Skip to content
Skillpedia
PT
Deploy & cloud (DevOps)280k · #264

ralphinho-rfc-pipeline

Lets your agent break down large tasks into smaller parts. It organizes these parts, defines how they depend on each other, and ensures everything is tested and combined correctly.

What it does

This agent organizes a large project into smaller, manageable parts. It breaks down the work, assigns tasks, implements each part, tests it, and ensures everything works together at the end.

When to use it

  • ✓When a task is too big to be done all at once.
  • ✓To organize the work of multiple people (agents) on a project.
  • ✓To ensure project parts fit together correctly before final integration.

Example of what to ask your AI

“Break down this website project into smaller tasks, with clear instructions for each.”

Want more? Open the sections below.

How to use

The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.

Skill link

https://github.com/affaan-m/ECC/blob/main/skills/ralphinho-rfc-pipeline/SKILL.md

Ready-to-paste message

Use this skill to help me: https://github.com/affaan-m/ECC/blob/main/skills/ralphinho-rfc-pipeline/SKILL.md Read the SKILL.md file at that link and follow its instructions for my task.
View on GitHub ↗Raw file
How it works

It takes a large idea (RFC), breaks it into pieces with clear dependencies, and then executes each piece in order, testing and reviewing before merging everything.

Installation

Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.

In the terminal (Claude Code, Codex, Cursor), in your project folder:

npx skills add affaan-m/ECC --skill ralphinho-rfc-pipeline

Or download just the file:

curl -L https://raw.githubusercontent.com/affaan-m/ECC/main/skills/ralphinho-rfc-pipeline/SKILL.md -o SKILL.md
Technical content (original SKILL.md)

Original text by the author, straight from GitHub.

Ralphinho RFC Pipeline

Inspired by humanplane style RFC decomposition patterns and multi-unit orchestration workflows.

Use this skill when a feature is too large for a single agent pass and must be split into independently verifiable work units.

Pipeline Stages

  1. RFC intake
  2. DAG decomposition
  3. Unit assignment
  4. Unit implementation
  5. Unit validation
  6. Merge queue and integration
  7. Final system verification

Unit Spec Template

Each work unit should include:

  • id
  • depends_on
  • scope
  • acceptance_tests
  • risk_level
  • rollback_plan

Complexity Tiers

  • Tier 1: isolated file edits, deterministic tests
  • Tier 2: multi-file behavior changes, moderate integration risk
  • Tier 3: schema/auth/perf/security changes

Quality Pipeline per Unit

  1. research
  2. implementation plan
  3. implementation
  4. tests
  5. review
  6. 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
FAQ

What is an RFC?

It's a document proposing an idea or change, serving as the starting point for the work.

What are 'work units'?

These are the smaller pieces the project is divided into, each with its own instructions and tests.

What happens if a part fails its tests?

The failing part is removed, its findings are saved, and it's redone with adjusted instructions before trying again.

Details

Original description by the author

Split an RFC into a multi-agent execution DAG — decompose into work units with dependencies and acceptance tests, run research, plan, implement, test, and review per unit, then merge through a queue with re-based branches and final system verification. Use when a feature is too large for a single agent pass, orchestrating RFC-driven multi-agent execution, or managing merge queues across agent-buil

repo: affaan-m/ECC

Popularity

GitHub stars
280k
Ranking position
#264
License
MIT
Updated
10/15/2026

Is this skill useful?

0

Sign in to vote.

Comments

  • …

More skills from this repository

Interfaces (UI/UX)280k

accessibility

Helps your agent create interfaces that everyone can use. Ensures websites and apps work well for people with disabilities, like those who are blind or have reduced mobility.

affaan-m/ECC

Agents280k

agent-architecture-audit

Makes your agent check if everything is working correctly. It finds and fixes problems in AI systems, ensuring they perform as expected.

affaan-m/ECC

Agents280k

agent-eval

Helps your agent compare different AI coding tools. It measures which one is faster, cheaper, and more reliable for specific tasks.

affaan-m/ECC

Agents280k

agent-harness-construction

Makes your agent better understand how to perform tasks. It optimizes the tools and instructions the agent uses to increase its chances of success.

affaan-m/ECC

Similar skills

Deploy & cloud (DevOps)107k

git-workflow-and-versioning

Organizes code work using Git. Helps save progress, manage different versions, and avoid conflicts when working in a team.

addyosmani/agent-skills

Deploy & cloud (DevOps)107k

observability-and-instrumentation

Adds tools to monitor what the code does in production. Helps understand if something went wrong and why, making fixes easier.

addyosmani/agent-skills

Deploy & cloud (DevOps)103k

github-pr-workflow

Prepares GitHub pull requests, ensuring code quality and documentation.

paperclipai/paperclip