lindy-local-dev-loop
Set up local development workflow for testing Lindy AI agent integrations. Use when building webhook receivers, testing agent callbacks, or iterating on Lindy-connected applications locally. Trigger with phrases like "lindy local dev", "lindy development", "test lindy locally", "lindy webhook local".
What this skill does
# Lindy Local Dev Loop
## Overview
Lindy agents run on Lindy's managed infrastructure — you do not run agents locally.
Local development focuses on building and testing the **webhook receivers**, **callback
handlers**, and **application code** that Lindy agents interact with. Use ngrok or
similar tunnels to expose local endpoints for Lindy webhook triggers.
## Prerequisites
- Node.js 18+ or Python 3.10+
- ngrok or Cloudflare Tunnel for HTTPS tunneling
- Lindy account with at least one agent configured
- Completed `lindy-install-auth` setup
## Instructions
### Step 1: Create Webhook Receiver
```typescript
// server.ts — Express webhook receiver for Lindy callbacks
import express from 'express';
import dotenv from 'dotenv';
dotenv.config();
const app = express();
app.use(express.json());
const WEBHOOK_SECRET = process.env.LINDY_WEBHOOK_SECRET;
// Verify Lindy webhook authenticity
function verifyWebhook(req: express.Request): boolean {
const auth = req.headers.authorization;
return auth === `Bearer ${WEBHOOK_SECRET}`;
}
// Receive Lindy agent callbacks
app.post('/lindy/callback', (req, res) => {
if (!verifyWebhook(req)) {
console.error('Unauthorized webhook attempt');
return res.status(401).json({ error: 'Unauthorized' });
}
console.log('Lindy callback received:', JSON.stringify(req.body, null, 2));
// Process the agent's output
const { taskId, result, status } = req.body;
console.log(`Task ${taskId}: ${status}`);
res.json({ received: true });
});
// Health check for Lindy to verify endpoint
app.get('/health', (req, res) => res.json({ status: 'ok' }));
app.listen(3000, () => console.log('Webhook receiver running on :3000'));
```
### Step 2: Expose Local Server via Tunnel
```bash
# Install and start ngrok
npm install -g ngrok
ngrok http 3000
# Output: https://abc123.ngrok.io -> http://localhost:3000
# Use this URL in Lindy webhook configuration
```
### Step 3: Configure Lindy Agent to Call Your Endpoint
In the Lindy dashboard, add an **HTTP Request** action to your agent:
- **Method**: POST
- **URL**: `https://abc123.ngrok.io/lindy/callback`
- **Headers**: `Content-Type: application/json`
- **Body** (AI Prompt mode):
```
Send the task result as JSON with fields: taskId, result, status
```
Or configure a webhook trigger pointing to your tunnel URL:
```
https://abc123.ngrok.io/lindy/webhook
```
### Step 4: Create Test Harness
```typescript
// test-trigger.ts — Fire a test webhook to your Lindy agent
import fetch from 'node-fetch';
async function triggerAgent() {
const WEBHOOK_URL = process.env.LINDY_WEBHOOK_URL!;
const SECRET = process.env.LINDY_WEBHOOK_SECRET!;
const response = await fetch(WEBHOOK_URL, {
method: 'POST',
headers: {
'Authorization': `Bearer ${SECRET}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
action: 'test',
data: { message: 'Hello from local dev', timestamp: new Date().toISOString() },
}),
});
console.log(`Status: ${response.status}`);
console.log(`Response: ${await response.text()}`);
}
triggerAgent();
```
### Step 5: Watch Mode Development
```json
// package.json scripts
{
"scripts": {
"dev": "tsx watch server.ts",
"test:trigger": "tsx test-trigger.ts",
"tunnel": "ngrok http 3000"
}
}
```
```bash
# Terminal 1: Start server with auto-reload
npm run dev
# Terminal 2: Start tunnel
npm run tunnel
# Terminal 3: Fire test triggers
npm run test:trigger
```
### Step 6: Environment Configuration
```bash
# .env
LINDY_API_KEY=lnd_live_xxxxxxxxxxxx
LINDY_WEBHOOK_SECRET=whsec_xxxxxxxxxxxx
LINDY_WEBHOOK_URL=https://public.lindy.ai/api/v1/webhooks/YOUR_ID
NODE_ENV=development
```
## Development Workflow
```
[Edit local code] → [Auto-reload via tsx watch]
↓
[Fire test webhook] → [Lindy agent processes]
↓
[Agent calls back] → [ngrok tunnel → localhost:3000]
↓
[Review logs] → [Iterate]
```
## Error Handling
| Issue | Cause | Solution |
|-------|-------|----------|
| ngrok tunnel expires | Free tier limit (2hr) | Restart ngrok or use paid plan |
| Lindy can't reach endpoint | Tunnel URL changed | Update webhook URL in Lindy dashboard |
| Callback not received | Agent HTTP Request misconfigured | Check URL and headers in action config |
| `ECONNREFUSED` | Local server not running | Start server before testing |
| SSL error | ngrok not using HTTPS | Always use the `https://` ngrok URL |
## Resources
- [Webhook Triggers](https://www.lindy.ai/academy-lessons/webhook-triggers)
- [Calling Any API](https://www.lindy.ai/academy-lessons/calling-any-api)
- [Lindy Documentation](https://docs.lindy.ai)
## Next Steps
Proceed to `lindy-sdk-patterns` for integration patterns and best practices.
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.