Visual Agent Map — AI skill for Claude Code
Visual AI research for Obsidian.
How to install Visual Agent Map
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open kevcltsai/visual-agent-map and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Visual Agent Map does
Visual AI research for Obsidian. Research complex topics with Codex or Claude Code in a visual map and keep every result as editable Markdown.
Alternatives in AI
- ARIS Agent Guide — For AI agents reading this repo 6.2k ★
- AI Research SKILLs — Visual Skills Pack for Obsidian: generate Canvas, Excalidraw, and Mermaid diagrams from text with Claude Code 5.7k ★
- Open Researcher — 🔥 Visual AI research assistant that displays real-time thinking, provides split-view analysis, and automatic 634 ★
README
Visual Agent Map
[English](#english) · [繁體中文](#繁體中文)
English
Explore big questions with visual AI research in Obsidian
**Start with a question. See the pieces. Follow the ideas worth exploring.** Build a visual research map, let AIM investigate a question, or talk through a new idea in Coffee Tables. Keep what you learn in editable Markdown notes.
[**Get started**](#get-started) · [See the 0.15.0 release](https://github.com/kevcltsai/visual-agent-map/releases/tag/0.15.0) · [Installation guide](INSTALL.md)
Take a look

*Example visual map; this image does not show every guided research control.*
Three ways to explore
- Visual maps. Break a question into topics, research a branch with AI, and review suggestions before adding them. Manual mapping needs no AI.
- AIM — Adaptive Inquiry Map. Work from your question and background toward a document with supporting sources. Follow the research in the map, build on useful earlier findings, and resume unfinished work when a step fails.
- Coffee Tables. Bring an unfinished idea to simulated AI guests. Add
.txt/.mdbackground, choose a conversation style, invite guests with a question, and revisit observer insights and conversation segments.
Coffee Tables guests are simulated, not real experts; their conversations are not automatically fact-checked.
Get started
- In Obsidian Desktop → Settings → Community plugins → Browse, find Visual Agent Map, then install and enable it. Requires Obsidian 1.13.7+.
- Try the built-in sample or create a visual map. For AI features, install and sign in to Codex CLI or Claude Code, then check the CLI in VAM settings.
- Choose Create Adaptive Inquiry Map (AIM) to try AIM. Enter your question and background, answe
Related Skills
Understanding Studio
An Agent Skill that turns complex topics and AI outputs into clear explanations, diagrams, interactive single-
Agent Think Map
A visual debugger for AI agents. See every tool, skill, MCP call, and subagent beside Claude Code or Codex, wi
Sherwanis Claude Md
Drop-in AGENTS.md / CLAUDE.md that keeps AI coding agents honest: ask before assuming, keep it simple, change
LLM Gtd
GTD (Getting Things Done) skill for Claude Code, Cursor & Codex — one Markdown trusted system, three platform
Dsh Research Graph
DSH Research Graph · 研图 — DeepSeek Harness plugin for research topics, traceable knowledge cards, and reusable
Pp Papers
A paper library in plain text: one Markdown file per paper, a Unix CLI, an editable lineage graph, made for AI
Related Agents
Librarian Agent
Librarian for a notes/knowledge-base vault (Obsidian-style or plain-markdown) — filing new notes, organizing f
Local Writer
Use for high-token repetitive writing (docstrings, inline code comments, Markdown documentation, CHANGELOG/REA
Zettelkasten Linker
Use this agent to comprehensively analyze the workspace markdown files for quality and connections. This agent