The Builder's Prompt Library

io.github.ADahling由 GitHub 账号 ADahling 发布v1.0.0更新于 Oct 25, 2026

Search 3,323 graded AI prompts for software builders; fetch any prompt by slug. No key needed.

已验证Streamable HTTP可网页运行开发者工具AI 与机器学习

概览

AI 生成的概览

一个公开、无需密钥的 MCP 服务器，让助手按关键词搜索并获取 3,323 条按评分标准分级、覆盖六个软件交付阶段的 AI 提示词。

可以做什么
按关键词搜索提示词，可按交付阶段或写作等级筛选，返回带 slug、标题、摘要、阶段、类别和等级的排序结果（search_prompts）。按 slug 获取单条提示词的全文和元数据，包括其适用运行环境（get_prompt）。列出六个交付阶段及每个阶段已发布提示词的数量（list_stages）。
适用场景
适合让助手为软件任务（如构思、设计、构建、测试、安全或发布）查找现成提示词，或把某条提示词的完整文本取到对话中。
运行要求
位于 buildersprompt.com 的远程 Streamable HTTP 端点；未声明需要 API 密钥、账户、环境变量或请求头。客户端需支持远程 MCP 连接。
安装前请注意
工具为只读，不要求写入或凭据。等级只反映提示词写作质量，不代表模型实测结果，应仅作写作参考。提示词含需替换的填空字段。按 CC BY 4.0 转载提示词需署名。

安装

在 SourceWeft 中

  1. 打开 控制台中的 The Builder's Prompt Library，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.ADahling%2Fbuilders-prompt-library/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "the-builder-s-prompt-library": {
      "type": "http",
      "url": "https://buildersprompt.com/mcp"
    }
  }
}

README

The Builder's Prompt Library, as data

3,323 rubric-graded AI prompts for every stage of shipping software, from idea to launch. This is the open data behind buildersprompt.com, exported from the live catalog so you can grep it, vendor it, load it into your own tools, or point an agent at it.

Built by Alicia Dahling and Peter Lowe. Free to read, copy and adapt under CC BY 4.0 (see LICENSE): keep the attribution, do what you like with the prompts.

What is in here

PathWhat it is
data/prompts.jsonEvery published prompt as one JSON array (title, summary, stage, category, difficulty, tags, variables, tips, prompt text, writing score and grade, hand-reviewed flag, canonical URL).
data/by-stage/*.jsonThe same rows split by delivery stage: idea, design, build, test, secure, ship.
data/index.tsvOne line per prompt: stage, category, grade, score, slug, title. Good for grep and awk.
prompts/<stage>/<slug>.mdOne Markdown file per prompt with YAML front matter, for editors, static-site generators and retrieval pipelines.

Fill-in fields look like {{project_name}}. Replace them before you paste.

How the grades work

Every prompt is scored 0 to 100 on a five-part writing rubric (clarity, specificity, format, variables, actionability) and stamped A+ (90+), A (80 to 89), B (70 to 79) or C (60 to 69). Anything below 60 is not published. The grade describes how well the prompt is written, not how well a model answered it. Prompts that were actually run in ChatGPT, Claude and Gemini, with the graded answers, are shown on their pages at buildersprompt.com under "Tested in real AI models". Twenty-two prompts were read line by line by a human and carry hand_reviewed: true.

Use it from an AI assistant instead

The library is also a public MCP server. Point Claude, Cursor, ChatGPT or any MCP client at https://buildersprompt.com/mcp (Streamable HTTP, JSON-RPC 2.0, no key) and you get three read tools: search_prompts, get_prompt and list_stages.

Freshness

This export is regenerated from the live database. Each prompt's updated_at is the last edit on the site. If you need a specific prompt's current text, its url is the source of truth.

Attribution

Please credit "The Builder's Prompt Library, buildersprompt.com" and link back when you republish prompts from this set. That is the whole license.

来源：README.md，提交 e9e31c7

工具

3

search_prompts

Search prompts

Search the Builder's Prompt Library (3,323 rubric-graded prompts for software delivery) by keyword. Optionally filter by delivery stage or prompt-writing grade. Returns ranked matches with slug, title, summary, stage, category, and grade. Grades and quality_score describe prompt writing, not tested model performance.

输入参数gradelimitquery必填stage

get_prompt

Get prompt

Fetch the full text and metadata of a single published prompt by its slug, including where it runs (any chat app, chat app with your code pasted in, a tool with web access, or a coding agent).

输入参数slug必填

list_stages

List stages

List the six delivery stages in the Builder's Prompt Library and how many published prompts each contains.

无需输入参数。

版本历史

1
  1. v1.0.0最新Oct 25, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。