Communitygithub.com

Orchestrator Pipeline(共享引擎)

共享編排引擎,供 orch-* 技能家族使用。定義了閘門式 Research-Plan-TDD-Review-Commit 流程、規模分類器、代理對應表及兩個人為閘門。通常不直接調用。當 orch-* 技能委派其閘門式流程時適用。

Orchestrator Pipeline(共享引擎) 是什麼?

Orchestrator Pipeline (orch-pipeline) 是 orch-* 技能家族的核心共享引擎,提供一個閘門式 Research-Plan-TDD-Review-Commit 流程。此技能定義了規模分類器(依影響範圍與複雜度將請求分為 trivial、small、standard、large 四個等級)、五個階段(從需求釐清到提交)、以及兩個人為閘門(計畫審核與提交前確認),確保開發流程在可控範圍內進行。它並非獨立使用的技能,而是由 orch-add-feature、orch-fix-defect、orch-refine-code 等操作技能委派執行,這些操作技能僅為薄封裝層,實際工作皆由此引擎統籌。支援的代理包括 code-explorer、planner、tdd-guide、code-reviewer、security-reviewer 等,並可根據語言與專案需求切換審查代理。手動安全審查觸發條件涵蓋認證、使用者輸入、資料庫查詢、檔案系統路徑等敏感區域。此引擎無隱藏狀態,所有交接資訊皆存放於 task_list 或 docs/ 目錄下的文件。

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

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Orchestrator Pipeline(共享引擎) 是做什麼的?

orch-* 技能是薄封裝層。它們不會重新實作任何工作,而是 分類請求、選擇此流程中要執行的階段,並將每個階段委派給 現有的 ECC 代理或指令。此檔案即為該流程。

請調用作業技能(orch-add-feature、orch-fix-defect……), 而非直接使用此引擎。此檔案是它們參考的基礎。

使用時機

  • 每當 orch-* 作業技能執行時間接載入。
  • 僅在為家族新增作業或調整共享階段、閘門或代理對應表時直接閱讀。

作業家族

技能作業觸發條件第一動作
orch-add-featurefeature功能尚未存在研究 + 規劃新切面
orch-change-featuretweak可運作但預期行為不同修改既有行為及其測試
orch-fix-defectfix故障;行為錯誤以失敗測試重現,然後修正
orch-refine-coderefactor行為不變,結構改善在維持測試綠燈下重構
orch-build-mvpmvp從設計/規格文件啟動擷取文件 → 垂直切面

這些封裝層組合現有 ECC 指令而非取代它們: /feature-dev、/plan、/code-review、/build-fix、/refactor-clean 及 /gan-build,加上 tdd-workflow 技能。orch-* 家族在它們之上添加了共享 規模分類器和兩個閘門, 因此一個統一架構即可涵蓋全部五種作業。

步驟 0 — 分類規模(適度規模化)

儀式規模與影響範圍成正比。根據三個訊號對請求評分,取任何訊號達到的最高層級, 並以一行陳述結果,讓使用者可以覆寫:

層級觸及檔案新增相依/合約設計模糊性執行的階段
trivial1 個檔案,幾行無無 — 變更顯而易見4 → 5 → 6
small1 個檔案 / 1 個函式無閱讀程式碼後即可釐清(1 輕量) → 4 → 5 → 6
standard2–5 個檔案可能有新的內部模組需做一項實際決策1 → 2 → 4 → 5 → 6
large多個 / 跨層面新的外部相依、公開 API 或規格文件多個待解問題1 → 2 → (3) → 4 → 5 → 6

階段 0(接收)永遠執行,且未列於上方遮罩欄中。 打破平手規則:任何觸及安全觸發條件(如下)或公開 API / 合約的事項 至少為 standard,無論檔案數量為何。

階段

每個階段皆為委派 — 不直接執行工作。

  • 0. 接收 — 重新陳述請求。對於 orch-build-mvp,讀取規格/設計文件並提取範疇、已鎖定決策及功能清單。
  • 1. 研究與重用 — 根據 rules/common/development-workflow.md:gh search repos / gh search code,然後 Context7 / 供應商文件,接著套件註冊表,再來 Exa。優先採用經過驗證的實作而非新寫程式碼。
  • 2. 規劃 — 委派給 planner 代理(或 architect / code-architect 進行結構性決策)。輸出順序為薄垂直切面的 task_list。→ 閘門 1。
  • 3. 骨架建立 — 僅限 orch-build-mvp:建立第一個端到端切面。
  • 4. 實作 (TDD) — 透過 tdd-guide 代理(或 tdd-workflow 技能)驅動每個任務: 紅 → 綠 → 重構。遵守作業的第一動作規則。
  • 5. 審查 — code-reviewer 代理 / /code-review。每當差異觸及安全觸發條件(如下)時加入 security-reviewer。
  • 6. 提交 — conventional commits(feat: / fix: / refactor: / ……),每個邏輯區塊一個。→ 閘門 2。

兩個閘門

此家族是閘門式,非自主執行:

  1. 閘門 1 — 規劃後。 展示 task_list;在使用者批准前不寫入實作程式碼。
  2. 閘門 2 — 提交前。 展示差異摘要及建議訊息;在使用者確認前不提交。

兩個閘門之間的所有流程持續執行,無需中斷。

代理 / 指令對應表

階段主要降級 / 升級
接收 / 理解code-explorer在調整、修正或重構前追蹤既有路徑
規劃plannerarchitect、code-architect 進行結構性呼叫
實作tdd-guide(或 tdd-workflow 技能)build-error-resolver / /build-fix 處理建置錯誤
審查code-reviewer / /code-review語言審查者(python-reviewer、typescript-reviewer……)
安全security-reviewer—
MVP 內部迴圈/gan-build "<簡述>" --skip-planner驅動 gan-generator → gan-evaluator;調整 --max-iterations / --pass-threshold

語言審查者應與儲存庫相符(參見儲存庫本身的 CLAUDE.md)。

安全審查觸發條件

當差異觸及以下任一項目時,引入 security-reviewer: 驗證或授權、使用者輸入處理、資料庫查詢、檔案系統路徑、 外部 API 呼叫、密碼學、或祕密 / 憑證。(根據 rules/common/security.md。)

交接產出

流程不攜帶隱藏狀態 — 規劃文件即為交接:

  • task_list(來自規劃階段)驅動實作迴圈。
  • 較大的工作可能還會在儲存庫的 docs/ 目錄下產出 PRD / architecture / system_design, 根據 rules/common/development-workflow.md。
  • 審查發現(CRITICAL / HIGH)必須在閘門 2 前解決。

驗證

  • 規模層級已陳述並與工作相符
  • 閘門 1(規劃)與閘門 2(提交)皆已遵守
  • security-reviewer 僅在觸及安全觸發條件時執行
  • 提交為 conventional 格式且範圍限於單一邏輯變更
  • 新增/變更行為有測試;覆蓋率 ≥ 80% 根據 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.

相關技能