executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
demos-and-servingGuides Janus Gradio demos, FastAPI services, and client workflows.
Independent GitHub snapshot · Automated classification · Original documentation governs
Use this sub-skill when the task is about running or adapting a Janus-family Gradio demo, a FastAPI service, or a small client for the demo endpoints.
references/gradio-and-fastapi.md for demo commands, endpoint contracts, and safe launch patterns.references/troubleshooting.md for optional dependency, port, payload, and streaming failures.scripts/janus_fastapi_skeleton.py for a lazy-loading service skeleton.scripts/janus_fastapi_client.py for a configurable client.For the core model workflows, use the sibling sub-skills:
Choose this route when the user asks to:
The upstream demo scripts load models at import time and some use share=True. Use the generated helper scripts instead when you want a safer starting point.
gradio is only needed for the UI path.fastapi, uvicorn, and python-multipart are only needed for the API path.requests is only needed for the client path.