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.

GitHub stars: 572
last updated: Jun 2, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

agent-research-aggregator

Should I run? (decision gate)

Before starting Phase 1, check whether aggregation is actually needed:

Situation	Action
`workspace/inputs/idea.md` and `workspace/inputs/experimental_log.md` both exist and are non-empty	Skip this skill entirely. Proceed directly to `paper-orchestra`.
Either file is missing or empty, and the user provided a directory path	Run this skill with that directory as `--search-roots`.
Either file is missing or empty, and no directory was provided	Scan cwd and `~` by default; show the discovery summary to the user before continuing.
The inputs exist but look thin (e.g. idea.md has < 5 lines, no numeric data in experimental_log.md)	Ask the user whether to supplement with aggregation or proceed as-is.