easypaper-paper-from-m…
Generate a paper directly from metadata using the EasyPaper Python SDK.
Interactively build EasyPaper metadata from a research-materials folder using Claude Code's file-investigation tools. Output is JSON consumable by `/easypaper-paper-from-metadata`.
$ npx -y skills add tsinghua-fib-lab/agentsociety --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/easypaper-metadata-buildContext preview
What this command does when you run it.
Interactively build EasyPaper metadata from a research-materials folder using Claude Code's file-investigation tools. Output is JSON consumable by `/easypaper-paper-from-metadata`.
Interactively build EasyPaper metadata from a research-materials folder using Claude Code's file-investigation tools. Output is JSON consumable by `/easypaper-paper-from-metadata`.
Use this command when the user wants Claude to co-author metadata instead of running the SDK one-shot `ep.generate_metadata_from_folder(...)` pipeline silently.
1. Present the three modes and wait for an explicit choice:
2. Ask for the corresponding input:
3. Ask for optional style/template settings:
4. Hand off to the `easypaper-interactive-metadata-build` skill for the detailed 6-phase workflow. 5. Save to `<materials_root>/easypaper_metadata.json` by default and tell the user to run `/easypaper-paper-from-metadata` next.
Before saving, validate the in-memory metadata with public SDK/Pydantic plus explicit checks:
$ARGUMENTS
AgentSociety 2 is a modern, LLM-native agent simulation platform designed for social science research and experimental design. It provides a flexible framework for creating and managing intelligent agents in simulated environments.
Generate a paper directly from metadata using the EasyPaper Python SDK.
Generate or revise a single paper section through EasyPaper.
Set up EasyPaper environment including Python dependencies and LaTeX toolchain.
Run the EasyPaper end-to-end paper generation workflow with guided setup and metadata collection.