Intake skill for new research directions in computer systems, networking, and AI. Use when the user has a rough idea, partial implementation, benchmark intuition, or venue target and needs to turn it into a clear paper plan with thesis, hypotheses, workstreams, and next decisions.
Read ../references/workflow.md, ../references/venues.md, and ../references/memory.md.
If this is not a brand-new project, read project memory and researcher preferences first. Pull in only relevant durable context:
Produce a compact research brief with:
Push the user toward a falsifiable framing. Replace "this seems useful" with:
If the idea is too broad, split it into:
When choosing venues, reason from contribution type:
At the end, propose 1 to 3 durable memory entries when the session clarified something future work should inherit, especially: