Interactive Viz

Documents

interactive-viz

Interactive Viz is an Agent Skill for documents published in the tsinghua-fib-lab/AgentSociety repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

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.

View on GitHub ↗

QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

Open your project in Codex.
Copy and paste the prompt below.
Review files and risks before approving any action.

Prompt to paste

Inspect the Agent Skill at https://github.com/tsinghua-fib-lab/AgentSociety/blob/HEAD/extension/skills/agentsociety-analysis/v1.0.0/support/interactive-viz/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/interactive-viz, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Interactive Viz (bundled support)

When to use

User wants interactive / diverse data presentation
Stage 2 explore: run run-eda --type bundle
Stage 4: presentation_mode: static_plus_interactive
Stage 5: multi-tab §数据 with eda_hub.html

Commands

# Full interactive EDA pack + hub
ags.py analysis run-eda --db-path DB --output-dir DIR/data --type bundle --workspace WS --hypothesis-id HID

# Single modes
ags.py analysis run-eda ... --type pygwalker
ags.py analysis run-eda ... --type datatable
ags.py analysis run-eda ... --type plotly-profile
ags.py analysis run-eda ... --type eda-hub

Read order

references/eda.md
references/charts.md (optional interactive export)
references/reports.md (HTML embed)

Python (run-code)

from agentsociety2.skills.analysis.chart_export import export_plotly_html, export_pygwalker_html

Report

Embed data/eda_hub.html as primary §数据 interactive surface; per-claim plotly iframes under .figure-block.