Research Pipeline

This is the full autonomous research loop: you give it a research direction, and it runs idea discovery with literature review and novelty checking, picks the top idea (or waits for your approval), spins up experiments with optional code review, runs iterative auto-review loops until claims are solid, then generates a narrative report and optionally a formatted paper. It's resumable if it crashes mid-run, which matters because this thing can run overnight. The constants let you dial how adversarial the reviews are (medium to nightmare), whether to auto-proceed through gates, and whether to pull a base repo or start from scratch. Most useful when you actually want to walk away and let it cook through the entire pipeline, though you can checkpoint at stages if you want to steer. Ships with the standard research workflow assumptions baked in.

Install to Claude Code

npx -y skills add wanshuiyin/auto-claude-code-research-in-sleep --skill research-pipeline --agent claude-code