AGENT SKILL

lindy-deploy-integration

Configure deployment pipelines for Lindy AI integrations. Use when deploying to production, setting up staging environments, or automating agent deployments. Trigger with phrases like "deploy lindy", "lindy deployment", "lindy production deploy", "release lindy agents".

License 许可
MIT
最近更新
2026-11-11
Stars
★ 2.0k
Forks
231

01 前言 Front Matter

name
lindy-deploy-integration
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
version
1.0.0
description
Configure deployment pipelines for Lindy AI integrations. Use when deploying to production, setting up staging environments, or automating agent deployments. Trigger with phrases like "deploy lindy", "lindy deployment", "lindy production deploy", "release lindy agents".
allowed-tools
Read, Write, Edit, Bash(gh:*), Bash(docker:*)

03 SKILL.md 正文

Lindy Deploy Integration

Overview

Configure deployment pipelines for Lindy AI agent integrations.

Prerequisites

  • CI pipeline configured (see lindy-ci-integration)
  • Production Lindy API key
  • Deployment target (Vercel, AWS, GCP, etc.)

Instructions

Step 1: Create Deployment Workflow

# .github/workflows/lindy-deploy.yml
name: Deploy Lindy Integration

on:
  push:
    branches: [main]
  workflow_dispatch:

env:
  LINDY_ENVIRONMENT: production

jobs:
  deploy:
    runs-on: ubuntu-latest
    environment: production

    steps:
      - uses: actions/checkout@v4

      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: '20'
          cache: 'npm'

      - name: Install dependencies
        run: npm ci

      - name: Build
        run: npm run build

      - name: Run pre-deploy checks
        run: npm run predeploy
        env:
          LINDY_API_KEY: ${{ secrets.LINDY_PROD_API_KEY }}

      - name: Deploy to Vercel
        uses: amondnet/vercel-action@v25
        with:
          vercel-token: ${{ secrets.VERCEL_TOKEN }}
          vercel-org-id: ${{ secrets.VERCEL_ORG_ID }}
          vercel-project-id: ${{ secrets.VERCEL_PROJECT_ID }}
          vercel-args: '--prod'

      - name: Sync Lindy agents
        run: npm run sync:agents
        env:
          LINDY_API_KEY: ${{ secrets.LINDY_PROD_API_KEY }}

      - name: Notify Slack
        if: success()
        uses: slackapi/slack-github-action@v1
        with:
          payload: |
            {
              "text": "Lindy integration deployed successfully"
            }

Step 2: Create Agent Sync Script

// scripts/sync-agents.ts
import { Lindy } from '@lindy-ai/sdk';
import fs from 'fs';

interface AgentConfig {
  id?: string;
  name: string;
  instructions: string;
  tools: string[];
}

async function syncAgents() {
  const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });

  // Load agent configurations
  const configPath = './agents/config.json';
  const configs: AgentConfig[] = JSON.parse(fs.readFileSync(configPath, 'utf-8'));

  for (const config of configs) {
    if (config.id) {
      // Update existing agent
      await lindy.agents.update(config.id, {
        name: config.name,
        instructions: config.instructions,
        tools: config.tools,
      });
      console.log(`Updated agent: ${config.id}`);
    } else {
      // Create new agent
      const agent = await lindy.agents.create({
        name: config.name,
        instructions: config.instructions,
        tools: config.tools,
      });
      console.log(`Created agent: ${agent.id}`);

      // Update config with new ID
      config.id = agent.id;
    }
  }

  // Save updated config
  fs.writeFileSync(configPath, JSON.stringify(configs, null, 2));
}

syncAgents().catch(console.error);

Step 3: Configure Environments

# .github/workflows/lindy-deploy-staging.yml
name: Deploy to Staging

on:
  push:
    branches: [develop]

jobs:
  deploy:
    environment: staging
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - run: npm ci
      - run: npm run build
      - run: npm run deploy:staging
        env:
          LINDY_API_KEY: ${{ secrets.LINDY_STAGING_API_KEY }}

Step 4: Add Rollback Capability

// scripts/rollback.ts
import { Lindy } from '@lindy-ai/sdk';

async function rollback(agentId: string, version: string) {
  const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });

  // Get version history
  const versions = await lindy.agents.versions.list(agentId);
  const targetVersion = versions.find(v => v.id === version);

  if (!targetVersion) {
    throw new Error(`Version ${version} not found`);
  }

  // Restore to previous version
  await lindy.agents.versions.restore(agentId, version);
  console.log(`Rolled back agent ${agentId} to version ${version}`);
}

rollback(process.argv[2], process.argv[3]).catch(console.error);

Output

  • Automated deployment pipeline
  • Agent sync mechanism
  • Environment-specific deployments
  • Rollback capability

Error Handling

Issue Cause Solution
Deploy failed Build error Check build logs
Agent sync failed Invalid config Validate JSON
Rollback failed Version missing Check version history

Examples

Docker Deployment

# Dockerfile
FROM node:20-alpine
WORKDIR /app
COPY package*.json ./
RUN npm ci --production
COPY dist ./dist
ENV NODE_ENV=production
CMD ["node", "dist/index.js"]
# Deploy job
- name: Build and push Docker image
  run: |
    docker build -t my-lindy-app:${{ github.sha }} .
    docker push my-lindy-app:${{ github.sha }}

Resources

Next Steps

Proceed to lindy-webhooks-events for event handling.

04 同仓库更多 Skills

Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

测试与质量前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

slack-gif-creator

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

邮件与沟通图像与多媒体
★ 2.0k