-
UCLA
- Los Angeles, California
- mhmdaskari.github.io
- https://orcid.org/0009-0002-4136-8947
- in/mhmd-askari
Highlights
- Pro
Lists (26)
Sort Name ascending (A-Z)
Agentic AI
Agentic Vibe Coding
App Developement
Awesome stuff
Deep Learning and Computer Vision
Deep learning and computer vision + datasetsFoundation Models
Generative AI
GIS
Graph Neural Networks
GUI
Interview-related
Job search
LLM Skills
LLMs
Repositories related to large language modelsMachine Learning
Machine learning, causal inference, ensemble learningMCP
Useful MCPs for LLMsNatural Language Processing
Natural Language Processing, Large Language Models, PII removal toolsProbability and Statistics
Quant
Recommender systems
Reinforcement Learning
Speech Generation
System Design
Utilities
Weather Forcasting
World Models
Stars
A curated list of decision models (System One / typed decision models): hosted APIs, open-weight models, runtimes, SDKs, applications, benchmarks, and papers.
Generate a single PDF file from MkDocs repository.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Removes 20+ patterns of AI slop from any piece of writing.
Agent skill that removes signs of AI-generated writing from text
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, and Pi. 44 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
An LLM agnostic agent with causal reasoning tools and symbolic memory
Python framework for integrating geospatial data, 3D city modeling, and urban simulation.
Collection of publicly available IPTV channels from all over the world
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
Fast, interactive geospatial data visualization in Jupyter.
High Speed Assessment and Satellite Tracking for Emergencies
Skills for Designers and Engineers.
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
Desktop app to manage markdown knowledge bases
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Production-grade engineering skills for AI coding agents.
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills b…
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Skills for Real Engineers. Straight from my .agents directory.
An agent skill that helps make your interface feel better.
Astro template to help you build a website for your research paper, based on the Nerfies project page
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
Academic Research Skills for Claude Code: research → write → review → revise → finalize
Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows