Agent Research Aggregator

If you've been running experiments through Claude, Cursor, or other coding agents and now want to write them up, this bridges the gap. It scans cache directories for scattered logs, extracts the actual experimental results and methods using LLM-assisted parsing, then outputs the structured idea.md and experimental_log.md files that PaperOrchestra expects. The project selection gate is smart: it shows you what it found across multiple repos and makes you pick one before doing any expensive processing. Works as a standalone prep step or gets called automatically by PaperOrchestra when inputs are missing. Honest take: this solves a real problem if you prototype in agents but hate manually reconstructing what you did three weeks ago.

Install to Claude Code

npx -y skills add ar9av/paperorchestra --skill agent-research-aggregator --agent claude-code