Ralphinho Rfc Pipeline
- 5.3k installs
- 238k repo stars
- Updated August 5, 2026
- affaan-m/everything-claude-code
Ralphinho RFC Pipeline is an agent skill that decomposes large RFC features into DAG work units with quality gates, merge queue rules, and multi-unit orchestration.
About
Ralphinho RFC Pipeline is an agent skill that decomposes oversized features into independently verifiable work units using Humanplane-style RFC breakdown and multi-unit orchestration. Activate when a single-agent path cannot safely deliver a large capability and you need DAG-based decomposition, quality gates, and a disciplined merge queue. The seven-stage pipeline runs RFC intake, DAG decomposition, unit assignment, implementation, validation, merge queue integration, and final system verification. Each unit ships with id, depends_on, scope, acceptance_tests, risk_level, and rollback_plan. Complexity tiers classify isolated file edits as Tier 1, multi-file behavior as Tier 2, and schema, auth, performance, or security work as Tier 3. Every unit passes research, implementation plan, implementation, tests, review, and merge-ready reporting. Merge rules forbid integrating units with unresolved dependency failures, require rebasing on the latest integration branch, and mandate integration test reruns after each queued merge. Stalled units are evicted, findings snapshotted, scope narrowed, and retries constrained. Outputs include RFC execution logs, unit scorecards, dependency graph s.
- Seven-stage pipeline from RFC intake through DAG decomposition, unit work, validation, merge queue, and final verificati
- Unit spec template requires id, depends_on, scope, acceptance_tests, risk_level, and rollback_plan per work unit.
- Complexity tiers from Tier 1 isolated edits through Tier 3 schema, auth, performance, and security changes.
- Per-unit quality pipeline: research, plan, implementation, tests, review, and merge-ready report before integration.
- Merge queue rules block unresolved dependencies, require rebase on integration branch, and rerun integration tests after
Ralphinho Rfc Pipeline by the numbers
- 5,329 all-time installs (skills.sh)
- +224 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #144 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
ralphinho-rfc-pipeline capabilities & compatibility
- Capabilities
- decompose rfcs into dag work units with dependen · assign and validate units through acceptance tes · enforce merge queue rules with rebase and integr · recover stalled units by evicting, snapshotting · produce rfc execution logs, scorecards, and depe
- Use cases
- orchestration · planning · project management · code review · testing
What ralphinho-rfc-pipeline says it does
単一エージェントパスでは大きすぎる機能を独立して検証可能なワークユニットに分割する必要がある場合、このスキルを使用します。
Never merge a unit with unresolved dependency failures.
npx skills add https://github.com/affaan-m/everything-claude-code --skill ralphinho-rfc-pipelineAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 5.3k |
|---|---|
| repo stars | ★ 238k |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 5, 2026 |
| Repository | affaan-m/everything-claude-code ↗ |
How do I split a feature too large for one agent into independently verifiable work units with safe merge ordering and recovery when units stall?
Split large RFC features into DAG work units with quality gates, merge queue rules, and multi-agent orchestration.
Who is it for?
Teams running multi-agent coding workflows on large RFCs that need DAG decomposition, per-unit validation, and disciplined merge queue integration.
Skip if: Small single-file edits, one-shot prompts without RFC structure, or tasks with no need for dependency-aware unit orchestration.
When should I use this skill?
User needs RFC intake, DAG decomposition, unit assignment, validation gates, merge queue management, or recovery when a work unit stalls.
What you get
RFC execution logs, unit scorecards, dependency graph snapshots, integration risk summaries, and merge-ready units validated through acceptance tests.
- Work-unit DAG
- Merge queue plan
- Verification checklist
By the numbers
- Defines a 7-stage RFC-driven multi-agent pipeline
Files
Ralphinho RFC Pipeline
humanplane スタイルのRFC分解パターンと複数ユニットオーケストレーションワークフローにインスパイア。
単一エージェントパスでは大きすぎる機能を独立して検証可能なワークユニットに分割する必要がある場合、このスキルを使用します。
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
各ワークユニットに含める：
iddepends_onscopeacceptance_testsrisk_levelrollback_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
ユニットが stall した場合：
- 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
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10Forks & variants (1)
Ralphinho Rfc Pipeline has 1 known copy in the catalog totaling 1.4k installs. They canonicalize to this original listing.
- affaan-m - 1.4k installs
How it compares
Use this over simple task-splitting skills when parallel agents need DAG dependencies, validation gates, and merge-queue integration.
FAQ
When should I use the Ralphinho RFC Pipeline skill?
Use it when a single-agent path is too large and you need independently verifiable work units with DAG decomposition, quality gates, and merge queue orchestration.
What does each work unit spec include?
Each unit includes id, depends_on, scope, acceptance_tests, risk_level, and rollback_plan, plus a six-step quality pipeline ending in a merge-ready report.
What are the merge queue rules?
Never merge a unit with unresolved dependency failures, always rebase on the latest integration branch, and re-run integration tests after each queued merge.
Is Ralphinho Rfc Pipeline safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.