Spatial9 Agent Skills for immersive audio

Free Spatial9 Agent Skills (SKILL.md) for Claude, Codex, Copilot, Cursor and Gemini CLI, production solutions for Databricks, Snowflake, Vertex AI and Bedrock, and n8n, Zapier and Airflow workflows.

Download every file as a zip · Read the guide · Enterprise guide · Source on GitHub

Skills

Spatial9 Agent Skills

Agent Skills (SKILL.md format) and ready-to-run workflow examples that teach AI agents to use the Spatial9 immersive audio engine. They work in Claude, Claude Code, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI and any agent that reads the Agent Skills standard.

Every skill uses the Spatial9 MCP server:

  • https://spatial9.ai/mcp: sign in with OAuth, or send Authorization: Bearer s9_... (create a key at https://spatial9.ai/connect)
  • https://spatial9.ai/mcp/free: free guest allowance, no sign-in

How this repository is organized

skills/       Agent Skills (SKILL.md) your agent loads
solutions/    Production code for data platforms and an open source pipeline
workflows/    No-code and scheduler automations
examples/     Short demos and agent setup files
templates/    Start your own skill

Skills

Skill · What the agent can do

spatial9-immersive-mix · Song, stems or video to Eclipsa Audio (IAMF) with a binaural headphone version

spatial9-stem-split · Separate a song into instrument stems

spatial9-atmos-to-eclipsa · Convert Dolby or ADM BWF masters to Eclipsa Audio

spatial9-chorus-preview · Free 30-second headphone preview of the chorus

spatial9-remix-by-voice · Move, level, animate and add effects to a mix from plain language

spatial9-release-publisher · Publish to YouTube and make 9:16 social clips

spatial9-enterprise-catalog · Governed catalog renders from Databricks, Snowflake, Vertex AI and Bedrock

Install

  1. Connect the server. For Claude Code, run examples/setup/claude-code.sh. For apps that read an mcpServers file, use examples/setup/mcp.json.
  2. Copy a folder from skills/ into your agent's skills folder, for example .claude/skills/ for a project or ~/.claude/skills/ for your user. Other agents use their own skills folder.
  3. Ask in plain words: "Make my song immersive", "Split this into stems", "Preview the chorus in 3D".

Solutions

Deployable, production-ready code. Every solution reuses the clients in solutions/shared.

Folder · What it runs

solutions/databricks/solution-accelerator · Databricks Solutions Accelerator: an Asset Bundle with six notebooks for intake, render queue, MCP renders, A2A delegation, Dolby Atmos masters from the REST API and gold views

solutions/databricks · Single Databricks job for a governed catalog

solutions/snowflake · Snowflake stored procedure with an external access integration

solutions/vertex-ai · Google ADK agent on Vertex AI Agent Engine, plus a batch job on Cloud Run

solutions/bedrock · Amazon Bedrock agent with Strands, a Lambda and a Step Functions loop

solutions/open-source · MinIO, Kafka, PostgreSQL, FFmpeg, FastAPI and Dagster pipeline with real-time A2A webhooks and a live preview page

solutions/shared · Shared Python MCP and A2A clients

See solutions/README.md for how they fit together.

Workflows

Folder · What it automates

workflows/n8n · Form to Slack workflow with HTTP Request nodes, or an AI Agent with the MCP Client Tool

workflows/zapier · Two Zaps with a catch hook, plus the Make version

workflows/power-automate · A "Do until" loop for Microsoft 365 teams

workflows/github-actions · Render whenever a master is pushed

workflows/airflow · Nightly catalog job with a pool of 3

Examples

Folder · What it shows

examples/python · Commented batch pipeline: upload, render with 3 workers, download

examples/node · Start an A2A task and get a webhook when it finishes

examples/setup · Connect Claude Code or any mcpServers app to Spatial9

Write your own skill

Start from templates/SKILL.template.md. Keep the description specific about when to use the skill, list the exact tool names, and include the rules your team cares about.

Limits worth knowing

  • Up to 3 renders at once and 20 per day per account.
  • A failed render refunds its project automatically.
  • Upload links last 2 hours and accept files up to 2 GB.
  • Always send an idempotency_key so a retry never starts a second render.

Learn more

  • Full guide: https://spatial9.ai/blog/spatial9-agent-skills-pipelines-n8n-workflows
  • Enterprise guide: https://spatial9.ai/blog/spatial9-enterprise-agents-databricks-snowflake-vertex-bedrock
  • Open source pipeline guide: https://spatial9.ai/blog/open-source-spatial-audio-pipeline-real-time-spatial9
  • Browse these files online: https://spatial9.ai/agents/skills
  • A2A agents: https://spatial9.ai/agents

License

MIT. See LICENSE.

All 65 files

Frequently asked questions

What are Spatial9 Agent Skills?

Free instruction packs in the open SKILL.md format that teach AI agents to use the Spatial9 MCP server for immersive mixes, stem splits, Dolby and ADM to Eclipsa Audio conversion, chorus previews, remixing by voice, YouTube publishing and governed enterprise catalog renders.

Which agents can use them?

Claude, Claude Code, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI and any agent that reads the Agent Skills standard.

How do I install a skill?

Connect the Spatial9 MCP server at https://spatial9.ai/mcp, then copy a skill folder into your agent's skills folder, for example .claude/skills/.

Are there production solutions?

Yes. The solutions folder has deployable code for Databricks (including a Solutions Accelerator), Snowflake, Google Vertex AI, Amazon Bedrock and an open source pipeline, plus shared Python MCP and A2A clients. Microsoft Fabric is not supported.

How is the repository organized?

skills holds the SKILL.md files, solutions holds production code for data platforms, workflows holds n8n, Zapier, Make, Power Automate, GitHub Actions and Airflow automations, examples holds short Python and Node demos and setup files, and templates holds a starter SKILL.md.

Is it free?

Yes. Every file is MIT licensed and can be downloaded as one zip file.

Is the source on GitHub?

Yes. The same files are on GitHub at https://github.com/lzanardos9/Spatial9-Agents, so you can clone, star or fork them.