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.
@tsinghua-fib-lab强制使用：凡是时间尺度在小时及以下的日常行为模拟，必须使用本 Skill 生成、评估、执行和修正每日 Story。
@tsinghua-fib-labUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any…
@tsinghua-fib-labEnforce academic writing and LaTeX drafting conventions for EasyPaper outputs.
@tsinghua-fib-labInteractively build EasyPaper metadata from a research-materials folder using Claude Code's file-investigation tools. Output is…
@tsinghua-fib-labGenerate a full academic paper from metadata using the EasyPaper Python SDK. Collects metadata interactively if not provided,…
@tsinghua-fib-labAutomatically set up EasyPaper environment including Python dependencies and LaTeX toolchain in an isolated environment.
@tsinghua-fib-labRun the EasyPaper end-to-end paper generation workflow with guided setup and metadata collection.
@tsinghua-fib-labInteractively build EasyPaper metadata from a research-materials folder using Claude Code's file-investigation tools. Output is…
@tsinghua-fib-labGenerate a paper directly from metadata using the EasyPaper Python SDK.
@tsinghua-fib-labGenerate or revise a single paper section through EasyPaper.
@tsinghua-fib-labSet up EasyPaper environment including Python dependencies and LaTeX toolchain.
@tsinghua-fib-lab© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
