About this skill
The "Ralphinho RFC Pipeline" is a sophisticated skill designed for AI agents to manage and execute large, complex software development features that would overwhelm a single agent. Inspired by RFC (Request for Comments) decomposition patterns, it enables a multi-agent team to break down a grand task into smaller, independently verifiable work units. This skill provides a structured DAG (Directed Acyclic Graph) execution model, guiding agents through a comprehensive pipeline from initial RFC reception and decomposition to final system validation and integration. It incorporates critical engineering practices such as quality gates for each unit, a meticulously managed merge queue to ensure integration stability, and detailed work unit orchestration, including risk assessment and rollback plans. The goal is to facilitate the development of robust, production-ready systems by ensuring quality, managing dependencies, and providing clear recovery paths for stalled units.
Best use case
Ideal for AI agents tasked with implementing large-scale software features or refactoring complex systems that require breaking down into modular, independently testable components and coordinated development across multiple agent instances.
基于RFC驱动的多智能体DAG执行模式，包含质量门、合并队列和工作单元编排。
Successful implementation and integration of a complex software feature, documented by comprehensive RFC execution logs, unit scorecards, dependency graph snapshots, and an integration risk summary. The outcome is a well-tested, high-quality, and robust system component, developed through a managed, multi-agent process, with clear traceability and reduced integration risks.
Practical example
Example input
A high-level Request for Comments (RFC) document outlining a new feature: "Implement a distributed caching layer for the user authentication service, supporting geo-replication and automatic invalidation." This RFC would detail the desired functionality, high-level architecture, and success criteria.
Example output
{"RFC Execution Log": "A chronological record of pipeline stages, agent assignments, and status updates.", "Unit Scorecards": "Detailed reports for each work unit, including implementation status, test results, review feedback, and risk assessment.", "Dependency Graph Snapshot": "A visual or textual representation of the decomposed work units and their interdependencies, showing completed and pending units.", "Integration Risk Summary": "An assessment of potential integration challenges and how they were mitigated.", "Final Codebase": "The completed and integrated code for the distributed caching layer, thoroughly tested and merged into the main development branch."}When to use this skill
- Implementing significant new features that span multiple codebases or modules.
- Executing architectural changes, security enhancements, or performance optimizations.
- Projects where rigorous quality control, phased integration, and clear dependency management are paramount.
- When a single AI agent's context window or processing capacity is insufficient for the entire task.
When not to use this skill
- For small, isolated bug fixes or minor code improvements.
- Simple, self-contained tasks that can be efficiently handled by a single agent without complex decomposition.
- Projects with extremely tight deadlines where the overhead of this structured process might outweigh the benefits for very minor changes.
- When the task does not involve interdependent sub-tasks or complex integration concerns.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ralphinho-rfc-pipeline/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ralphinho-rfc-pipeline Compares
| Feature / Agent | ralphinho-rfc-pipeline | Standard Approach |
|---|---|---|
| Platform Support | Claude | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | medium | N/A |
Frequently Asked Questions
What does this skill do?
基于RFC驱动的多智能体DAG执行模式，包含质量门、合并队列和工作单元编排。
Which AI agents support this skill?
This skill is designed for Claude.
How difficult is it to install?
The installation complexity is rated as medium. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# Ralphinho RFC 管道 灵感来源于 [humanplane](https://github.com/humanplane) 风格的 RFC 分解模式和多单元编排工作流。 当一个功能对于单次代理处理来说过于庞大，必须拆分为独立可验证的工作单元时，请使用此技能。 ## 管道阶段 1. RFC 接收 2. DAG 分解 3. 单元分配 4. 单元实现 5. 单元验证 6. 合并队列与集成 7. 最终系统验证 ## 单元规范模板 每个工作单元应包含： * `id` * `depends_on` * `scope` * `acceptance_tests` * `risk_level` * `rollback_plan` ## 复杂度层级 * 层级 1：独立文件编辑，确定性测试 * 层级 2：多文件行为变更，中等集成风险 * 层级 3：架构/认证/性能/安全性变更 ## 每个单元的质量管道 1. 研究 2. 实现计划 3. 实现 4. 测试 5. 审查 6. 合并就绪报告 ## 合并队列规则 * 永不合并存在未解决依赖项失败的单元。 * 始终将单元分支变基到最新的集成分支上。 * 每次队列合并后重新运行集成测试。 ## 恢复 如果一个单元停滞： * 从活动队列中移除 * 快照发现结果 * 重新生成范围缩小的单元 * 使用更新的约束条件重试 ## 输出 * RFC 执行日志 * 单元记分卡 * 依赖关系图快照 * 集成风险摘要
Related Skills
cost-aware-llm-pipeline
LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存。
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
safety-guard
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
repo-scan
Cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports.
project-flow-ops
Operate execution flow across GitHub and Linear by triaging issues and pull requests, linking active work, and keeping GitHub public-facing while Linear remains the internal execution layer. Use when the user wants backlog control, PR triage, or GitHub-to-Linear coordination.
manim-video
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.
laravel-plugin-discovery
Discover and evaluate Laravel packages via LaraPlugins.io MCP. Use when the user wants to find plugins, check package health, or assess Laravel/PHP compatibility.
design-system
Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling.
click-path-audit
Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores.
ck
Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.
canary-watch
Use this skill to monitor a deployed URL for regressions after deploys, merges, or dependency upgrades.
benchmark
Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.