lindy-local-dev-loop
Set up local development workflow for Lindy AI agents. Use when configuring local testing, hot reload, or development environment. Trigger with phrases like "lindy local dev", "lindy development", "lindy hot reload", "test lindy locally".
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 2.0k
- Forks
- 233
01 前言 Front Matter
- name
- lindy-local-dev-loop
- author
- Jeremy Longshore <jeremy@intentsolutions.io>
- license
- MIT
- version
- 1.0.0
- description
- Set up local development workflow for Lindy AI agents. Use when configuring local testing, hot reload, or development environment. Trigger with phrases like "lindy local dev", "lindy development", "lindy hot reload", "test lindy locally".
- allowed-tools
- Read, Write, Edit, Bash(npm:*), Bash(node:*)
03 SKILL.md 正文
Lindy Local Dev Loop
Overview
Configure efficient local development workflow for Lindy AI agent development.
Prerequisites
- Completed
lindy-install-authsetup - Node.js 18+ with npm/pnpm
- Code editor with TypeScript support
Instructions
Step 1: Set Up Project Structure
mkdir lindy-agents && cd lindy-agents
npm init -y
npm install @lindy-ai/sdk typescript ts-node dotenv
npm install -D @types/node nodemon
Step 2: Configure TypeScript
// tsconfig.json
{
"compilerOptions": {
"target": "ES2022",
"module": "NodeNext",
"moduleResolution": "NodeNext",
"outDir": "./dist",
"strict": true,
"esModuleInterop": true
},
"include": ["src/**/*"]
}
Step 3: Create Development Script
// package.json scripts
{
"scripts": {
"dev": "nodemon --exec ts-node src/index.ts",
"build": "tsc",
"start": "node dist/index.js",
"test:agent": "ts-node src/test-agent.ts"
}
}
Step 4: Create Agent Test Harness
// src/test-agent.ts
import 'dotenv/config';
import { Lindy } from '@lindy-ai/sdk';
const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });
async function testAgent(agentId: string, input: string) {
console.log(`Testing agent ${agentId} with: "${input}"`);
const start = Date.now();
const result = await lindy.agents.run(agentId, { input });
console.log(`Response (${Date.now() - start}ms): ${result.output}`);
return result;
}
// Run test
testAgent(process.argv[2], process.argv[3] || 'Hello!');
Output
- Configured development environment
- Hot reload enabled for agent code
- Test harness for rapid iteration
- TypeScript support with type checking
Error Handling
| Error | Cause | Solution |
|---|---|---|
| ts-node not found | Dev deps missing | npm install -D ts-node |
| ENV not loaded | dotenv not configured | Add import 'dotenv/config' |
| Type errors | Missing types | npm install -D @types/node |
Examples
Watch Mode Development
# Start development with hot reload
npm run dev
# Test specific agent
npm run test:agent agt_abc123 "Test input"
Environment Setup
# .env file
LINDY_API_KEY=your-api-key
LINDY_ENVIRONMENT=development
Resources
Next Steps
Proceed to lindy-sdk-patterns for SDK best practices.
04 同仓库更多 Skills
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
neuropixels-analysis
Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
notebooklm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.