replit-local-dev-loop
Configure Replit development workflow with hot reload, Webview, and Replit Agent. Use when setting up dev server, configuring run commands, debugging in Workspace, or using Replit Agent for AI-assisted development. Trigger with phrases like "replit dev server", "replit hot reload", "replit local development", "replit agent", "replit workflow".
What this skill does
# 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
```toml
# .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:
```toml
# 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:**
```toml
# .replit
run = "npx tsx watch src/index.ts"
```
```json
{
"scripts": {
"dev": "tsx watch src/index.ts",
"test": "vitest",
"test:watch": "vitest --watch"
}
}
```
**Python with Flask auto-reload:**
```toml
run = "python main.py"
[env]
FLASK_DEBUG = "1"
```
```python
# 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:**
```toml
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`:
```typescript
// 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', () => ...);
```
```toml
[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:
```typescript
// 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.
```markdown
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
```toml
# .replit
[unitTest]
language = "nodejs"
```
```typescript
// __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
| Error | Cause | Solution |
|-------|-------|----------|
| Webview blank | App not on 0.0.0.0 | Bind to `0.0.0.0`, not `localhost` |
| Port already in use | Previous run active | Click "Stop" then "Run" |
| Module not found | Package missing | Use Packages tool or `npm install` |
| Hot reload broken | Wrong run command | Use `tsx watch` or `nodemon` |
| Agent stalls | Complex prompt | Break into smaller requests |
## Resources
- [Configuring Your Repl](https://docs.replit.com/replit-workspace/configuring-repl)
- [Replit Agent](https://docs.replit.com/replitai/agent)
- [Database FAQ](https://docs.replit.com/hosting/database-faq)
## Next Steps
See `replit-sdk-patterns` for production code patterns or `replit-deploy-integration` to deploy.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.