RE

replit-local-dev-loop

Optimizes Replit development cycles with hot reload configuration, run commands, and preview setups.

Install

mkdir -p .claude/skills/replit-local-dev-loop && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7089" && unzip -o skill.zip -d .claude/skills/replit-local-dev-loop && rm skill.zip

Installs to .claude/skills/replit-local-dev-loop

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Configure Replit development workflow with hot reload, Webview, and
67 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Configure run commands and compile steps
  • Set up hot reloading for Node.js and Python
  • Bind applications to 0.0.0.0 for Webview access
  • Use Replit Agent for autonomous development
  • Configure unit testing environments

How it works

It defines the .replit configuration parameters for run commands, environment variables, and port binding to ensure the workspace correctly serves the application to the Webview.

Inputs & outputs

You give it
Development workflow requirements
You get back
A configured, hot-reloading development environment

When to use replit-local-dev-loop

  • Configuring dev server hot reloading
  • Setting up multi-service run commands
  • Optimizing build steps for TypeScript or Go
  • Configuring Replit workspace environment

About this skill

Replit Local Dev Loop

Overview

Configure the Replit Workspace development cycle: run commands, hot reloading, port configuration, Webview preview, dev/production database separation, and Replit Agent for AI-assisted building.

Prerequisites

  • Replit App with .replit configured
  • Node.js or Python project initialized
  • Familiarity with Replit Workspace UI

Instructions

Step 1: Configure Run Commands

# .replit — run determines what happens when you click "Run"

# Simple string command
run = "npm run dev"

# Array form (recommended for deployment)
# run = ["sh", "-c", "npm run dev"]

# Multiple services simultaneously
# run = "npm run api & npm run frontend & wait"

entrypoint = "index.ts"

Compiled languages need a compile step:

# TypeScript
compile = "npx tsc -b"
run = "node dist/index.js"

# Go
compile = "go build -o main ."
run = "./main"

Step 2: Hot Reload Setup

Node.js with tsx watch:

# .replit
run = "npx tsx watch src/index.ts"
{
  "scripts": {
    "dev": "tsx watch src/index.ts",
    "test": "vitest",
    "test:watch": "vitest --watch"
  }
}

Python with Flask auto-reload:

run = "python main.py"

[env]
FLASK_DEBUG = "1"
# main.py — Flask auto-reloads in debug mode
if __name__ == '__main__':
    app.run(host='0.0.0.0', port=3000, debug=True)

Vite/Next.js dev server:

run = "npm run dev"

[env]
PORT = "3000"

Step 3: Port Configuration

Replit routes external traffic to your app's port. Your app must listen on 0.0.0.0:

// Correct — Replit can reach this
app.listen(3000, '0.0.0.0', () => console.log('Ready'));

// Wrong — unreachable from Webview
// app.listen(3000, '127.0.0.1', () => ...);
[deployment]
run = ["sh", "-c", "npm start"]
deploymentTarget = "autoscale"
# Ignore ports used by dev tools only
ignorePorts = [3001, 5555]

Use the Networking tool in the sidebar to view active port mappings.

Step 4: Dev vs Production Database

Replit provides separate development and production databases:

// Databases auto-switch based on context:
// - Workspace "Run" button -> development database
// - Deployed app -> production database
// Both use the same DATABASE_URL env var — no code changes needed

import { Pool } from 'pg';
const pool = new Pool({
  connectionString: process.env.DATABASE_URL,
  ssl: { rejectUnauthorized: false },
});

View database settings in the PostgreSQL pane:

  • Development tab: data for workspace testing
  • Production tab: live customer data (only after deployment)

Step 5: Using Replit Agent

Replit Agent (v4) builds apps from natural language prompts. It creates files, installs packages, runs tests, and can work up to 200 minutes autonomously.

Effective Agent prompts:
- "Build a todo app with user auth, PostgreSQL, and a React frontend"
- "Add a /api/search endpoint with full-text search"
- "Fix the login flow - users lose auth after redirect"

Agent 4 features:
- Parallel task forks (splits work, combines results)
- Self-testing and error correction
- Full .replit and replit.nix configuration
- Works with any framework

Step 6: Testing in Workspace

# .replit
[unitTest]
language = "nodejs"
// __tests__/api.test.ts
import { describe, it, expect } from 'vitest';

describe('Health Check', () => {
  it('returns ok', async () => {
    const res = await fetch('http://localhost:3000/health');
    expect(res.ok).toBe(true);
  });
});

Development Workflow Summary

1. Edit code in Workspace editor
2. Click "Run" -> dev server starts with hot reload
3. Webview tab shows live preview
4. Console tab shows server logs
5. Shell tab for CLI commands
6. Secrets tab (lock icon) for env vars
7. Database pane for PostgreSQL / KV data
8. Deploy when ready -> production database activates

Error Handling

ErrorCauseSolution
Webview blankApp not on 0.0.0.0Bind to 0.0.0.0, not localhost
Port already in usePrevious run activeClick "Stop" then "Run"
Module not foundPackage missingUse Packages tool or npm install
Hot reload brokenWrong run commandUse tsx watch or nodemon
Agent stallsComplex promptBreak into smaller requests

Resources

Next Steps

See replit-sdk-patterns for production code patterns or replit-deploy-integration to deploy.

When not to use it

  • When developing locally outside of the Replit Workspace

Prerequisites

Replit App with .replit configuredNode.js or Python project initializedFamiliarity with Replit Workspace UI

Limitations

  • App must listen on 0.0.0.0 to be reachable from Webview
  • Agent is limited to 200 minutes of autonomous work

How it compares

It provides specific configuration for Replit's unique environment-aware database routing and port mapping rather than generic local development setups.

Compared to similar skills

replit-local-dev-loop side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
replit-local-dev-loop (this skill)125dReviewIntermediate
browser-tools69moReviewIntermediate
browser-extension-builder66moNo flagsIntermediate
obsidian-data-handling425dNo flagsAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

More by jeremylongshore

View all by jeremylongshore

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

ollama-setup

jeremylongshore

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

1167

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

generating-database-seed-data

jeremylongshore

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

1033

cursor-codebase-indexing

jeremylongshore

Execute set up and optimize Cursor codebase indexing. Triggers on "cursor index setup", "codebase indexing", "index codebase", "cursor semantic search". Use when working with cursor codebase indexing functionality. Trigger with phrases like "cursor codebase indexing", "cursor indexing", "cursor".

885

testing-mobile-apps

jeremylongshore

Execute mobile app testing on iOS and Android devices/simulators. Use when performing specialized testing. Trigger with phrases like "test mobile app", "run iOS tests", or "validate Android functionality".

810

Search skills

Search the agent skills registry