Eleven plain-Python Claude skills that scan charts, time entries, and Monte-Carlo your trade 10,000 times before any order goes out — and no order goes out without your yes.
Domain Apps
underdogs breaking outA Rust-based Chinese IME that treats your daily typing as a language lesson, because opening a study app is a chore.
Freehire crawls 3.3 million live IT postings directly from company ATS pages, deduplicates the reposts, and serves them through a faceted search API — no recruiters, no dead links.
This contest entry orchestrates 15 McDonald's MCP tools to turn "city + headcount + budget" into real, priced group-meal plans — without ever inventing a number.
A pack of plain-Python Claude skills that clones 13F portfolios, stalks congressional trades, and sizes orders to your budget, but never places a trade without your yes.
Because LLMs confidently invent struct offsets and behavior from binaries, this toolkit makes them prove every claim against the actual bytes.
This MCP-based skill computes the genuinely cheapest order at your current McDonald's China store — and tells you how much money your expiring coupons are quietly bleeding.
Harvey runs an autonomous cold-email pipeline on your existing Claude or ChatGPT subscription instead of a metered API key.
ARTEX is a Go + Next.js autonomous penetration-testing system where LLM-driven agents explore your asset graph, with human approval gates on the dangerous parts.
Most AI writing tools destroy document formatting on save, so GenOffice treats the original file as immutable and splices edits only where you actually changed something.
ARTEX is an autonomous penetration-testing system that won Baidu's 'agent+' challenge by making every AI-driven attack auditable and interceptable.
mcncarl/jianying-headless lets Python scripts generate native, multi-track Jianying Pro drafts from JSON plans and export MP4 through the installed macOS app engine—without using an official SDK.
AiSOC is an open-source, self-hostable AI SOC that logs every LLM prompt and tool call so you can replay investigations instead of trusting a black box.
ARTEX is a multi-agent autonomous penetration testing system that won Baidu's agent attack-defense challenge, now maintained as open source.
CozyClay puts previsualization in a single browser tab so you can stage scenes, pose characters, and hand the camera off to an AI model or an LLM agent.
Dossier is a single-user, self-hosted app that turns one profile into tailored resumes and cover letters — using only facts you actually have.
A research platform that fuses CARLA, AirSim, and OpenSim into one Unreal-based sandbox for training autonomous cars, drones, and embodied humans.
VulnHunter is an agentic SAST tool that thinks like an attacker, then tries to disprove itself before showing you anything.
A hunter open-sources the LLM prompt chain behind an evidence-first bounty process — but leaves the infrastructure as an exercise for you.
Cairn searches unknown state spaces with no predefined agent roles, using only a shared blackboard of facts and intents—proven by clearing 54 of 54 hackathon targets on its first live run.


