Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Score first-contributor readiness: README, install and test docs, license, CI, lockfile.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"repoready": {
"command": "npx",
"args": [
"-y",
"@reneturcios/repoready",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add repoready -- npx -y @reneturcios/repoready mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"repoready": {
"command": "npx",
"args": [
"-y",
"@reneturcios/repoready",
"mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"repoready": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/repoready",
"mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 CloudCorpRecords 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.0)于4天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js, Docker。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Recta
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Cheaper cross-chain stablecoin routes for AI agents; 5 % of the verified saving, nothing if none.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
A repository can be technically excellent and still lose its first contributor in the first ten minutes: no README to orient them, no install steps to follow, no test command to prove the setup worked. repoready scores that first experience — from the facts you supply, running nothing.
You hand it the repo's file list (with the README's content when you have it) and, optionally, the package.json scripts. It hands back eight checks in a fixed order, each with a pass or fail and an exact detail string:
test script is defined.github/workflows/The first four checks are essential. Alongside the checks, the result counts how many passed (out of 8), lists the essential checks that failed in check order, and sets ready to true exactly when no essential check failed. A repo can therefore score well on the supporting checks — license, contributing guide, CI, lockfile — and still be honestly marked not ready because a newcomer cannot install it or cannot run a test.
The README is the first file in input order whose basename, lowercased, is readme.md or starts with readme.. When its content was not supplied, the two documentation checks say so plainly (README content not supplied) rather than guessing from its name. Basename matching is case-insensitive throughout, CI requires the exact .github/workflows/ path prefix, and the lockfile check recognises package-lock.json, yarn.lock, pnpm-lock.yaml, Cargo.lock, poetry.lock, Pipfile.lock, and go.sum.
Malformed input — a missing or empty file list, a missing, empty, or duplicated file path, a non-string content, or a package_scripts value that is not a string — is a validation error naming the offending path, and no partial assessment is produced. The computation is pure and local: no network, no configuration, and nothing is executed.
npx @reneturcios/repoready assess --input args.json
npx @reneturcios/repoready --version
args.json contains the full arguments object:
{
"files": [ { "path": "README.md", "content": "# Demo\n\n## Install\n\nnpm install\n\nRun npm test to verify.\n" }, { "path": "LICENSE" }, { "path": "CONTRIBUTING.md" }, { "path": ".github/workflows/ci.yml" }, { "path": "package-lock.json" } ], "package_scripts": { "test": "node --test", "build": "tsc" } }
The assessment is printed as JSON:
{
"checks": [ { "id": "readme", "status": "pass", "detail": "README found at README.md" }, { "id": "install_docs", "status": "pass", "detail": "README documents installation" }, { "id": "test_script", "status": "pass", "detail": "a test script is defined" }, { "id": "test_command_docs", "status": "pass", "detail": "README documents a test command" }, { "id": "license", "status": "pass", "detail": "license file found at LICENSE" }, { "id": "contributing", "status": "pass", "detail": "contributing guide found at CONTRIBUTING.md" }, { "id": "ci", "status": "pass", "detail": "CI workflows found" }, { "id": "lockfile", "status": "pass", "detail": "lockfile found at package-lock.json" } ], "passed": 8, "total": 8, "essential_failures": [], "ready": true }
Exit codes: 0 on success, 1 on a runtime error (including an unreadable or invalid input file, or invalid input), 2 on a usage error.
npx -y @reneturcios/repoready mcp
MCP client config:
{
"mcpServers": { "repoready": { "command": "npx", "args": ["-y", "@reneturcios/repoready", "mcp"] } } }
assess_readiness — Assess first-contributor readiness from repo files and package scripts.files (array, required, at least one) — files as {path, content?} objects; path is unique across the set and content is used for the README checkspackage_scripts (object, optional) — package.json scripts as a string-to-string mapReturns {checks, passed, total, essential_failures, ready}.
docker run -i ghcr.io/cloudcorprecords/repoready
docker run --rm -v "$PWD:/w" ghcr.io/cloudcorprecords/repoready assess --input /w/args.json
npm install
npm run build # tsc -> dist/ npm test # tsx --test test/*.test.ts (pure local, no network) npm run dev # run the CLI from source
MIT — Copyright (c) 2026 Rene Turcios