Skip to content

AGENTS.md

Latest commit

 

History

History
12 lines (9 loc) · 1.52 KB

AGENTS.md

File metadata and controls

12 lines (9 loc) · 1.52 KB
Raw

Agents entry point

  • What this project is: ReelPod Studio — a creator tool for generating AI music and visuals for YouTube, TikTok, and Facebook. Two modalities: long-form videos (multiple songs) and live streaming.

  • How to work here: Use this file as the single entry point. Follow the process phases in order; read and update .agents/state.json for the current iteration and phase. Invoke the skills under .agents/skills/ as indicated by each command. All iteration artifacts live in .agents/flow/ with the naming it_ + 6-digit iteration (e.g. it_000001_product-requirement-document.md). From the second iteration onward, adhere to .agents/PROJECT_CONTEXT.md.

  • Process: Define → Prototype → Refactor (see package or usage documentation).

  • Project context: .agents/PROJECT_CONTEXT.md (conventions and architecture; agent adheres from second iteration onward).

  • Rule: All generated resources in this repo must be in English.

  • MCP integration: The ReelPod UI MCP server lives under src/mcp/. Use the install-mcp skill to configure the reelpod-ui-mcp server for your MCP host, and the create-amv skill to drive AMV generations via the set_song_parameters, generate_audio, and add_to_queue tools.

  • Model artifacts: Do not commit large model weights or vendor assets (e.g. under backend/.realesrgan/ or external repos like SeedVR/SeedVR2). Treat them as local-only dependencies or download-time assets.

  • Roadmap and new features: ROADMAP.md — full iteration plan.