What Actually Improves Claude Code Performance: Configuration and Architecture

Keeping Claude Code minimal, forcing full reasoning with three settings.json lines, and investing in system architecture — a practical take on what actually moves the needle.

April 15, 2026 · 2 min · Junho Lee
32 Slash Command Shortcuts That LLMs Instantly Understand

32 Slash Command Shortcuts That LLMs Instantly Understand

32 slash commands that work out of the box with Claude, ChatGPT, and Gemini – no custom definitions needed. Categorized by use case with practical combination strategies.

April 7, 2026 · 2 min · Junho Lee

Analyzing the Official GitHub Repository of a Major Korean Brokerage Open API

A structural analysis of the official sample code from a major Korean brokerage API, optimized for LLM agents and Python environments.

April 5, 2026 · 2 min · Junho Lee
macshot: A Native macOS Tool Emerging as an Alternative to Paid Apps

macshot: A Native macOS Tool Emerging as an Alternative to Paid Apps

A look at macshot, a native open-source macOS screenshot and screen recording tool that delivers powerful features without the subscription burden.

April 5, 2026 · 2 min · Junho Lee
OpenDocuments: A Local RAG Platform That Unifies Fragmented Team Knowledge

OpenDocuments: A Local RAG Platform That Unifies Fragmented Team Knowledge

An open-source platform that connects documents scattered across Notion, GitHub, and S3, then queries them with a local LLM. Runs entirely on-premise without external APIs.

April 1, 2026 · 2 min · Junho Lee
Thinking Like an Agent Conductor in the AI Era

Thinking Like an Agent Conductor in the AI Era

Even after adopting agents, if the work structure itself does not change, productivity does not scale. Reid Hoffman’s conductor strategy starts by breaking that illusion.

April 1, 2026 · 2 min · Junho Lee
Using Korean Legal Data for AI Agent Development via Beopmang API

Using Korean Legal Data for AI Agent Development via Beopmang API

Parsing raw legal XML means broken table structures and half a day lost on preprocessing. Beopmang is an API that delivers pre-cleaned JSON, solving that problem upfront.

April 1, 2026 · 2 min · Junho Lee
Optimizing Large-Scale Excel Downloads in Spring Boot

Optimizing Large-Scale Excel Downloads in Spring Boot

A Spring Boot library for streaming 1M-row Excel downloads without OOM. A single annotation eliminates the boilerplate.

April 1, 2026 · 2 min · Junho Lee
OpenDocuments: A Self-Hosted RAG Platform Connecting Scattered Team Knowledge

OpenDocuments: A Self-Hosted RAG Platform Connecting Scattered Team Knowledge

A self-hosted RAG platform that runs on Ollama to unify team documents scattered across Notion, GitHub, and S3. Natural language search works even in air-gapped environments without external APIs.

April 1, 2026 · 2 min · Junho Lee