Roblox Luau Scripting
Use Roblox services, Instances, events, shared modules, server Scripts, LocalScripts, and validated remote requests.
Original workflows for websites, images, presentations, and everything in motion.
Use Roblox services, Instances, events, shared modules, server Scripts, LocalScripts, and validated remote requests.
Evaluates an ML GPU cluster for a cloud trial or acceptance test: environment dump, isolated newest PyTorch, matmul FLOPS (MAMF/MSMF) on every GPU while the others compute, intra-node all-reduce bandwidth and per-call latency of every collective, the same inter-node on every node you were given (omit those sections if there is only one node), fio on local disk and shared FS, dated markdown report.
Run resumable improvement loops or bounded investigations in local projects with explicit objectives, allowed changes, budgets, and evidence.
Route job evaluation, tailored CVs, application tracking and interview preparation through one workspace.
Create Lua game loops, delta-time motion, input handling, screen states, and window settings in LÖVE.
Evaluate useful calculators, generators and utilities as marketing assets with distribution plans.
Design and implement MCP servers with discoverable tools, clear schemas and task-based evaluations.
Create, revise, package, and evaluate agent Skills from workflows, prompts, SOPs, and scripts using a routed review process.
Turn a recurring problem into one installable skill through needs analysis and staged validation; prepare public distribution only when requested.
Attach a factual employer sponsorship signal from configured data to US-role evaluations.
Code comment hygiene for AI coding agents: remove generic AI-slop comments, keep the valuable ones, never touch the code.
Create and improve reusable skills with test cases, comparative evaluations and trigger-description refinement.
Build Lua gameplay with collections, game objects, lifecycle scripts, input, messages, factories, proxies, and Bob checks.
Assists with job applications: evaluating job postings, tailoring CVs, writing cover letters, and preparing for interviews.
Apply practical large-model training and operations guidance, and evaluate GPU cluster performance and readiness.
Consolidate previous agent sessions into reviewed memory and skill improvements through an offline sleep workflow.
A small library, made with care. More skills are on the way.