Agent Society

Automatically set up EasyPaper environment including Python dependencies and LaTeX toolchain in an isolated environment.

Interactively build EasyPaper metadata from a research-materials folder using Claude Code's file-investigation tools. Output is JSON consumable by the `easypaper-paper-from-metadata` skill.

Enforce academic writing and LaTeX drafting conventions for EasyPaper outputs.

Generate a full academic paper from metadata using the EasyPaper Python SDK. Collects metadata interactively if not provided, then generates the paper directly.

Apply venue-specific constraints for EasyPaper generation.

Use when packaging, validating, or publishing a dataset to the AgentSociety platform for later sharing or reuse.

Use when creating or revising a custom agent type, when an experiment needs an agent class that does not yet exist in the workspace, or when the agent design must be sized against a simulation budget.

Use when creating or revising a custom environment module, when an experiment needs an environment class that does not yet exist in the workspace, or when the module design must fit a simulation budget.

Use when external datasets need to be searched, inspected, or downloaded for experiments or analysis.

Use when experiment configuration already exists and a simulation run needs to be started, monitored, or stopped.

Use when defining or revising research hypotheses, experiment groups, or comparison structure after literature review.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working w

Use when a hypothesis already exists and experiment configuration files need to be created, validated, or revised, especially after the simulation scale budget has been decided.

Use when academic literature needs to be gathered or refreshed for a research topic, especially at the beginning of a project.

Use when agent or environment module names are unknown, need validation, or the user asks which modules are available in the workspace.

Multi-modal interactive data presentation for agentsociety-analysis — EDA bundle (PyGWalker, Plotly, sortable tables, eda_hub), plotly/altair claim charts, HTML tab surfaces. Use in explore, refine, and produce stages.

Publication-quality chart patterns for agentsociety-analysis Stage 4 refine — Okabe-Ito palettes, seaborn CI bands, small multiples, error bars, grayscale-safe encoding. Use when writing run-code chart scripts or reviewing chart QA failures.

Create distinctive, production-grade frontend interfaces with high design quality. Use when building or polishing analysis HTML reports under agentsociety-analysis — read via support/frontend-design/ inside that skill, not as a separate pipeline skill.

Composable HTML block patterns for agentsociety-analysis reports — KPI strips, figure cards, Mermaid, EDA tabs, optional interactive chart iframes. Use during Stage 5 produce when authoring report_zh.html / report_en.html.

Use when an experiment run has completed and the user wants rigorous interpretation, claim-driven charts, bilingual reports, or cross-hypothesis synthesis from simulation data. Also use when multiple charts or PNG/JPG assets must be assembled into one labeled composite figure. Requires high-quality narrative and evidence traceability, not only harness gate PASS.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images

Use when starting or resuming an AgentSociety research workspace, deciding which research skill to invoke next, checking current pipeline state, or sizing a simulation before configuration and module creation.

Append notable events to state/memory.jsonl. Use after meaningful interactions, discoveries, decisions, or state changes. Forgetting runs via maintenance script.

Update internal emotion and intention from observation, needs, memory, and recent plan state. Use after observation and before planning/action.

Execute the current intention via codegen. Use when acting on state/intention.json against the environment.

Fetch the current world observation for this tick via codegen observe. Use before cognition, memory, intention, or planning when fresh perception is needed.

Economic decision-making for agents in EconomySpace. Activate when the agent observes currency, prices, income, tax, or trading opportunities to make informed financial decisions.

Example custom agent skill — a template to get started.

Only these paths are in active CI, security scanning, and Dependabot scope:

AgentSociety is a framework for building LLM-based agent simulations in urban environments and research workflows. The repository contains two main packages: