Spatial9 Agent Skills for immersive audio

Browse and download free Spatial9 Agent Skills (SKILL.md) for Claude, Codex, Copilot, Cursor and Gemini CLI, plus Python, Node.js, n8n, Zapier, Make, Power Automate, GitHub Actions and Airflow examples.

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

Skills

spatial9-immersive-mix: Song, stems or video to Eclipsa Audio with a binaural headphone version.
spatial9-stem-split: Separate a song into vocals, drums, bass and other instrument stems.
spatial9-atmos-to-eclipsa: Convert Dolby or ADM BWF masters to Eclipsa Audio for YouTube.
spatial9-chorus-preview: A free 30-second headphone preview of the chorus, no project used.
spatial9-remix-by-voice: Move, level, animate and add effects to a mix in plain language.
spatial9-release-publisher: Publish to YouTube and make vertical social clips.
spatial9-enterprise-catalog: Run governed catalog renders from Databricks, Snowflake, Vertex AI or Bedrock.

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

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

Connect the server. For Claude Code, run examples/setup/claude-code.sh. For apps that read an mcpServers file, use examples/setup/mcp.json.
Copy a skill folder 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.
Ask in plain words: "Make my song immersive", "Split this into stems", "Preview the chorus in 3D".

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

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

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

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

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

examples/enterprise · Databricks, Snowflake, Google Vertex AI and Amazon Bedrock recipes with a shared MCP client

examples/enterprise/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

examples/enterprise/shared · Shared Python MCP and A2A clients used by every enterprise recipe

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

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 enterprise examples?

Yes. The examples/enterprise folder has recipes for Databricks, Snowflake, Google Vertex AI and Amazon Bedrock, plus a shared Python MCP client. Microsoft Fabric is not supported.

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.