agentleFS
aminbadhaminbadh/workspace-starter/.agents/skills/upgrade/SKILL.md

upgrade

Skill0 starsChanged 24 days agoMITView on GitHub

Take the fixes and new versions the template has released since this workspace was made, file by file, without overwriting anything the user changed. Use when the user asks to upgrade or update the workspace, asks whether the template has changed, or when the weekly review reports that it has.

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use new, context and 9 more.

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.
  • codebycoreySkill

    new

    Start a new change with a proposal. Use when starting a feature, creating a proposal, or beginning planned work.

    Also in 4 projects that use this

  • aegiswizardSkill

    context

    Also in 3 projects that use this

  • MicrosoftSkill

    init

    Also in 6 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 5 projects that use this

  • tuistSkill

    migrate

    Migrates existing Xcode projects to Tuist generated workspaces with build and run validation, external dependency mapping, and migration checklists. Use when adopting Tuist for an existing app or converting a hand-edited Xcode project to generated projects.

    Also in 3 projects that use this

  • imehrSkill

    frontend

    Use when building UI components, pages, or features - guides Claude through the approved frontend stack (Next.js 15, React 19, Shadcn, Tailwind) with design-first workflow for complex UIs, enforcing patterns and quality standards

    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 25 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:

    If README.md has no Upstream: line, skip this: the workspace has no template above it.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 25 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

Upgrade

The template this workspace was made from keeps improving: its skills, the linter, CONVENTIONS.md. This skill brings those changes in one file at a time, with the user's yes, and never touches their content (PROFILE.md, their domains, their answers in AGENTS.md).

The template's URL is on README.md's Upstream: line. What this workspace last received is .agents/manifest.json, which the template writes on every release. The script scripts/upgrade.py in this skill's folder compares the two; run it with uv run.

1. Plan

uv run .agents/skills/upgrade/scripts/upgrade.py plan fetches the template into a temporary folder and lists every file it changed since this workspace last took it, with what that means here:

It saysMeaningWhat to do
updateOnly the template changed itOffer it, with a one-line summary of the change
newThe template added itOffer it, saying what it is
conflict: both changedThe user edited it tooShow the diff both ways and ask: take theirs, keep yours, or merge by hand
removed upstreamThe template dropped itAsk before removing; keep it if they still use it

Read each change before offering it (git diff --no-index <their file> <template copy>), and say in plain words what it does for them. Never offer a batch as "updates available".

2. Apply

uv run .agents/skills/upgrade/scripts/upgrade.py apply <path> ... takes the template's version of the files the user agreed to. Give each file's template path: for an installed add-on, the path plan shows after "from". It saves each replaced file to a backup folder first and prints where. For a conflict they want merged, edit the file by hand instead, keeping both sides' intent, and show them the result.

Then, by hand:

  • A new skill: link it for Claude Code (ln -s ../../.agents/skills/<name> .claude/skills/<name>) and add its row to AGENTS.md's skills table.
  • AGENTS.md: it is the user's file, so it is never in the manifest. Compare the template copy's general sections (from "What this workspace is" through "What to do now", and "Output") with theirs, and offer any rule the template added or changed, one at a time. Their "Tasks", "Working with me" and "What the agent may do" stay theirs.
  • An add-on they have installed: its files arrive through the same plan. A new add-on appears in .agents/addons/; mention it, and leave moving it in to the onboard skill.

3. Finish

uv run .agents/skills/upgrade/scripts/upgrade.py finish records the template's manifest as received, including for files they chose to keep as theirs (they have seen that version, so it is not offered again), and removes the temporary copy. Run the linter, say what changed in a few lines, and leave everything uncommitted for them to review.

No manifest yet

A workspace made before the template shipped a manifest has no .agents/manifest.json. plan then treats nothing as received and lists every file that differs from the template, so the user looks at each once; finish writes the manifest, and later upgrades are file by file as above.

Weekly

If README.md has no Upstream: line, skip this: the workspace has no template above it. Otherwise run plan and report in one line whether the template has anything new, naming the files. Do not apply anything in the review; the user says when.

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.