Skip to content
View royphilip's full-sized avatar
1 follower · 0 following

Block or report royphilip

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
royphilip/README.md
BuilderBug Logo

Roy Philip // Tools & Tech for Developers Who Ship

Full-stack engineer building production-grade tools and DeFi infrastructure.
royphilip.xyz · X/Twitter · GitHub

I'm a full-stack engineer, currently building the tech behind aixCB Capital. My focus is on creating tools that solve real problems developers and users face daily. If I find myself doing something repetitive, I build a tool to automate it. This profile showcases some of those tools.

My philosophy is simple: ship quietly, consistently. The work is battle-tested in production; the repos are the proof.

🛠️ My Projects

These are personal dev tools I built to scratch my own itch. They are all housed in a private monorepo but deployed for public use.

Project Description Tech Stack
📊 PromptLint → Analyze code2prompt output for optimized LLM workflows. Cuts context bloat by 40-60%. React Vite TypeScript Tailwind
🧹 SyntaxScrub → Instantly strip comments from code. Perfect for cleaning files for prompt engineering or analysis. React Vite TypeScript Tailwind
✨ SVGClean → Optimize SVG files by removing unnecessary data for smaller files and faster loading. React Vite svgo Tailwind
🔄 Doc Converter → Convert between Markdown and Google Docs without the usual formatting headaches. React Vite marked turndown

📝 Featured Article & Analysis

I enjoy testing assumptions and sharing data-driven insights. Here's my latest analysis on LLM performance.

JSON vs XML OG Image

JSON vs. XML: A Data-Driven Analysis of LLM Parsing Efficiency

Tested 12 major LLMs across 8 companies. A definitive, data-driven analysis reveals that format preference is dictated by a model's underlying architecture, not a universal rule.

Read the full article →

💻 My Stack

I care more about shipping solutions than debating frameworks, but this is the gear I use most often.

Frontend Backend Databases Tooling & DevOps AI & LLMs
React Node.js PostgreSQL Bun Vite Claude Code Cursor
Next.js Python Redis Turbo PM2 OpenAI API Gemini
TypeScript Express SQLite TailwindCSS Git code2prompt
Wagmi viem Prisma MySQL Hardhat Repo Prompt
Various OSS Models

Popular repositories Loading

  1. royphilip royphilip Public

  2. llm-format-benchmark llm-format-benchmark Public

    Python

  3. docs docs Public

    Forked from base/docs

    Documentation for building on Base

    TypeScript