npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

create-prompt

v1.5.0

Published

Your daily prompt framework - creates organized AI prompts with smart auto-filling, context detection, and MCP context system.

Readme

create-prompt

Your daily prompt framework - organized AI prompts with smart auto-filling, context detection, and MCP support

Features

  • MCP Context System: Define personas, standards, schemas, and project context for AI-optimized prompts
  • Enhance Command: Generate contextualized prompts from casual intents
  • Multi-LLM Support: Optimize prompts for Claude, Cursor, GPT, and more
  • Project Structure Generation: Auto-generates project tree with customizable ignore patterns
  • Git Workflow Integration: Structured commit tracking with file change documentation
  • Auto-detection: Reads package.json to fill tools, versions, and environment

Installation

npm install -g create-prompt

Or use the short alias:

p

Quick Start

# 1. Initialize the MCP context system
p init

# 2. Edit your context files
#    .mcp/context/persona.md      - Define your AI persona
#    .mcp/context/standards.md    - Your coding standards
#    .mcp/context/instructions.md - Behavior rules

# 3. Generate contextual prompts
p e "create a login form with validation"

MCP Context System

The MCP (Model Context Protocol) system lets you define reusable context for generating optimized prompts.

Initialize MCP

p init    # or: p mi

Creates the .mcp directory structure:

.mcp/
├── prompts/              # Prompt templates (JSON)
│   ├── base.json
│   ├── ui.json
│   └── api.json
├── context/              # Project context (Markdown)
│   ├── persona.md        # AI persona definition
│   ├── standards.md      # Coding standards
│   ├── instructions.md   # Behavior rules
│   ├── project_structure.md
│   ├── history.md
│   └── latest_commit.md
├── schemas/              # Variable schemas (JSON/YAML)
│   └── colors.yaml
└── config.json           # MCP configuration

Generate Contextual Prompts

p enhance "create a signup button with primary color"
# or
p e "add user authentication API"

The enhance command:

  1. Parses your casual intent
  2. Loads relevant context from .mcp/context/
  3. Resolves variables from .mcp/schemas/
  4. Selects appropriate template from .mcp/prompts/
  5. Generates an optimized, contextualized prompt

Options:

| Flag | Short | Description | |------|-------|-------------| | --template | -t | Use specific template (ui, api, base) | | --target | -T | Target LLM (claude, cursor, gpt) | | --output | -o | Save to file | | --interactive | -i | Interactive mode | | --dry-run | -d | Preview without generating | | --no-context | - | Exclude context files | | --verbose | -V | Show detailed output | | --copy | - | Copy to clipboard |

Examples:

p e "create modal component" --template ui
p e "add REST endpoint" --template api --target cursor
p e "refactor auth service" --output prompt.md --verbose

Validate & List MCP Resources

p mcp-validate    # or: p mv - Check for errors
p mcp-list        # or: p ml - List all resources
p ml templates    # List only templates
p ml schemas -v   # List schemas with details

Project Commands

Generate Project Structure

p project-structure    # or: p ps

Generates .mcp/project_structure.md with your directory tree.

Custom ignore patterns - Create .mcp/ignore_files.txt:

public/images
public/css
*.log
dist/

Generate Files Markdown

p files-markdown    # or: p fm

Aggregates file contents into .mcp/requested_files.md.

Setup - Create .mcp/requested_files.txt:

src/index.js
src/components/Header.jsx
README.md

Git Workflow

Finish Your Work

p finish    # or: p f

Complete your work session:

  1. Describe what you did
  2. Review git status
  3. Add file-by-file descriptions (optional)
  4. Auto-generates .mcp/latest_commit.md
  5. Updates .mcp/context/history.md
  6. Performs git commit

Legacy Prompt Creation

For quick, standalone prompts without MCP context:

p              # Smart mode - asks for tags, task
p --quick      # Quick mode - minimal questions
p -q --no-history

Creates individual prompt files: .mcp/YYYYMMDD_NN_slug.md


Quick Reference

| Command | Shortcut | Description | |---------|----------|-------------| | p init | p mi | Initialize MCP context system | | p enhance <intent> | p e | Generate contextual prompt | | p mcp-validate | p mv | Validate MCP configuration | | p mcp-list | p ml | List MCP resources | | p project-structure | p ps | Generate project structure | | p files-markdown | p fm | Generate markdown from file list | | p finish | p f | Finish work with git commit | | p | - | Create standalone prompt | | p --quick | p -q | Quick prompt creation |


Workflow Example

# Initial setup (once per project)
p init                            # Initialize MCP
# Edit .mcp/context/persona.md with your AI persona
# Edit .mcp/context/standards.md with your standards

# Daily workflow
p ps                              # Update project structure
p e "implement user dashboard"    # Generate contextual prompt

# ... do your work ...

p f                               # Finish and commit

Programmatic API

const { mcp } = require('create-prompt');

const result = await mcp.generatePrompt(
  "create a signup form",
  { template: "ui", target: "claude" }
);

console.log(result.prompt);

License

MIT