Communitygithub.com

Blueprint — 建構計畫產生器

將一句目標轉換為逐步的建構計畫,任何編碼代理都能冷啟動執行。

Blueprint — 建構計畫產生器 是什麼?

Blueprint 是一個純 Markdown 技能,專為 Claude Code 等編碼代理設計,能將一行目標轉換為詳細、逐步的建構計畫。它透過一個五階段管線運作:研究(收集 git/GitHub 上下文)、設計(將目標分解為可單獨拉取請求的步驟)、草稿(將計畫寫入 `plans/` 目錄)、審查(由最強模型子代理進行對抗性審查)及註冊(保存計畫並更新記憶體索引)。Blueprint 自動偵測 git 和 GitHub CLI 的可用性,以啟用完整的分支/PR/CI 工作流程,或在沒有時優雅地降級為直接模式。主要功能包括冷啟動執行(每個步驟都包含自足的上下文摘要)、對抗性審查閘門、並行步驟偵測、透過正式協定的計畫變異,以及零運行時風險(整個技能僅由 `.md` 檔案組成,無可執行代碼)。

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

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

Blueprint — 建構計畫產生器 是做什麼的?

將一句目標轉換為逐步的建構計畫,任何編碼代理都能冷啟動執行。

使用時機

  • 將大型功能拆解為多個具有明確依賴順序的拉取請求
  • 規劃跨越多次會話的重構或遷移
  • 協調跨子代理的並行工作流
  • 任何會話間上下文遺失會導致重做的任務

請勿使用 於可在單次拉取請求中完成、少於 3 次工具呼叫的任務,或當使用者說「直接做」的時候。

運作方式

Blueprint 執行一個五階段管線:

  1. 研究 — 前置檢查 (git、gh auth、遠端、預設分支),然後讀取專案結構、現有計畫和記憶體檔案以收集上下文。
  2. 設計 — 將目標分解為一次拉取請求大小的步驟 (通常 3–12 個)。為每個步驟分配依賴邊緣、並行/序列順序、模型層級 (最強 vs 預設) 和回滾策略。
  3. 草稿 — 將自包含的 Markdown 計畫檔案寫入 plans/。每個步驟都包含上下文摘要、任務清單、驗證命令和退出條件 —— 讓全新的代理無需閱讀先前步驟即可執行任何步驟。
  4. 審查 — 將對抗性審查委派給最強模型子代理 (例如 Opus),針對檢查清單和反模式目錄進行審查。在最終確定前修復所有關鍵發現。
  5. 註冊 — 保存計畫,更新記憶體索引,並向使用者顯示步驟數量和並行度摘要。

Blueprint 會自動偵測 git/gh 的可用性。使用 git + GitHub CLI 時,它會產生完整的分支/PR/CI 工作流程計畫。沒有時,它會切換為直接模式 (原地編輯,無分支)。

範例

基本用法

/blueprint myapp "將資料庫遷移至 PostgreSQL"

產生 plans/myapp-migrate-database-to-postgresql.md,包含如下步驟:

  • 步驟 1:新增 PostgreSQL 驅動程式和連線設定
  • 步驟 2:為每個表格建立遷移腳本
  • 步驟 3:更新儲存層以使用新驅動程式
  • 步驟 4:新增針對 PostgreSQL 的整合測試
  • 步驟 5:移除舊的資料庫程式碼和設定

多代理專案

/blueprint chatbot "將 LLM 提供者提取為外掛系統"

產生一個計畫,其中在可能的情況下包含並行步驟 (例如「實作 Anthropic 外掛」和「實作 OpenAI 外掛」在外掛介面步驟完成後並行執行)、模型層級指派 (介面設計步驟使用最強模型,實作使用預設模型),以及在每個步驟後驗證的不變量 (例如「所有現有測試通過」、「核心中無提供者匯入」)。

主要功能

  • 冷啟動執行 — 每個步驟都包含自足的上下文摘要。無需先前的上下文。
  • 對抗性審查閘門 — 每個計畫都由最強模型子代理針對檢查清單進行審查,涵蓋完整性、依賴正確性和反模式偵測。
  • 分支/PR/CI 工作流程 — 內建於每個步驟。當缺少 git/gh 時優雅降級為直接模式。
  • 並行步驟偵測 — 依賴圖識別沒有共享檔案或輸出依賴的步驟。
  • 計畫變異協定 — 步驟可以透過正式協定和審計軌跡進行拆分、插入、跳過、重新排序或廢棄。
  • 零執行期風險 — 純 Markdown 技能。整個儲存庫僅包含 .md 檔案——無掛鉤、無 shell 腳本、無可執行代碼、無 package.json、無建置步驟。除了 Claude Code 的原生 Markdown 技能載入器之外,安裝或呼叫時不會執行任何操作。

安裝

此技能隨 Everything Claude Code 一起提供。安裝 ECC 後無需單獨安裝。

完整 ECC 安裝

如果您從 ECC 儲存庫檢出中工作,請使用以下命令驗證技能是否存在:

test -f skills/blueprint/SKILL.md

之後若要更新,請先檢視 ECC 差異再更新:

cd /path/to/everything-claude-code
git fetch origin main
git log --oneline HEAD..origin/main       # 更新前檢視新提交
git checkout <reviewed-full-sha>          # 固定至特定經審查的提交

自備獨立安裝

如果您只在完整 ECC 安裝之外自備此技能,請將經審查的檔案從 ECC 儲存庫複製到 ~/.claude/skills/blueprint/SKILL.md。自備副本沒有 git 遠端,因此請透過從經審查的 ECC 提交重新複製檔案來更新,而不是執行 git pull。

需求

  • Claude Code (用於 /blueprint 斜線命令)
  • Git + GitHub CLI (可選 —— 啟用完整的分支/PR/CI 工作流程;Blueprint 會偵測缺失並自動切換為直接模式)

來源

靈感來自 antbotlab/blueprint —— 上游專案和參考設計。

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