gates when a feature is too large for a single agent pass, requiring structured tiers for complexity, unit validation, and final system verification to ensure safe, auditable collaboration.

What happens if a work unit stalls during multi-agent orchestration?▼

If a work unit stalls during orchestration, it is evicted from the active queue, findings are snapshotted, and a narrowed unit scope is regenerated to retry implementation with updated constraints.

Can I use RFC-driven orchestration for schema and security changes across multiple files?▼

Yes, RFC-driven orchestration supports complexity Tier 3 changes involving schema, auth, performance, or security modifications across multiple files by routing them through the full quality validation pipeline.