Back to Details

blueprint

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Blueprint — Construction Plan Generator

Blueprint — 施工计划生成器

Turn a one-line objective into a step-by-step construction plan that any coding agent can execute cold.
将单行目标转换为任何编码Agent都能直接执行的分步施工计划。

When to Use

使用场景

  • Breaking a large feature into multiple PRs with clear dependency order
  • Planning a refactor or migration that spans multiple sessions
  • Coordinating parallel workstreams across sub-agents
  • Any task where context loss between sessions would cause rework
Do not use for tasks completable in a single PR, fewer than 3 tool calls, or when the user says "just do it."
  • 将大型功能拆分为具有明确依赖顺序的多个PR
  • 规划跨多会话的重构或迁移工作
  • 协调子Agent之间的并行工作流
  • 任何会话间上下文丢失会导致返工的任务
禁止使用场景：任务可通过单个PR或少于3次工具调用完成，或用户要求“直接执行”。

How It Works

工作原理

Blueprint runs a 5-phase pipeline:
  1. Research — Pre-flight checks (git, gh auth, remote, default branch), then reads project structure, existing plans, and memory files to gather context.
  2. Design — Breaks the objective into one-PR-sized steps (3–12 typical). Assigns dependency edges, parallel/serial ordering, model tier (strongest vs default), and rollback strategy per step.
  3. Draft — Writes a self-contained Markdown plan file to 
    plans/
    . Every step includes a context brief, task list, verification commands, and exit criteria — so a fresh agent can execute any step without reading prior steps.
  4. Review — Delegates adversarial review to a strongest-model sub-agent (e.g., Opus) against a checklist and anti-pattern catalog. Fixes all critical findings before finalizing.
  5. Register — Saves the plan, updates memory index, and presents the step count and parallelism summary to the user.
Blueprint detects git/gh availability automatically. With git + GitHub CLI, it generates full branch/PR/CI workflow plans. Without them, it switches to direct mode (edit-in-place, no branches).
Blueprint运行一个5阶段流程：
  1. 调研阶段 — 执行预检（git、gh认证、远程仓库、默认分支），然后读取项目结构、现有计划和内存文件以收集上下文信息。
  2. 设计阶段 — 将目标拆分为单个PR规模的步骤（通常3-12个）。为每个步骤分配依赖关系、并行/串行顺序、模型层级（最强模型 vs 默认模型）以及回滚策略。
  3. 起草阶段 — 将独立的Markdown计划文件写入
    plans/
    目录。每个步骤都包含上下文简介、任务列表、验证命令和退出标准，新Agent无需查看之前的步骤即可执行任何步骤。
  4. 审查阶段 — 委托最强模型子Agent（如Opus）根据涵盖完整性、依赖正确性和反模式检测的检查清单进行对抗性审查。在最终确定前修复所有关键问题。
  5. 注册阶段 — 保存计划、更新内存索引，并向用户展示步骤数量和并行性摘要。
Blueprint会自动检测git/gh的可用性。当有git + GitHub CLI时，它会生成完整的分支/PR/CI工作计划；没有时，则切换为直接模式（原地编辑，无分支）。

Examples

示例

Basic usage

基础用法

/blueprint myapp "migrate database to PostgreSQL"
Produces 
plans/myapp-migrate-database-to-postgresql.md
with steps like:
  • Step 1: Add PostgreSQL driver and connection config
  • Step 2: Create migration scripts for each table
  • Step 3: Update repository layer to use new driver
  • Step 4: Add integration tests against PostgreSQL
  • Step 5: Remove old database code and config
/blueprint myapp "migrate database to PostgreSQL"
生成
plans/myapp-migrate-database-to-postgresql.md
文件，包含以下步骤：
  • 步骤1：添加PostgreSQL驱动和连接配置
  • 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
  • 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

Multi-agent project

多Agent项目

/blueprint chatbot "extract LLM providers into a plugin system"
Produces a plan with parallel steps where possible (e.g., "implement Anthropic plugin" and "implement OpenAI plugin" run in parallel after the plugin interface step is done), model tier assignments (strongest for the interface design step, default for implementation), and invariants verified after every step (e.g., "all existing tests pass", "no provider imports in core").
/blueprint chatbot "extract LLM providers into a plugin system"
生成的计划会在可能的地方包含并行步骤（例如，在插件接口步骤完成后，“实现Anthropic插件”和“实现OpenAI插件”可并行执行），并分配模型层级（接口设计步骤使用最强模型，实现步骤使用默认模型），且每个步骤后都会验证不变量（例如，“所有现有测试通过”、“核心代码中无提供商导入”）。

Key Features

核心特性

  • Cold-start execution — Every step includes a self-contained context brief. No prior context needed.
  • Adversarial review gate — Every plan is reviewed by a strongest-model sub-agent against a checklist covering completeness, dependency correctness, and anti-pattern detection.
  • Branch/PR/CI workflow — Built into every step. Degrades gracefully to direct mode when git/gh is absent.
  • Parallel step detection — Dependency graph identifies steps with no shared files or output dependencies.
  • Plan mutation protocol — Steps can be split, inserted, skipped, reordered, or abandoned with formal protocols and audit trail.
  • Zero runtime risk — Pure Markdown skill. The entire repository contains only 
    .md
    files — no hooks, no shell scripts, no executable code, no 
    package.json
    , no build step. Nothing runs on install or invocation beyond Claude Code's native Markdown skill loader.
  • 冷启动执行 — 每个步骤都包含独立的上下文简介，无需前置上下文。
  • 对抗性审查关卡 — 每个计划都会由最强模型子Agent根据涵盖完整性、依赖正确性和反模式检测的检查清单进行审查。
  • 分支/PR/CI工作流 — 内置到每个步骤中。当没有git/gh时，会平稳降级为直接模式。
  • 并行步骤检测 — 依赖关系图可识别无共享文件或输出依赖的步骤。
  • 计划变更协议 — 可通过正式协议和审计跟踪对步骤进行拆分、插入、跳过、重排序或废弃操作。
  • 零运行时风险 — 纯Markdown Skill。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。除了Claude Code原生的Markdown Skill加载器外，安装或调用时无任何代码运行。

Installation

安装

This skill ships with Everything Claude Code. No separate installation is needed when ECC is installed.
该Skill随Everything Claude Code（ECC）一同发布。安装ECC后无需单独安装。

Full ECC install

完整ECC安装

If you are working from the ECC repository checkout, verify the skill is present with:
bash
test -f skills/blueprint/SKILL.md
To update later, review the ECC diff before updating:
bash
cd /path/to/everything-claude-code
git fetch origin main
git log --oneline HEAD..origin/main       # review new commits before updating
git checkout <reviewed-full-sha>          # pin to a specific reviewed commit
如果您从ECC仓库检出代码工作，可通过以下命令验证该Skill是否存在：
bash
test -f skills/blueprint/SKILL.md
后续更新时，请先查看ECC的差异再进行更新：
bash
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>          # 固定到经过审核的特定提交

Vendored standalone install

独立打包安装

If you are vendoring only this skill outside the full ECC install, copy the reviewed file from the ECC repository into 
~/.claude/skills/blueprint/SKILL.md
. Vendored copies do not have a git remote, so update them by re-copying the file from a reviewed ECC commit rather than running 
git pull
.
如果您要在完整ECC安装之外单独使用该Skill，请将ECC仓库中经过审核的文件复制到
~/.claude/skills/blueprint/SKILL.md
。独立打包的副本没有git远程仓库，因此需通过从经过审核的ECC提交中重新复制文件来更新，而非运行
git pull
。

Requirements

要求

  • Claude Code (for 
    /blueprint
    slash command)
  • Git + GitHub CLI (optional — enables full branch/PR/CI workflow; Blueprint detects absence and auto-switches to direct mode)
  • 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会检测其是否存在并自动切换到直接模式）

Source

来源

Inspired by antbotlab/blueprint — upstream project and reference design.
灵感来源于antbotlab/blueprint — 上游项目和参考设计。