shuguang1994/project-blueprint
一条命令让任何项目为AI代理做好准备。自适应技术栈检测(7种语言 × 14种框架 × 61个组件),自动生成AGENTS.md、文档框架、CI/CD及测试基础设施。
Project Overview项目介绍
Project Blueprint is an autonomous AI agent skill that prepares any new or existing project for AI-driven development by generating a customized set of coding conventions and project configurations. It works with over 28 different AI coding agents and tools, including Claude Code, Cursor, Codex, GitHub Copilot, DeepSeek Harness, and more. To install it globally from GitHub, you can run the npx command npx skills add shuguang1994/project-blueprint, and DSH users can install it directly via the DSH plugin command dsh plugin --profile web add 'github:shuguang1994/project-blueprint'. Chinese users can also install from a Gitee mirror without a proxy.
The typical workflow for using Project Blueprint is simple: after installation, all a user needs to do is ask their AI agent to "Initialize this project's development standards" and the skill handles the rest. It first scans the project to classify files, infer dependencies, identify the project structure, and determine the project's business type. Then it assembles a customized AGENTS.md file, documentation skeleton, Git configuration, CI/CD pipeline setup, testing policy, and self-maintenance rules, all tailored to the project's actual tech stack. This tool is built for any developer or team that uses AI coding assistants to build new software projects.
Project Blueprint is released under the permissive MIT license, so it can be used freely for both personal and commercial projects. The only requirements to use it are an AI coding agent that supports the SKILL.md format, and a working installation of Node.js to run the installation command. It uses an incremental update mode that never overwrites existing files on existing projects, only filling gaps in existing project configuration. The project also welcomes community contributions to expand its knowledge base of frameworks, coding conventions, and AI best practices.
Project Blueprint 是一个可复用的 AI 智能体技能,支持为任意新项目一键生成符合 AGENTS.md 行业规范的完整 AI 编程规范体系。它不是静态模板,而是能自动扫描项目文件、智能分类依赖,从 70+ 组件知识库动态生成定制内容。它支持超过 28 款 AI 编程智能体,包括 Claude Code、Cursor、Codex、DeepSeek Harness 等,可通过 npx 或 DSH 插件命令安装。
对于开发者来说,只需要向 AI 智能体输入「初始化本项目的开发规范」,Project Blueprint 就会自动完成后续全部工作:从自主扫描项目文件到分类依赖、识别项目结构、推理业务类型,最终生成适配项目技术栈的 AGENTS.md、文档框架、CI/CD 配置、Git 规范和测试策略。它适合所有使用 AI 编程助手的开发团队和个人开发者,尤其适合新建项目快速建立标准。
该项目基于 MIT 许可证开源,可免费使用和修改。使用前提是你的 AI 编程智能体支持 SKILL.md 格式,并且需要安装 Node.js 来运行安装命令。它采用增量模式,不会覆盖已有项目的现有文件,只会补充缺失内容,项目知识库也欢迎社区贡献新的语言框架和规则。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:project-blueprint(shuguang1994/project-blueprint)
仓库:https://github.com/shuguang1994/project-blueprint
本站详情页:https://www.yhbd.top/plugins/shuguang1994-project-blueprint/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 22 · 最近提交 2026-09-18 · 主语言 JavaScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- 22 stars - an early-stage project星标 22,属于早期项目
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add 'github:shuguang1994/project-blueprint'
把 shuguang1994/project-blueprint 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
Project Blueprint 🏗️
One command to make any project AI-agent-ready. 一键为新项目建立完整 AI 编程规范体系。
What is this?
Project Blueprint is a reusable AI agent skill that transforms any new project into an AI-ready codebase in one sentence. It's not a static template — it's an autonomous discovery engine: scan your project files, intelligently classify dependencies, and dynamically assemble a customized AGENTS.md, documentation skeleton, CI/CD pipeline, and testing policy from a 95-entry component knowledge base.
Just say: "Initialize this project's development standards" and the agent does the rest.
Quick Install
# Global (GitHub)
npx skills add shuguang1994/project-blueprint
# China (Gitee mirror, no proxy needed)
npx skills add https://gitee.com/shuguang1994/project-blueprint.git
# Update later
npx skills update project-blueprint
DeepSeek Harness (dsh) plugin:
dsh plugin --profile web add 'github:shuguang1994/project-blueprint'
Supported agents: Claude Code, Cursor, GitHub Copilot, Codex, Windsurf, Trae, OpenCode, DeepSeek Harness, and 28+ more.
Why
AGENTS.md is now an industry standard in 2026 — used by 60,000+ open-source repos, co-promoted by OpenAI, Google, Anthropic, and Microsoft. 76% of developers use AI coding assistants (Stack Overflow 2025), but without AGENTS.md, AI agents are like "new hires with no onboarding" — producing inconsistent code styles, broken architecture, and failing CI.
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
akira399/dsh-novel-writer
linhut/gongwen-skill
yannicksong0106/dsh-550c-boot
hr98w/dsh-memory
omdsh-dev/dsh-advisor
SummerSec/AI-Inner-Os
wlj521/dsh-ui-tweaks