RFC Pipeline Multi-Agent Orchestration is a ai-agents claude skill built by Affaan M. Best for: Engineering teams decompose complex features into independently verifiable work units with dependency tracking and integration safety..

What it does
Execute large features through RFC-driven multi-agent DAG with quality gates and merge queues.
Category
ai-agents
Created by
Affaan M
Last updated
Claude Skillai-agents GitHub-backed CuratedadvancedClaude Code

RFC Pipeline Multi-Agent Orchestration

Execute large features through RFC-driven multi-agent DAG with quality gates and merge queues.

Skill instructions

name: ralphinho-rfc-pipeline description: RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration. origin: ECC

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
View raw SKILL.md on GitHub

Use this skill

Most skills are portable instruction packages. Claude Code supports SKILL.md directly. Other agents can use adapted files like AGENTS.md, .cursorrules, and GEMINI.md.

Claude Code

Save SKILL.md into your Claude Skills folder, then restart Claude Code.

mkdir -p ~/.claude/skills/rfc-pipeline-multi-agent-orchestration && curl -L "https://raw.githubusercontent.com/affaan-m/everything-claude-code/HEAD/skills/ralphinho-rfc-pipeline/SKILL.md" -o ~/.claude/skills/rfc-pipeline-multi-agent-orchestration/SKILL.md

Installs to ~/.claude/skills/rfc-pipeline-multi-agent-orchestration/SKILL.md.

Use cases

Engineering teams decompose complex features into independently verifiable work units with dependency tracking and integration safety.

Reviews

No reviews yet. Be the first to review this skill.

No signup required

Stats

Installs0
GitHub Stars157.8k
Forks24520
LicenseMIT
UpdatedMar 27, 2026

Creator

A

Affaan M

@affaan-m

View on GitHub