Communitygithub.com

编排流水线

供 orch-* 技能系列共享的编排引擎。定义了门控式研究-计划-TDD-审查-提交流水线、规模分类器、智能体映射以及两个人工门控。通常不直接调用。

编排流水线 是什么?

本技能是 orch-* 系列操作智能体(如 orch-add-feature、orch-fix-defect 等)的共享流水线引擎,为它们提供统一的“研究-计划-TDD-审查-提交”执行流程。技能通过自动化分类任务规模(从微小到大型),决定执行哪些阶段(研究、计划、实现、审查、提交),并在计划后和提交前设置两道人房门控,确保用户对重大决策有最终控制权。支持多种平台(如 VSCode、Cursor、Windsurf),依赖现有的 ECC 智能体(包括 planner、tdd-guide、code-reviewer 等)和 /feature-dev、/code-review 等命令组合执行,而非内联重复工作。流水线本身不携带隐藏状态,通过 task_list 等规划文档实现阶段间交接,并内置安全检查门控,自动识别认证、用户输入等安全敏感变更,必要时引入 security-reviewer。

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/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

编排器流水线(共享引擎)

orch-* 技能是轻量包装器。它们不重新实现任何工作——而是将请求分类,选择本流水线的哪些阶段运行,并将每个阶段委托给现有的 ECC 智能体或命令。本文件即该流水线。

调用操作技能(orch-add-feature、orch-fix-defect……)而非直接调用本引擎。本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。
  • 仅在向技能家族添加新操作或调整共享阶段、门控或智能体映射时直接阅读。

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调整现有功能需更改行为修改现有行为及其测试
orch-fix-defect修复行为错误先复现为失败测试,再修复
orch-refine-code重构行为不变,结构优化在保持测试通过的前提下重构
orch-build-mvpMVP从设计/规范文档启动摄入文档 → 生成垂直切片

这些包装器组合现有 ECC 命令而非替换它们: /feature-dev、/plan、/code-review、/build-fix、/refactor-clean、/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道门控,因此一个统一框架可一致地覆盖全部五种操作。

步骤 0 — 分类规模(合理规模)

仪式感随影响范围扩大而增加。根据三个信号为请求打分,取信号触及的最高层级,并在一行中陈述结果,以便用户覆盖:

层级涉及文件新依赖/契约设计歧义执行的阶段
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个函数无阅读代码后清晰(1简化) → 4 → 5 → 6
标准2–5个文件可能有新内部模块有一个真正的选择1 → 2 → 4 → 5 → 6
大型多个/跨层级新的外部依赖、公开 API 或规范文档多个未解决问题1 → 2 → (3) → 4 → 5 → 6

阶段 0(输入)始终运行,在上面的掩码列中省略。平局裁决:任何触及安全触发器(见下文)或公开 API/契约的变更至少是标准级别,无论文件数量如何。

阶段

每个阶段进行委托——不内联执行工作。

  • 0. 输入 — 重申请求。对于 orch-build-mvp,读取规范/设计文档并提取范围、已锁定决策和功能列表。
  • 1. 研究与复用 — 依据 rules/common/development-workflow.md:gh search repos / gh search code,然后是 Context7 / 供应商文档,接着是包注册表,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 智能体(或 architect / code-architect 进行结构决策)。输出按薄垂直切片排序的 task_list。→ 门控 1。
  • 3. 搭建脚手架 — 仅 orch-build-mvp:搭建首个端到端切片。
  • 4. 实现 (TDD) — 通过 tdd-guide 智能体(或 tdd-workflow 技能)驱动每个任务:红 → 绿 → 重构。遵循操作的第一步规则。
  • 5. 审查 — code-reviewer 智能体 / /code-review。当 diff 触及安全触发器(见下文)时,添加 security-reviewer。
  • 6. 提交 — 常规提交(feat: / fix: / refactor: / ……),每个逻辑块一个提交。→ 门控 2。

两道门控

本家族是门控的,非自动的:

  1. 门控 1 — 计划后。 展示 task_list;在用户批准之前不编写实现代码。
  2. 门控 2 — 提交前。 展示 diff 摘要和提议的提交信息;在用户确认之前不提交。

两道门控之间的流程不间断执行。

智能体/命令映射

阶段主要备用/升级
输入/理解code-explorer在调整、修复或重构前追踪现有路径
计划plannerarchitect、code-architect 进行结构决策
实现tdd-guide(或 tdd-workflow 技能)build-error-resolver / /build-fix 处理构建失败
审查code-reviewer / /code-review语言审查器(python-reviewer、typescript-reviewer……)
安全security-reviewer—
MVP 内循环/gan-build "<简要说明>" --skip-planner驱动 gan-generator → gan-evaluator;调整 --max-iterations / --pass-threshold

语言审查器与仓库匹配(参见仓库自身的 CLAUDE.md)。

安全审查触发器

当 diff 触及以下任一内容时引入 security-reviewer:认证或授权、用户输入处理、数据库查询、文件系统路径、外部 API 调用、加密、或密钥/凭证。(依据 rules/common/security.md。)

交接产物

流水线不携带隐藏状态——规划文档就是交接物:

  • task_list(来自计划阶段)驱动实现循环。
  • 较大工作还可能根据 rules/common/development-workflow.md,在仓库的 docs/ 下输出 PRD / 架构 / 系统设计文档。
  • 审查发现(CRITICAL / HIGH)必须在门控 2 之前解决。

验证

  • 规模层级已声明并与工作匹配
  • 门控 1(计划)和门控 2(提交)均已遵守
  • security-reviewer 仅在触及安全触发器时运行
  • 提交采用约定式提交规范,并限定于单一逻辑变更
  • 新/变更行为有测试;覆盖率 ≥ 80%(依据 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/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m/fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳:このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

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.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

相关技能