| # Hello, World! | |
| This is a test file. |
This document captures learnings about how Agent Skills handle references/, recipes/, and services/ folders, including token budget implications and best practices based on the AgentSkills.io specification and GitHub Copilot implementation behavior.
Agent Skills use a three-tier loading model to efficiently manage LLM context windows:
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.
Launch a new agent that has access to the following tools: Bash, Glob, Grep, LS, exit_plan_mode, Read, Edit, MultiEdit, Write, NotebookRead, NotebookEdit, WebFetch, TodoRead, TodoWrite, WebSearch. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries, use the Agent tool to perform the search for you.
When to use the Agent tool:
When NOT to use the Agent tool:
.claude/ at the project root (per-repo, team config)~/.claude/ in your home directory (global, personal config)There is also a separate file ~/.claude.json (not a directory) that Claude Code writes to for app state and OAuth tokens. Think of it like .git/ vs .gitconfig: one is a per-project directory, one is global.
Note: There is no .claude-code directory, Claude Code uses .claude/.
| # Jason Gomez - June 2024 | |
| # Problem 1: When installing Vim for Windows using winget it's not added | |
| # to $PATH so it cannot easily be used from the command line. | |
| # Problem 2: The path to the Vim executables keeps changing as the | |
| # version number is part of the path. | |
| # Solution: This script makes a persistent symlink to the latest installed | |
| # version of Vim for Windows and adds it to $PATH. Re-run the | |
| # script when a new version of Vim is installed. | |
| # Get all Vim directories and sort them by version number |
Note: for a Windows setup without WSL see this gist
See also Windows Subsystem for Linux Installation Guide for Windows 10
| #Requires -Version 5.1 | |
| <# | |
| .SYNOPSIS | |
| BootstrapUtils - Reusable PowerShell utilities for Windows bootstrap and configuration | |
| .DESCRIPTION | |
| This module provides common utilities for: | |
| - Logging with consistent formatting | |
| - Admin privilege management | |
| - Scoop package manager operations |
| #!/usr/bin/env bash | |
| # | |
| # bootstrap.sh - macOS 輕量終端開發環境一鍵安裝腳本 | |
| # 包含：Ghostty + zellij + yazi + lazygit + fastfetch + Neovim/LazyVim + 現代工具 + oh-my-zsh | |
| # 語言環境：Python(uv/pipx)、Go、Rust(rustup)、Java(Liberica 20 Full+JavaFX)、Node(pnpm+bun)、Ruby | |
| # | |
| # 用法：curl -fsSL https://gist.githubusercontent.com/fuzzbuster/a117689823ba87c27437a44129253dcb/raw/1b2e930ad152a7ceb9fbb7df581b304e2d1685a0/macos_bootstrap.sh | bash | |
| # 或 bash bootstrap.sh | |
| # | |
| # 可重複執行，不會重複安裝或破壞既有配置 |
| #!/usr/bin/env bash | |
| ## | |
| # Bootstrap | |
| ## | |
| # export HOMEBREW_CASK_OPTS="--appdir=${HOME}/Applications" | |
| # XCode Select | |
| sudo xcode-select --install |