hboon

name	review-dirty
description	Review dirty code changes. When user say to "review" or "review changes" or "review dirty code"

All dirty repo changes are likely made in this session, though not always

if you are Codex, just review the dirty code and ignore the rest in this skill. If you are not Codex, continue (even if this is a small diff):

Do not modify anything unless I tell you to. Run this cli command (using codex as our reviewer) passing in the original prompt to review the changes: codex exec "Do not modify anything unless I tell you to. Review the dirty repo changes which are to implement: ". $ARGUMENTS. Do it with Bash tool. Make sure if there's a timeout to be at least 10 minutes.

hboon

#Run by itself and keep running to watch for new screenshots and copy to clipboard. Useful for pasting them into Claude Code instead of dragging and dropping files
function watchscreenshots
  fswatch -0 --monitor fsevents_monitor --latency 0.1 \
    --event Created --event Renamed --event Updated ~/Desktop | while read -z path
    test -f "$path"; or continue
    set base (basename -- "$path")

    # Match macOS-style screenshots only
    if string match -q "Screenshot * at *.*.png" "$base"
      # Wait briefly for the file to finish writing

hboon

Error in user YAML: (<unknown>): did not find expected key while parsing a block mapping at line 1 column 1

---
argument-hint: [filename with project prompt] [msg]
description: Load a file as context of what the current task is about and do something. Useful for reviewing or fixing based on reviews
---

The current git dirty state (refrain from automatically read all the modified files right away unless filename(s) are explicitly mentioned) is to implement the requirements described in the file reference/$1.

Don't do anything until I tell you to. I will tell you next.

This is what is next:

hboon

Executive Summary

This guide documents how to use Factory's Droid CLI with your Claude Code Max subscription (OAuth authentication) instead of pay-per-token API keys. The solution leverages CLIProxyAPI as a transparent authentication proxy that converts API key requests from Factory CLI into OAuth-authenticated requests for Anthropic's API.

Architecture Overview

Factory CLI → [Anthropic Format + API Key] → CLIProxyAPI → [Anthropic Format + OAuth] → Anthropic API
                                                  ↓
 (Auth Header Swap)

hboon

The Ultimate Swift Testing Playbook (2024 WWDC Edition, expanded with Apple docs from June 2025)

Updated with info from https://developer.apple.com/documentation/testing fetched via Firecrawl on June 7, 2025.

See also my blog: See also my blog post: https://steipete.me/posts/2025/migrating-700-tests-to-swift-testing

A hands-on, comprehensive guide for migrating from XCTest to Swift Testing and mastering the new framework. This playbook integrates the latest patterns and best practices from WWDC 2024 and official Apple documentation to make your tests more powerful, expressive, and maintainable.

---

1. Migration & Tooling Baseline

hboon

Notes

• MCP servers enabled: Brave Search, Fetch, Puppeteer (optional).
• Recommended way to use it: create a project "Deep Research" and add the prompt as custom instructions.
• Recommended model: Sonnet 4 with Thinking. Sonnet vs Opus does not make much difference from experience.
• (As of the time of writing,) Do not enable Claude's built-in web search feature!
  • I've compared the two versions and the quality difference is significant.
  • It seems that the built-in system prompt that gets enabled, is terrible for deep research. A few examples: It explicitly limits Claude to only running one or a few searches in most cases; it contains numerous instructions regarding never quoting directly,

hboon

--Modified from https://stackoverflow.com/a/5519588
function diffLineWithNext()
    local f1 = vim.fn.tempname()
    local f2 = vim.fn.tempname()

    vim.api.nvim_command(".w " .. f1)
    vim.api.nvim_command("+1 w " .. f2)

    vim.api.nvim_command("tabedit " .. f1)
    vim.api.nvim_command("hor diffsplit " .. f2)

hboon

#Use this to do `gco -b <branch> <commit>`
function pr
    set --local hash (gcommit)
    #echo "in our pr: $hash"
    set --local msg (git show -s --format=%B $hash | head -1)
    #echo "in our pr: $msg"
    set --local branch (string lower $msg | string replace -a -r "[ /#]" "-" | string replace -a -r "[\(\)\.\[\]'`\":]" "")
    #echo "in our pr: $branch"
    echo "Running: git checkout -b $branch $hash"
    git checkout -b $branch $hash

hboon

#!/usr/bin/env ruby

#Opens URLs embedded in STDIN (so it's useful in vim by selecting text and running it)

require 'uri'

input = $stdin.read.split("\n")

urls = input.map do |line|
  URI.extract(line, ['http', 'https'])

hboon

//Proper way to implement error types. Implement `errorDescription`, not `localizedDescription` and the global handler `getErrorMessage(error: Error)` is easy to implement, not need a stupid switch case
//Key is implement `errorDescription` instead of `localizedDescription` and must not implement `localizedDescription` at all

import Foundation

struct E1: LocalizedError {
    var errorDescription: String? {
      return "E1's errorDescription"
    }
}