Communitygithub.com

Orchestrator Pipeline(共享引擎)

orch-* 技能系列的共享编排引擎。定义了带门控的研究-计划-TDD-审查-提交流程、规模分类器、代理映射以及两个人工门控,由 orch-* 操作技能代理调用。通常不直接调用。

Orchestrator Pipeline(共享引擎) 是什么?

Orchestrator Pipeline(orch-pipeline)是 orch-* 技能家族的共享编排引擎,为操作技能如添加功能、修复缺陷、变更功能、重构代码和构建 MVP 提供了统一的、门控的研究-计划-TDD-审查-提交流程。该引擎通过 size classifier 根据影响范围动态调整流程开销:小规模变更可跳过部分阶段,而大规模或触发性安全边界的变更则强制执行完整流程。流程的关键在于两个人工门控——计划后的任务列表审批和提交前的差异摘要确认——确保用户始终拥有控制权,而非完全自主运行。每个阶段都委托给专门的 ECC 代理或命令(如 planner、tdd-guide 和 code-reviewer),包含代码示例和技术细节,适用于 Claude Code、Cursor 等支持多代理编排的开发工具。

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/everything-claude-code/tree/main/skills/orch-pipeline

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Orchestrator Pipeline(共享引擎) 是做什么的?

orch-* 技能是薄包装器。它们不重新实现任何工作——它们对请求进行分类,选择此管道运行的阶段,并将每个阶段委托给现有的 ECC 代理或命令。此文件即为该管道。

请直接调用操作技能(orch-add-feature、orch-fix-defect……),而不是直接使用此引擎。此文件是它们指向的参考。

何时使用

  • 每当 orch-* 操作技能运行时,间接加载。
  • 仅在向家族添加新操作或调整共享阶段、门控或代理映射时直接阅读。

操作家族

技能操作触发条件第一步
orch-add-feature功能能力尚不存在研究 + 规划新切片
orch-change-feature调整功能存在但期望行为不同修改现有行为及其测试
orch-fix-defect修复损坏;行为错误将缺陷重现为失败的测试,然后修复
orch-refine-code重构行为不变,结构改善重构,同时保持测试通过
orch-build-mvpMVP从设计/规范文档启动读取文档 → 垂直切片

这些包装器组合了现有的 ECC 命令而非替换它们: /feature-dev、/plan、/code-review、/build-fix、/refactor-clean 和 /gan-build,以及 tdd-workflow 技能。orch-* 家族在此基础上添加了共享的 规模分类器和两个门控,因此一个统一的覆盖层可以始终如一地覆盖所有五种操作。

步骤 0 — 分类规模(合适规模)

流程复杂度应随影响范围缩放。根据以下三个信号对请求评分,取任何信号达到的最高层级,并在一行中陈述结果,以便用户可以覆盖:

层级涉及文件数新依赖/契约设计模糊性执行的阶段
微小1个文件,几行无无 — 变更显而易见4 → 5 → 6
小型1个文件/1个函数无阅读代码即可明确(1 轻量) → 4 → 5 → 6
标准2–5个文件可能新增内部模块存在一个实际需要做决定的问题1 → 2 → 4 → 5 → 6
大型多个/跨层新的外部依赖、公共 API 或规范文档多个待解决问题1 → 2 → (3) → 4 → 5 → 6

阶段 0(接收)始终运行,在上面的掩码列中省略。打破平局规则:任何触及安全触发器(见下文)或公共 API / 契约的内容至少属于标准级,无论文件数多少。

各阶段

每个阶段都进行委托——不内联完成工作。

  • 0. 接收 — 重述请求。对于 orch-build-mvp,读取规范/设计文档并提取范围、已锁定的决策和功能列表。
  • 1. 研究与复用 — 根据 rules/common/development-workflow.md:gh search repos / gh search code,然后是 Context7 / 供应商文档,然后是包注册表,最后是 Exa。优先采用经过验证的实现而非全新代码。
  • 2. 计划 — 委托给 planner 代理(或 architect / code-architect 处理结构决策)。输出按薄垂直切片排序的 task_list。→ 门控 1。
  • 3. 脚手架 — 仅 orch-build-mvp:搭建第一个端到端切片。
  • 4. 实现(TDD) — 通过 tdd-guide 代理(或 tdd-workflow 技能)驱动每个任务: 红 → 绿 → 重构。遵守操作的第一步规则。
  • 5. 审查 — code-reviewer 代理 / /code-review。当差异触及安全触发器(见下文)时,添加 security-reviewer。
  • 6. 提交 — 符合约定的提交(feat: / fix: / refactor: / ……),每个逻辑块一个提交。→ 门控 2。

两个门控

此家族是门控的,而非自主运行:

  1. 门控 1 — 计划后。 呈现 task_list;在用户批准之前,不编写实现代码。
  2. 门控 2 — 提交前。 呈现差异摘要和建议的提交消息;在用户确认之前,不进行提交。

两个门控之间的流程持续进行,不会停止。

代理/命令映射

阶段主要代理备用/升级
接收/理解code-explorer在调整、修复或重构前追踪现有路径
计划plannerarchitect、code-architect 处理结构决策
实现tdd-guide(或 tdd-workflow 技能)构建失败时使用 build-error-resolver / /build-fix
审查code-reviewer / /code-review语言审查者(python-reviewer、typescript-reviewer……)
安全security-reviewer—
MVP 内部循环/gan-build "<简要>" --skip-planner驱动 gan-generator → gan-evaluator;调整 --max-iterations / --pass-threshold

根据仓库选择语言审查者(请参阅仓库自身的 CLAUDE.md)。

安全审查触发器

当差异涉及以下任何内容时,引入 security-reviewer:身份验证或授权、用户输入处理、数据库查询、文件系统路径、外部 API 调用、加密技术或密钥/凭据。(根据 rules/common/security.md。)

交接产物

管道不携带隐藏状态——规划文档就是交接物:

  • task_list(来自计划阶段)驱动实现循环。
  • 较大型的工作也可能在仓库 docs/ 目录下生成 PRD / 架构 / 系统设计文档,遵循 rules/common/development-workflow.md。
  • 审查发现(严重 / 高)必须在门控 2 之前解决。

验证

  • 已说明规模层级,并且与实际工作匹配
  • 门控 1(计划)和门控 2(提交)均已遵循
  • 当且仅当触发了安全触发器时,security-reviewer 已运行
  • 提交通常遵循约定,并限定于单个逻辑变更
  • 新增/变更的行为有测试;覆盖率 ≥ 80%(根据 rules/common/testing.md)

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

affaan-m/everything-claude-code

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

affaan-m/gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

affaan-m/motion-ui

Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.

affaan-m/project-guidelines-example

Example project-specific skill template based on a real production application.

affaan-m/pubmed-database

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring.

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

相关技能