AGENT SKILL

lindy-upgrade-migration

Guide for upgrading Lindy SDK and migrating between versions. Use when upgrading SDK versions, migrating agents, or handling breaking changes. Trigger with phrases like "upgrade lindy", "lindy migration", "lindy breaking changes", "update lindy SDK".

License 许可
MIT
最近更新
2026-11-15
Stars
★ 2.0k
Forks
233

01 前言 Front Matter

name
lindy-upgrade-migration
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
version
1.0.0
description
Guide for upgrading Lindy SDK and migrating between versions. Use when upgrading SDK versions, migrating agents, or handling breaking changes. Trigger with phrases like "upgrade lindy", "lindy migration", "lindy breaking changes", "update lindy SDK".
allowed-tools
Read, Write, Edit, Bash(npm:*)

03 SKILL.md 正文

Lindy Upgrade & Migration

Overview

Guide for safely upgrading Lindy SDK versions and migrating configurations.

Prerequisites

  • Current SDK version identified
  • Changelog reviewed for target version
  • Backup of current configuration
  • Test environment available

Instructions

Step 1: Check Current Version

# Check installed version
npm list @lindy-ai/sdk

# Check latest available
npm view @lindy-ai/sdk version

# View changelog
npm view @lindy-ai/sdk changelog

Step 2: Review Breaking Changes

// Common breaking changes by version

// v1.x -> v2.x
// - Client initialization changed
// Before: new Lindy(apiKey)
// After:  new Lindy({ apiKey })

// - Agent.run() signature changed
// Before: agent.run(input)
// After:  lindy.agents.run(agentId, { input })

// - Events renamed
// Before: 'complete'
// After:  'completed'

Step 3: Update Dependencies

# Update to latest
npm install @lindy-ai/sdk@latest

# Or specific version
npm install @lindy-ai/sdk@2.0.0

# Check for peer dependency warnings
npm ls @lindy-ai/sdk

Step 4: Update Code

// Migration script for v1 -> v2

// Old code (v1)
import Lindy from '@lindy-ai/sdk';
const client = new Lindy(process.env.LINDY_API_KEY);
const result = await client.runAgent('agt_123', 'Hello');

// New code (v2)
import { Lindy } from '@lindy-ai/sdk';
const client = new Lindy({ apiKey: process.env.LINDY_API_KEY });
const result = await client.agents.run('agt_123', { input: 'Hello' });

Step 5: Run Migration Tests

// tests/migration.test.ts
import { Lindy } from '@lindy-ai/sdk';

describe('SDK Migration', () => {
  const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });

  test('client initialization works', async () => {
    const user = await lindy.users.me();
    expect(user.email).toBeDefined();
  });

  test('agent operations work', async () => {
    const agents = await lindy.agents.list();
    expect(Array.isArray(agents)).toBe(true);
  });

  test('run operations work', async () => {
    const result = await lindy.agents.run('agt_test', {
      input: 'Test migration',
    });
    expect(result.output).toBeDefined();
  });
});

Migration Checklist

[ ] Backup current configuration
[ ] Review changelog for breaking changes
[ ] Update package.json
[ ] Run npm install
[ ] Update import statements
[ ] Update client initialization
[ ] Update method calls
[ ] Run test suite
[ ] Test in staging environment
[ ] Deploy to production
[ ] Monitor for issues

Output

  • Updated SDK to target version
  • Migrated code patterns
  • Passing test suite
  • Documented changes

Error Handling

Issue Cause Solution
Import error Named exports changed Check new import syntax
Type error Interface changed Update TypeScript types
Runtime error Method signature changed Check new API

Examples

Automated Migration Script

#!/bin/bash
# migrate-lindy.sh

echo "Starting Lindy SDK migration..."

# Backup
cp package.json package.json.backup
cp -r src src.backup

# Update
npm install @lindy-ai/sdk@latest

# Run tests
npm test

if [ $? -eq 0 ]; then
  echo "Migration successful!"
  rm -rf src.backup package.json.backup
else
  echo "Migration failed. Rolling back..."
  mv package.json.backup package.json
  rm -rf src && mv src.backup src
  npm install
  exit 1
fi

Resources

Next Steps

Proceed to Pro tier skills for advanced features.

04 同仓库更多 Skills

Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

视觉设计
★ 2.0k
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