Hello world
Your LLM, with MCP tools + agent skills built in — MCP · skills · native · HTTP · built-in · A2A tools behind one interface, byte-identical across JavaScript, Python, Go, Java, C# and Elixir. Docs: https://muthuishere.github.io/toolnexus/
npx -y skills add muthuishere/toolnexus --skill hello-worldAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
A tiny example skill. Use when you want to see how skill loading (progressive disclosure) works end to end.
SKILL.md
0.6 KB, as published. Nobody here has run it
Hello World Skill
This is the skill body. When the model calls the skill tool with
{ "name": "hello-world" }, everything below the frontmatter is injected into the
conversation, along with a sampled list of files in this directory.
Steps
- Read
scripts/greet.shin this skill's base directory. - Run it with the user's name.
- Report the greeting back.
Relative paths (like scripts/greet.sh) are resolved against the base directory
printed in the tool output.