buildover-setup

Set up and integrate BuildOver into any existing web project. BuildOver is an AI-powered dev tool that wraps a running web app with a floating chat widget via a reverse proxy — letting you ask Claude to modify source files in real-time with HMR. Use this skill when the user says /buildover-setup, asks to "add BuildOver to my project", "integrate BuildOver", "set up AI coding assistant on my dev server", or wants to connect BuildOver to their existing running application.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "buildover-setup" with this command: npx skills add zimins/buildover/zimins-buildover-buildover-setup

BuildOver Setup

BuildOver wraps your existing dev server with a reverse proxy + AI chat widget. You visit localhost:<buildover-port> instead of your original port, and a floating panel lets you ask Claude to edit your source files live with HMR.

Packages (all pulled in by the buildover CLI):

  • buildover — CLI (buildover dev)
  • buildover-server — auto-installed dependency
  • buildover-widget — auto-installed dependency

Workflow

1. Check Existing Installation

buildover --version 2>/dev/null || npx buildover --version 2>/dev/null

2. Install BuildOver

Global (recommended):

npm install -g buildover

Local dev dependency:

npm install --save-dev buildover
# pnpm add -D buildover / yarn add -D buildover

3. Detect Target Port

Read package.json to find the dev port:

cat package.json | grep -E '"dev"|"start"'

Common defaults if not specified:

  • 3000 — React CRA, Next.js
  • 5173 — Vite
  • 4200 — Angular
  • 8080 / 8000 — generic / Django / Flask

Ask the user to confirm if unclear.

4. Configure API Key

grep "ANTHROPIC_API_KEY" .env 2>/dev/null || echo "not set"

If missing, add to .env (create if needed):

ANTHROPIC_API_KEY=sk-ant-...

Get a key at https://console.anthropic.com/settings/keys.

The proxy and widget work without a key — only AI chat requires it.

5. Start BuildOver

# Global install:
buildover dev --target <target-port> --port <buildover-port>

# Local install:
npx buildover dev --target <target-port> --port <buildover-port>

Default --port is 4100. Use 10001 to avoid common conflicts.

Example (Next.js on 3000, BuildOver on 10001):

buildover dev --target 3000 --port 10001
# → Open http://localhost:10001

6. (Optional) Cloudflare Tunnel for Remote Access

If the user wants a public HTTPS URL:

# Install (macOS)
brew install cloudflared

# Authenticate & create tunnel
cloudflared tunnel login
cloudflared tunnel create <tunnel-name>

Create ~/.cloudflared/config.yml:

tunnel: <tunnel-id>
credentials-file: /Users/<username>/.cloudflared/<tunnel-id>.json

ingress:
  - hostname: your-subdomain.yourdomain.com
    service: http://localhost:<buildover-port>
  - service: http_status:404
cloudflared tunnel run <tunnel-name>

Verification Checklist

  • No ⚠ No authentication configured at startup → API key loaded ✓
  • Banner shows correct target and BuildOver URLs ✓
  • Opening http://localhost:<buildover-port> shows original site + floating chat button ✓
  • Sending a chat message triggers [Agent] logs in the server output ✓

Common Issues

IssueFix
EADDRINUSE on BuildOver portlsof -i :<port> → kill the process
⚠ No authentication configuredAdd ANTHROPIC_API_KEY to .env and restart server
Chat sends but no code changesCheck server logs for [Agent] Error — usually auth failure
Widget not visibleHard-refresh; check /buildover/widget.js returns 200
HMR not workingStart the original dev server before BuildOver

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

coupang-shopping

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

openclaw-version-monitor

监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明

Archived SourceRecently Updated
Coding

ask-claude

Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file operations confined to workspace. Use when the user asks to run Claude, delegate a coding task, continue a previous Claude session, or any task benefiting from Claude Code's tools (file editing, code analysis, bash, etc.).

Archived SourceRecently Updated