agentleFS
thenavidmthenavidm/skill-builder/skills/skill-publish/SKILL.md

skill-publish

Skill0 starsChanged 29 days agoMITView on GitHub

Puts a plugin repository on GitHub, private first, with a description and topics people search for. Runs only when asked by name.

  • Installs packages

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No email address, key or private path anywhere in the repository (check catches keys).

    line 17

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Publish the repository

What people see first decides whether they install it: the description, the topics, the README's first screen. A public repository is indexed the moment it goes public, so it goes up private, gets checked, then opens.

The engine runs as npx -y @thenavidm/skill-builder@latest. Where skill-builder is installed (npm install -g @thenavidm/skill-builder), run skill-builder instead: it's the same engine, without the download.

1. Ready?

  • check and package --check pass, and install passes each tool's validator.
  • The README's first line and product.json's description say the same thing in the same words, and lead with what people search for.
  • No email address, key or private path anywhere in the repository (check catches keys).

2. The steps

npx -y @thenavidm/skill-builder@latest repo publish --profile profile.json

It lists the GitHub commands in order: create it private with the description and push; set the topics; turn on private vulnerability reporting (so the security policy's link works); make it public; tag the first release. Show each command, get a yes for that one, run it, confirm it worked, then the next.

3. After it's public

Open the repository page and check what a stranger sees: the description, the topics, the README's first screen, the licence. Then tell them how people install it in each tool, from the README.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.