The Builder's Prompt Library
Search 3,323 graded AI prompts for software builders; fetch any prompt by slug. No key needed.
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
claude mcp add --transport http the-builder-s-prompt-library 'https://buildersprompt.com/mcp'{
"mcpServers": {
"the-builder-s-prompt-library": {
"type": "http",
"url": "https://buildersprompt.com/mcp"
}
}
}Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
Sommaire
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
| Path | What it is |
|---|---|
data/prompts.json | Every 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/*.json | The same rows split by delivery stage: idea, design, build, test, secure, ship. |
data/index.tsv | One line per prompt: stage, category, grade, score, slug, title. Good for grep and awk. |
prompts/<stage>/<slug>.md | One 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.
Questions fréquentes
Qu'est-ce que The Builder's Prompt Library ?
Search 3,323 graded AI prompts for software builders; fetch any prompt by slug. No key needed.
Comment installer The Builder's Prompt Library ?
Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http the-builder-s-prompt-library 'https://buildersprompt.com/mcp'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour The Builder's Prompt Library ?
Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.
The Builder's Prompt Library est-il open source ?
Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.
Qui maintient The Builder's Prompt Library ?
Il est publié par ADahling. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.