Kürşad Erson erson

1) Prime Claude with `/init`

I started by running /init so Claude reads the repo and rewrites CLAUDE.md with real project affordances: how to run one test with xcodebuild, where Vice models live, what Swift 6.1 concurrency rules we enforce, and the bundle/CloudKit facts. I cut redundancy, kept only the sharp bits, and verified with CI. This establishes a trustworthy "ops manual" Claude sees first, not tribal memory.

Why: if the source of truth is precise, agents stop hallucinating paths/flags.

2) Level up Claude Code (settings, commands, hooks, nested docs)

Next pass: I mapped the whole Claude Code surface (settings, slash commands, MCP hooks, status line, nested CLAUDE.mds). Then I added:

.claude/settings.json — status line, model prefs, environment, and hook wiring.
Custom commands as the primary UX: small, composable, documented.

Complete iOS Project Claude Code Setup - Master Prompt

IMPORTANT: This comprehensive setup will transform any iOS project into a fully automated, context-aware, self-maintaining Claude Code environment. This prompt is designed specifically for Claude Code (claude.ai/code) users.

PHASE 0: Prerequisites & Environment Verification

0.1 Check Required Tools

Before starting, verify these tools are installed:

Using Gemini CLI for Large Codebase Analysis

When analyzing large codebases or multiple files that might exceed context limits, use the Gemini CLI with its massive context window. Use gemini -p to leverage Google Gemini's large context capacity.

File and Directory Inclusion Syntax

Use the @ syntax to include files and directories in your Gemini prompts. The paths should be relative to WHERE you run the gemini command:

Examples:

<core_identity> You are an assistant called Cluely, developed and created by Cluely, whose sole purpose is to analyze and solve problems asked by the user or shown on the screen. Your responses must be specific, accurate, and actionable. </core_identity>

<general_guidelines>

NEVER use meta-phrases (e.g., "let me help you", "I can see that").
NEVER summarize unless explicitly requested.
NEVER provide unsolicited advice.
NEVER refer to "screenshot" or "image" - refer to it as "the screen" if needed.
ALWAYS be specific, detailed, and accurate.

You are an expert in prompt engineering, specializing in optimizing AI code assistant instructions. Your task is to analyze and improve the instructions for Claude Code. Follow these steps carefully:

Analysis Phase: Review the chat history in your context window.

Then, examine the current Claude instructions, commands and config <claude_instructions> /CLAUDE.md /.claude/commands/*

Building Your Own MCP Server for Claude Code

This guide will walk you through creating a custom MCP (Model Context Protocol) server that integrates with Claude Code, allowing you to extend Claude's capabilities with external tools, APIs, or even other AI models.

What is MCP?

MCP (Model Context Protocol) is a protocol that allows Claude to communicate with external servers to access tools and capabilities beyond its built-in features. Think of it as a plugin system for Claude.

Prerequisites

Why did you do this?

Relax, I only have one Sunday to work on idea, literally my weekend project. So I tried Deepseek to see if it can help. Surprisingly, it works and it saves me another weekend...

What is your setup?

Just chat.deepseek.com (cost = free) with prompts adapted from this gist.

Does it work in one-shot or I have to prompt it multiple times?

Lessons learned with Cursor

Here are some key things that I've found working with Cursor that have really helped take it to the next level.

Ensure that you have a well written .cursorrules file. Cursor Directory has some great starting points.
The @Docs is crazy powerful. Cursor may not have indexed the version of the dependencies required. Using @SomePackageDocs vastly improve the accuarcy of code generation related to a depenency.
@web is also a very strong tool, but doesn't get added by default when using Cursor's composer. While you may not always need @web, its very useful for more obscure implementations.

Prompting

The most important thing by far is cearly articulating what you want to do. The more well defined your requirements the less deviation from the request will happen. I've added a prompt example.

Think o

	#!/usr/bin/env bun
	/**
	* Resilient AST-based patcher for Generic Code CLI
	*
	* This patcher uses Babel to parse and transform the CLI bundle,
	* making certain LLM-based checks configurable via environment variables.
	*
	* The patcher finds code by stable identifiers (querySource strings used for telemetry)
	* rather than function names, making it resilient to minification and refactoring.
	*

	You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

	## Core Principles

	1. EXPLORATION OVER CONCLUSION
	- Never rush to conclusions
	- Keep exploring until a solution emerges naturally from the evidence
	- If uncertain, continue reasoning indefinitely
	- Question every assumption and inference