Evidence-based rebuttal

For a standalone skill installation, use python3 <installed-skill-directory>/scripts/paper_agent.py instead of python3 src/main.py. Its readable runtime is bundled in scripts/runtime/. If dependencies are missing, create a Python 3.10+ virtual environment and install scripts/requirements.txt from this skill. No model key is needed by the tools.

Export the complete paper and review text for the host agent:

python3 src/main.py rebuttal --paper paper.md --reviews reviews.txt --out runs/rebuttal-01

Use paper-agent instead of python3 src/main.py after installation. Read all inputs and write rebuttal.md plus actions.json in the exported directory. The command prepares a task; it does not automatically generate or submit a reply.