Developer guide

How to find, install, write and publish a skill — in the browser, from a terminal, or from inside an agent. Everything here works against the live catalogue.

Connect

The catalogue speaks the Model Context Protocol, so an agent can search it mid-task instead of you stopping to look it up.

Over HTTP — nothing to install

Any client that takes a remote server needs only the URL:

{
  "mcpServers": {
    "llmskillhub": {
      "url": "https://api.llmskillhub.com/mcp"
    }
  }
}

Over stdio — if you have the CLI

The same tools from the same code, reaching the catalogue through the same public API:

{
  "mcpServers": {
    "llmskillhub": {
      "command": "llmsh",
      "args": ["mcp"]
    }
  }
}

One difference worth knowing: the stdio server sends your token if you are signed in, so it can see your own versions before they are listed. The URL is anonymous and sees only what is public.

The tools

search_skills	the same search the website uses
get_skill	description, licence, every version and its digest
read_skill_file	any file from a published version
list_categories	the category vocabulary
install_command	the command to install one

read_skill_file is the one worth reaching for before recommending anything: it returns the instructions an agent would actually load, with hidden and bidirectional characters revealed rather than passed through.

What it will not do

Nothing here writes to your disk. install_command hands back the command instead of running it. Installing puts a third party’s instructions somewhere an agent will load them, and that is a decision for a person rather than for a model — over HTTP it is also the only honest answer, since the server cannot reach your machine at all.

Nothing here needs an account. Every tool reads what is already public, so there is no token to configure and nothing to revoke.