Communitygithub.com

Blueprint — 构建计划生成器

将一行目标转化为逐步执行的构建计划,任何编码代理都能直接执行。

Blueprint — 构建计划生成器 是什么?

Blueprint 是一款针对 AI 编码代理(如 Claude Code)的纯 Markdown 技能,旨在将复杂的大型任务分解为多个独立的拉取请求(PR)或执行步骤,并附带清晰的依赖关系和并行执行路径。它通过一个五阶段管线(研究、设计、起草、审查、注册)运行,自动进行预检(git/gh 可用性检测)、项目结构分析、依赖图构建以及对抗性审查,确保生成的计划完整且无反模式。每个步骤都包含自包含的上下文简报、任务列表、验证命令和退出标准,支持冷启动执行——新代理无需阅读先前步骤即可开始任何步骤。Blueprint 主要适用于跨会话重构、迁移、多代理协作等场景,当任务可在一个 PR 内完成时则不建议使用。它与 git 和 GitHub CLI 原生集成,可生成完整的分支/PR/CI 工作流计划;在缺少这些工具时会自动降级为直接编辑模式。该技能仅包含 .md 文件,无运行时风险。

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

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

Blueprint — 构建计划生成器 是做什么的?

将一行目标转化为逐步执行的构建计划,任何编码代理都能直接执行。

何时使用

  • 将大型功能拆分为多个拉取请求(PR),并明确依赖顺序
  • 规划跨多个会话的重构或迁移
  • 跨子代理协调并行工作流
  • 任何因会话间上下文丢失而导致返工的任务

不要用于 可在单个 PR 内完成的任务、少于 3 次工具调用的任务,或用户说“直接做”的情况。

工作原理

Blueprint 运行一个五阶段管线:

  1. 研究 — 预检(git、gh 认证、远程仓库、默认分支),然后读取项目结构、现有计划和记忆文件以收集上下文。
  2. 设计 — 将目标分解为适合单个 PR 的步骤(通常 3–12 个)。为每个步骤分配依赖边、并行/串行顺序、模型层级(最强 vs 默认)和回滚策略。
  3. 起草 — 将自包含的 Markdown 计划文件写入 plans/。每个步骤都包含上下文简报、任务列表、验证命令和退出标准——这样新代理无需阅读先前步骤即可执行任何步骤。
  4. 审查 — 将对抗性审查委托给最强模型子代理(例如 Opus),对照检查清单和反模式目录进行审查。在最终确定前修复所有关键发现。
  5. 注册 — 保存计划,更新记忆索引,并向用户显示步骤数和并行度摘要。

Blueprint 会自动检测 git/gh 可用性。当有 git 和 GitHub CLI 时,它会生成完整的分支/PR/CI 工作流计划;没有这些工具时,它会切换到直接模式(原地编辑,无分支)。

示例

基本用法

/blueprint myapp "将数据库迁移到 PostgreSQL"

生成 plans/myapp-migrate-database-to-postgresql.md,包含类似以下步骤:

  • 步骤 1:添加 PostgreSQL 驱动程序和连接配置
  • 步骤 2:为每个表创建迁移脚本
  • 步骤 3:更新仓库层以使用新驱动程序
  • 步骤 4:添加针对 PostgreSQL 的集成测试
  • 步骤 5:移除旧数据库代码和配置

多代理项目

/blueprint chatbot "将 LLM 提供者提取为插件系统"

生成一个包含可能并行步骤的计划(例如,“实现 Anthropic 插件”和“实现 OpenAI 插件”在插件接口步骤完成后并行运行)、模型层级分配(接口设计步骤使用最强模型,实现步骤使用默认模型),以及在每个步骤后验证的不变量(例如,“所有现有测试通过”、“核心中没有提供者导入”)。

关键特性

  • 冷启动执行 — 每个步骤都包含自包含的上下文简报。无需先前上下文。
  • 对抗性审查门 — 每个计划都由最强模型子代理对照检查清单进行审查,涵盖完整性、依赖正确性和反模式检测。
  • 分支/PR/CI 工作流 — 内置于每个步骤中。当 git/gh 缺失时优雅降级到直接模式。
  • 并行步骤检测 — 依赖图识别没有共享文件或输出依赖的步骤。
  • 计划变更协议 — 步骤可以拆分、插入、跳过、重新排序或放弃,并附有正式协议和审计追踪。
  • 零运行时风险 — 纯 Markdown 技能。整个仓库仅包含 .md 文件——无钩子、无 shell 脚本、无可执行代码、无 package.json、无构建步骤。安装或调用时除了 Claude Code 的原生 Markdown 技能加载器外,不会运行任何内容。

安装

此技能随 Everything Claude Code 提供。安装 ECC 后无需单独安装。

完整 ECC 安装

如果你正在 ECC 仓库 checkout 中工作,请使用以下命令验证技能是否存在:

test -f skills/blueprint/SKILL.md

后续更新时,请先查看 ECC 差异再更新:

cd /path/to/everything-claude-code
git fetch origin main
git log --oneline HEAD..origin/main       # 查看新提交后再更新
git checkout <reviewed-full-sha>          # 固定到特定的审查提交

独立 vendored 安装

如果你在完整 ECC 安装之外仅 vendoring 此技能,请将审查后的文件从 ECC 仓库复制到 ~/.claude/skills/blueprint/SKILL.md。Vendored 副本没有 git 远程仓库,因此请通过从审查过的 ECC 提交重新复制文件来更新,而不是运行 git pull。

要求

  • Claude Code(用于 /blueprint 斜杠命令)
  • Git + GitHub CLI(可选——启用完整的分支/PR/CI 工作流;Blueprint 会检测缺失并自动切换到直接模式)

来源

受 antbotlab/blueprint 启发——上游项目及参考设计。

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