Agent Research Aggregator (PaperOrchestra input builder)

Scans AI coding-agent caches (.claude, .cursor, .antigravity, .openclaw) or any folder you name, then turns scattered experiment logs into PaperOrchestra-ready idea.md and experimental_log.md.

EducationAdvanced★ 665⑂ 92AI score 8/10Last updated: Sep 21, 2026

What it does

Runs a discovery script over agent cache folders (or a directory you specify) to catalog every relevant experiment log, with depth, agent-type and date filters.
Forces a single-project choice, then reads logs in batches and extracts hypotheses, methods and numeric results into structured JSON.
Synthesizes duplicated records into one coherent research narrative and emits workspace/inputs/idea.md plus workspace/inputs/experimental_log.md in PaperOrchestra's expected format.
Produces an audit report (aggregation_report.md) with per-agent file counts, iteration history and data-quality warnings.
Hard rules: read-only on cache dirs, strip PII/credentials, mark low-confidence metrics [UNVERIFIED], never fabricate results.

Who it's for

Researchers and grad students who iterated heavily with Claude Code/Cursor but never kept a clean lab notebook.
Anyone who wants to run the PaperOrchestra pipeline but lacks its structured input files.
Teams needing to consolidate benchmark numbers and failure modes spread across many agent sessions.

Examples

"Aggregate my agent logs for paper writing" → it lists discovered projects, you pick one, and two input files appear.
--search-roots ~/projects --since 2025-01-01 to include only recent experiments and rebuild the results tables.
Review the audit report, spot a "conflicting numbers" warning, fix the metric, then hand off to paper-orchestra.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/Ar9av/PaperOrchestra/HEAD/skills/agent-research-aggregator/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/agent-research-aggregator folder from the GitHub repo Ar9av/PaperOrchestra into my ~/.claude/skills/agent-research-aggregator/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/Ar9av/PaperOrchestra.git && mkdir -p ~/.claude/skills && cp -r PaperOrchestra/skills/agent-research-aggregator ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal in the folder where you keep tools.
Clone the repo: git clone https://github.com/Ar9av/PaperOrchestra.git
Copy the skill into Claude Code's skills folder: mkdir -p ~/.claude/skills && cp -r PaperOrchestra/skills/agent-research-aggregator ~/.claude/skills/
Confirm Python 3 is available (python --version) since the skill calls scripts in scripts/.
Restart Claude Code and ask something like "prepare PaperOrchestra inputs from my agent cache".
On the first run, pass a narrow --search-roots (your project folder) instead of letting it scan your entire home directory.
Answer the project-selection prompt, then review the generated idea.md and experimental_log.md yourself. Add template.tex and conference_guidelines.md before running the paper pipeline.

View source on GitHub ↗License: NOASSERTION