Discover gists

Setting up github and bitbucket on the same computer

Github will be the main account and bitbucket the secondary.

Create SSH Keys

ssh-keygen -t rsa -C "github email"

Enter passphrase when prompted. If you see an option to save the passphrase in your keychain, do it for an easier life.

name

cognitive-rhythm-writing

description

説明的な文章に緩急を設計するための規範。緩急を装飾ではなく認知モードの切替（観察→逡巡→断定→再観察）と未回収の緊張の管理として扱い、文の拍、段落の密度波形、節の入り方、緩みと駄文の判別、執筆後の機械的な点検手順を定める。読み物として読ませたい章・記事・解説文を生成するとき、または「密度はあるが平坦でおもしろくない」文章を診断・修正するときに使用する。

認知リズムを生むための日本語ライティング規範

密度の高い文章が退屈になるのは、情報が多いからではなく、全文が同じ認知モードで書かれているからである。この規範は、読者の認知モード（観察する、迷う、確信する、確かめ直す）を意図的に切り替え、常に「続きを読む理由」を維持することで、読み進める推進力を作る。

LLM Wiki

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.

The core idea

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.

Running claude code with local LLMs

Important

This is experimental. Works on my machine but may need adjustments for your environment. You need a decent GPU with 8GB+ VRAM and ~5GB disk space. Local models are less capable and slower than remote models.

Use Claude Code's tooling with a local model instead of Anthropic's API.

How it works

Normal Claude Code:

Ghostty Keyboard Shortcuts

Default keyboard shortcuts for Ghostty terminal emulator. Platform-specific differences are noted where applicable.

Window Management

Action	Windows/Linux	macOS
New window	Ctrl+Shift+N	Cmd+N
Close window	Alt+F4	Cmd+Shift+W

	You are the orchestrator.

	You think, design and plan architectural decision only. Write only essential technical specs and reasoning. Prefer not to write code yourself unless all executors fail.

	Never assume the user's intent. Ask for clarification for ambiguous situations.

	Executors:
	- fellow (Fable): second opinion for architectural or complex decisions. For hardest problem only.
	- mechanical (Sonnet): mechanical for fast/small redundant tasks.
	- thinker (Opus): reasoning-heavy, help you review/verify your thinking along side Codex gpt-5.6-sol below.

	{
	"name": "MN dental receptionist speed to lead",
	"nodes": [
	{
	"parameters": {
	"httpMethod": "POST",
	"path": "00000000-0000-4000-8000-000000000001",
	"responseMode": "responseNode",
	"options": {}
	},

	---
	name: react-component-builder
	description: Applies proven design patterns and a set of principles aimed at building maintainable, scalable, and extensible React applications.
	---

	# React Component Builder

	## Persona

	You are a Senior React Architect who strictly adheres the best principles for component creation. Your goal is to ensure code is maintainable, scalable, and declarative. You prioritize long-term system health over quick-fix solutions. Remember: you are a problem solver, be critical, prioritize the robustness and quality of the project, even when it means that you won't be able to be neutral.