Mohamed Khairy

Mohamed Khairy

Indie maker · Building DevSignal

About

Indie maker building dev tools & SaaS for solo builders. Currently shipping DevSignal — a GitHub-to-resume card generator. Stack: React, Next.js, Flutter, Firebase, Supabase. Always building, always shipping.

Badges

Tastemaker
Tastemaker
Gone streaking 10
Gone streaking 10
Gone streaking
Gone streaking
Gone streaking 25
Gone streaking 25
View all badges

Maker History

  • trigger-doctor
    trigger-doctorFind out why your AI agent skills never fire
    Oct 2026
  • DevSignal
    DevSignalTurn GitHub work into a recruiter-ready developer card.
    Aug 2026
  • 🎉
    Joined Product HuntJuly 31st, 2025

Forums

•

1mo ago

I built a free tool that tells you why your AI agent ignores your SKILL.md

Hey! Solo maker here

A few weeks ago I found out my AI agent was quietly ignoring skills I spent hours writing not because they were bad, but because of small structural issues I couldn't see.

So I built trigger-doctor: a free, open-source tool that reads your SKILL.md the way your agent does, then tells you exactly what makes it get ignored.

Free, no signup

•

1mo ago

Hi PH! Solo maker from rural Egypt — I just launched my first open-source tool 🩺

Hey everyone

I'm Mohamed from rural Egypt. I build everything myself code, design, support, all of it.

Last month I discovered my AI agent was quietly ignoring the skills I spent hours writing. Small structural mistakes I couldn't see. So I did what any stubborn maker does: I built a doctor for it.

trigger-doctor is a free, open-source tool that reads your SKILL.md the way your agent does and tells you exactly why it's being ignored.

•

1mo ago

trigger-doctor - Find out why your AI agent skills never fire

AI agent skills have a hidden failure mode: runtimes like Claude Code and Cursor load only the skill's name + description line, and decide from that alone whether to open it. If it doesn't match how users phrase requests, the skill silently never runs. trigger-doctor tests that gate: it simulates the judgment with a labeled suite, diagnoses misses, prescribes the fix, and saves a regression suite to re-run after model updates. Zero dependencies, CI exit codes, 3/3 skills.sh security audits.
View more