Token导航 LogoToken导航

Agent Skill · 研究检索

blueprint-development(蓝图发展)

blueprint-development 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

blueprint-development 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 39,733。

总安装 1,371周安装 56GitHub Stars 28下载 444核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:blueprint-development(蓝图发展)
来源仓库:https://github.com/laurigates/claude-plugins
仓库路径:skills/blueprint-development
安装命令:
npx skills add https://github.com/laurigates/claude-plugins --skill blueprint-development
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/laurigates/claude-plugins --skill blueprint-development

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

blueprint-development 提供 Blueprint 开发方法论的指导,用于生成项目特定行为规则。适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。基于 PRD 生成工作流程命令和路径特定规则,支持团队协作开发。

安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/blueprint-development

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/laurigates/claude-plugins --skill blueprint-de…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

blueprint-development 怎么安装?

在终端执行 npx skills add https://github.com/laurigates/claude-plugins --skill blueprint-development。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

blueprint-development 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

blueprint-development 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/laurigates/claude-plugins --skill blueprint-development 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

blueprint-development 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

blueprint-development 用的人多吗?

公开数据是累计安装 1,371 次,近一周安装 56 次,下载 444 次,GitHub 28 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

blueprint-development 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
blueprint-development

蓝图发展 · 本页

1,37128执行命令未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

/blueprint:development

Guide and reference for the Blueprint Development methodology that generates project-specific behavioral rules and workflow commands from PRDs (Product Requirements Documents).

When to Use This Skill

Use this skill when...Use alternative when...
Starting Blueprint Development in a projectProject is already using Blueprint (use /blueprint:status)
Need to generate rules from PRDsStarting a brand new project with no PRD yet
Want project-specific behavioral guidelinesUsing generic development practices
Creating workflow automation for a projectWorking on isolated tasks without project context

For detailed rule templates, command templates, and generation guidelines, see REFERENCE.md.

Context

  • Blueprint initialized:!find docs/blueprint -maxdepth 1 -name 'manifest.json' -type f
  • PRDs present:!find docs/prds -name "*.md" -type f
  • Rules directory:!find.claude -maxdepth 1 -name 'rules' -type d
  • Existing rules:!find.claude/rules -maxdepth 1 -name "*.md"
  • Project type:!find. -maxdepth 1 \(-name 'package.json' -o -name 'pyproject.toml' -o -name 'Cargo.toml' -o -name 'go.mod' \) -type f -print -quit

Execution

Execute the complete Blueprint Development setup and rule generation workflow:

Step 1: Verify project readiness

Check context values above:

  1. If Blueprint initialized = "NO" → Error: "Blueprint not initialized. Run /blueprint:init first"
  2. If PRDs present = "0" → Error: "No PRDs found. Create at least one PRD in docs/prds/ before generating rules"
  3. If Rules directory = "NO" → Create: mkdir -p.claude/rules

Step 2: Analyze PRDs and extract patterns

Read all PRD files in docs/prds/ and extract:

  1. Architecture Patterns: Project structure, dependency injection, error handling, module boundaries, layering, code organization
  2. Testing Strategies: TDD workflow, test types (unit, integration, e2e), mocking patterns, coverage requirements
  3. Implementation Guides: Patterns for implementing feature types (APIs, UI, database, external services)
  4. Quality Standards: Code review checklist, performance baselines, security requirements, style standards

See REFERENCE.md for specific extraction patterns for each category.

Step 3: Generate four behavioral rules in .claude/rules/

Create project-specific rules that guide Claude's behavior during development:

Three required core rules:

  1. architecture-patterns.md - Project structure, design patterns, dependency management, error handling, integration patterns
  2. testing-strategies.md - TDD workflow, test structure, test types, mocking patterns, coverage requirements
  3. quality-standards.md - Code review checklist, performance baselines, security standards, style, documentation

One optional advanced rule (if applicable):

  1. implementation-guides.md - Step-by-step patterns for implementing specific feature types from PRDs

For each rule file:

  • Use templates from REFERENCE.md
  • Extract content directly from PRDs
  • Include code examples and specific references
  • Document rationale for architectural choices
  • Use imperative language ("Use...", "Follow...", "Ensure...")

See REFERENCE.md for detailed guidelines on creating effective rules.

Step 4: Generate workflow commands

Create project-specific workflow commands in .claude/skills/ or docs/blueprint/:

Six core commands:

  1. /blueprint:init - Initialize Blueprint Development structure
  2. /blueprint:generate-rules - Generate project rules from PRDs (main entry point)
  3. /blueprint:generate-commands - Generate workflow commands based on project type
  4. /blueprint:work-order - Create isolated work-order for subagent execution
  5. /project:continue - Analyze state and resume development
  6. /project:test-loop - Run automated TDD cycle

For each command:

  • Determine project type and language
  • Extract test runners, build commands, development workflows
  • Customize command implementations using REFERENCE.md
  • Verify with expected allowed-tools permissions

Step 5: Create mapping in manifest

Update docs/blueprint/manifest.json with:

{
  "generated": {
    "rules": [
      "architecture-patterns.md",
      "testing-strategies.md",
      "quality-standards.md",
      "implementation-guides.md"
    ],
    "commands": [
      "blueprint-init.md",
      "blueprint-generate-rules.md",
      "blueprint-generate-commands.md",
      "blueprint-work-order.md",
      "project-continue.md",
      "project-test-loop.md"
    ]
  },
  "source_prds": ["project-overview.md"],
  "last_generated": "ISO-8601-timestamp"
}

This enables regeneration without losing track of what was auto-generated vs. manually created.

Step 6: Test and validate

Verify rules and commands work correctly:

  1. Test rules apply: Check that Claude follows architecture-patterns, testing-strategies, and quality-standards during development
  2. Test commands execute: Run each command to verify it works as expected
  3. Verify output quality: Check that generated rules match PRD requirements and include concrete examples
  4. Refine as needed: Update rules and commands based on feedback and actual project development

Step 7: Report results and next steps

Create summary report:

  • Rules generated: {count} in .claude/rules/
  • Commands created: {count} (use /project:continue to start development)
  • Manifest updated with tracking metadata
  • Next steps:

1. Review generated rules for accuracy 2. Add project-specific additions or clarifications 3. Run /project:continue to begin Blueprint Development workflow 4. Use /blueprint:work-order to create isolated tasks for team members

Integration with Blueprint Development

This skill enables the core Blueprint Development workflow:

PRDs (requirements) - Rules (behavioral guidelines) - Commands (workflow automation) - Work-orders (isolated tasks)

By generating project-specific rules and commands from PRDs, Blueprint Development creates a self-documenting, AI-native development environment where behavioral guidelines, patterns, and quality standards are first-class citizens.

GitHub Work Order Integration

Work orders can be linked to GitHub issues for transparency and cooperative development. See REFERENCE.md for workflow modes (--no-publish, --from-issue N), label setup, completion workflow, and work order file format.

Agentic Optimizations

ContextAction
Check if rules exist`find.claude/rules -maxdepth 1 -name "*.md" \wc -l`
List existing rulesls -1.claude/rules/*.md 2>/dev/null
Count PRDs`ls docs/prds/*.md 2>/dev/null \wc -l`
Extract PRD sectionsUse Grep to find specific sections by heading pattern
Fast generationSkip manual review step, proceed with standard templates

Examples

See .claude/docs/blueprint-development/ for complete workflow documentation and examples.


For detailed rule templates, command examples, extraction patterns, and project-specific customization, see REFERENCE.md.

平台分布

Codex

35.09%
按下载量换算156

Claude

30.45%
按下载量换算135

Cursor

17.44%
按下载量换算77

Gemini CLI

9.55%
按下载量换算42

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/laurigates/claude-plugins --skill blueprint-development 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills