agentleFS
lithammerlithammer/ai/skills/librarian/SKILL.md

librarian

Skill0 starsChanged 52 days agoMITView on GitHub

Clone or refresh a remote git repository into a shared local cache and return its path, so the source can be read with ordinary file tools instead of over the web. Use before cloning a repository yourself, before fetching repository files over the web, when a dependency's or upstream project's implementation needs reading, or when a repository URL or `owner/repo` reference names code the task must look at. Not for the repository already checked out as the working directory, nor for pull request or issue metadata that `gh` answers without a checkout.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use bro and retro.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    bro

    Re-explain the previous assistant message in a much simpler way, for when the reply made you go 'bro what'. Use /bro to get a simpler version of the last answer in Plain Language + Chicago Manual of Style, with diagrams where they help.

    Also in 3 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 3 projects that use this

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 19 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:

    Add --force-update when the checkout must reflect commits pushed minutes ago.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 19 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

Librarian

Resolve the repository to a cached checkout, then search and read it with ordinary file tools. checkout.sh sits in this skill's directory; run it from there:

bash <skill-dir>/checkout.sh <repo>

<repo> is any reference to the repository: owner/repo, host/org/repo, an HTTPS or SSH URL, or a deep link to a file, tree, or pull request. The command prints the checkout path, cloning on first use and fast-forwarding a stale checkout, so re-running it for a repository already resolved is cheap — call it again rather than holding on to a path from earlier in the session.

Add --force-update when the checkout must reflect commits pushed minutes ago; refreshes are throttled to five minutes otherwise.

A warning on stderr means the checkout could not be fast-forwarded and may be behind origin. The path it prints is still the one to read.

Working in a checkout

Checkouts live under ~/.cache/checkouts/<host>/<org>/<repo> and are shared across every session and task, so treat one as read-only. When a task needs to modify the source, copy the checkout or add a worktree elsewhere and work there, leaving a clean tree that the next fetch can fast-forward.

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.