lindy-hello-world
Create your first Lindy AI agent with a real trigger and action. Use when starting with Lindy, testing your setup, or learning basic agent workflow patterns. Trigger with phrases like "lindy hello world", "lindy example", "lindy quick start", "simple lindy agent", "first lindy".
What this skill does
# Lindy Hello World
## Overview
Build a minimal Lindy AI agent: **Webhook Received** trigger -> LLM processing ->
**Slack notification**. Demonstrates the three core building blocks every Lindy agent
uses: Trigger, Agent Step (prompt + model + skills), and Action.
## Prerequisites
- Lindy account at
- Slack workspace connected (or Gmail for email variant)
- Completed `lindy-install-auth` setup
## Instructions
### Step 1: Create Agent via Dashboard
1. Click **"New Agent"** at
2. In the prompt field ("How can I help you?"), type:
```
When I send a webhook, summarize the message and post it to Slack
```
3. Agent Builder auto-generates the workflow with trigger + action nodes
### Step 2: Configure the Webhook Trigger
1. Click the trigger node at the top of the workflow canvas
2. Select **Webhook Received**
3. Copy the generated URL:
```
https://public.lindy.ai/api/v1/webhooks/<unique-id>
```
4. Click **Generate Secret** — copy immediately (shown once)
### Step 3: Add the Slack Action
1. Click **"+"** to add a step
2. Search for **Slack Send Channel Message**
3. Authorize your Slack workspace when prompted
4. Configure fields:
- **Channel**: `#general` (or test channel)
- **Message** field mode: **AI Prompt**
- Instruction:
```
Summarize the webhook payload in one sentence.
Payload: {{webhook_received.request.body}}
```
### Step 4: Set the Agent Prompt
Open **Settings > Prompt**:
```
You are a webhook summarizer. When you receive a webhook payload,
extract the key information and create a concise one-sentence summary.
Be factual and specific. Do not add opinions or speculation.
```
### Step 5: Test It
```bash
curl -X POST "https://public.lindy.ai/api/v1/webhooks/YOUR_ID" \
-H "Authorization: Bearer YOUR_SECRET" \
-H "Content-Type: application/json" \
-d '{
"event": "order.created",
"customer": "Jane Doe",
"amount": 149.99,
"items": ["Widget Pro", "Adapter Cable"]
}'
```
Expected Slack message:
> Jane Doe placed a $149.99 order for Widget Pro and Adapter Cable.
### Step 6: Verify in Dashboard
Navigate to the **Tasks** tab in your agent view. Confirm status shows **Completed**.
Click into the task to see each step's input/output for debugging.
## Agent Anatomy
| Component | Purpose | Hello World Value |
|-----------|---------|-------------------|
| **Prompt** | Core behavioral instructions | "Summarize webhook payloads" |
| **Model** | AI engine powering decisions | Default (GPT-4 / Claude / Gemini) |
| **Skills** | Available actions & tools | Slack Send Channel Message |
| **Exit Conditions** | When the task is "done" | Message sent successfully |
## Webhook Data Variables
| Variable | Contents |
|----------|----------|
| `{{webhook_received.request.body}}` | Full JSON payload |
| `{{webhook_received.request.headers}}` | HTTP request headers |
| `{{webhook_received.request.query}}` | URL query parameters |
## Field Configuration Modes
| Mode | Behavior | Credit Cost |
|------|----------|-------------|
| **Auto** | Agent determines value from context | Standard |
| **AI Prompt** | Natural language instructions generate content | Standard |
| **Set Manually** | Exact value, no AI processing | Lower |
## Variant: Email Instead of Slack
Replace the Slack action with **Gmail Send Email**:
- **To**: Set manually or reference a webhook field
- **Subject**: AI Prompt — `"Summary: {{webhook_received.request.body.event}}"`
- **Body**: AI Prompt — `"Summarize this event: {{webhook_received.request.body}}"`
## Error Handling
| Issue | Cause | Solution |
|-------|-------|----------|
| Webhook returns 401 | Missing Authorization header | Add `Bearer <secret>` header |
| Slack message not sent | Channel not authorized | Re-authorize Slack in Lindy |
| Task shows "Failed" | Action misconfigured | Check field references in step config |
| No task created | Agent not active | Publish/activate the agent |
| Empty summary | Payload not reaching LLM | Verify `{{webhook_received.request.body}}` reference |
## Cost
~1-3 credits per invocation on basic models. Free tier (400 credits/month) supports
~130-400 test runs per month.
## Resources
- [Getting Started 101](https://www.lindy.ai/academy-lessons/getting-started-101)
- [Webhook Triggers Academy](https://www.lindy.ai/academy-lessons/webhook-triggers)
- [Lindy Documentation](https://docs.lindy.ai)
## Next Steps
Proceed to `lindy-core-workflow-a` for a full multi-step agent workflow.
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.