Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

🔥 Real-time terminal dashboard for Caddy servers, with built-in FrankenPHP support

WIP Caddy 2 ingress controller for Kubernetes

Daily-updated IP ranges for 35+ providers (AWS, Azure, GCP, Cloudflare, GitHub, Fastly, Linode + GoogleBot, BingBot, GPTBot) in 12+ formats: TXT, JSON, CSV, SQL, Nginx, Apache, iptables, nftables, UFW, HAProxy, Caddy + merged CIDRs

Guide the user through containerizing and serving a simple website or documentation folder with Docker — inspects the project to detect what to serve (ready-to-serve static HTML, a buildable site that emits static output, or a raw markdown/docs folder that needs rendering), generates a Dockerfile, .dockerignore, docker-compose.yml, helper run/build commands, and a 'Running with Docker' README section, then offers to build and smoke-test the container and publish the image to Docker Hub or GHCR. Uses nginx:alpine for static content and a multi-stage build when the site must be generated. Only invoke when the user explicitly types /ai-assist-dockerize-website. Never auto-trigger from general conversation about Docker, containers, websites, or Dockerfiles.