We built a suite of skills, agents and tools bundled as a plugin to make the Spotify Ads Platform easily accessible to AI agentic tools. The spotify-ads-api plugin is available on  and through .

The Spotify Engineering Blog provides  insights, technical deep dives, and behind-the-scenes stories from the engineering team at Spotify. Covering a wide range of topics, including backend systems, data processing pipelines, and frontend architecture, the blog offers a glimpse into the technology stack and engineering practices used to power one of the world's leading music streaming platforms. Developers can learn about scalable infrastructure solutions, innovative engineering techniques, and best practices for building high-performance software systems. By following the Spotify Engineering Blog, developers can gain inspiration, knowledge, and practical insights to apply to their own projects and endeavors.

Spotify Labs

Spotify Engineering built a Claude Code plugin that translates natural language into Spotify Ads API v3 calls, eliminating the need to manually orchestrate complex multi-step campaign creation workflows. The plugin is written entirely in Markdown files with no compiled code, using skills, agents, and hooks. It ships the full OpenAPI spec (~8,600 lines) as the source of truth, leveraging OpenAPI Links to encode entity relationships (campaign → ad set → ad) so the LLM agent can follow the correct call sequence. The team deliberately avoided MCP due to the large API surface and chose curl-based execution for transparency and debuggability. The plugin is open source under Apache 2.0 and available on GitHub and Anthropic's Claude Plugins marketplace.

Building a Natural Language Interface to the Spotify Ads API with Claude Code Plugins