agentleFS
dracocephalumdracocephalum/dc-agentics/.claude/skills/upgrade/SKILL.md

upgrade

Skill0 starsChanged 37 days agoApache-2.0View on GitHub

Three operations under one verb - bring the dc-agentics toolkit's own pinned versions current; sync a repository it initialized to a newer toolkit commit, replacing the toolkit-owned folders whole with the script in repo/sync.sh; or convert a standalone repository to a monorepo. Plans first; applies second.

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use context, init and 8 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.
  • 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

  • 0xSeroSkill

    security

    Also in 4 projects that use this

The file

Files
SKILL.md

agentics/ and the toolkit's shims in a target are the toolkit's: a sync replaces them whole, by script, and the repository's own rules live outside them. The recorded commit says what changed, not what to merge.

Find the standard

repo/upgrade.md in a dc-agentics checkout. Operation 2 needs both repositories present, because its script runs from the toolkit checkout; ask for the checkout path rather than guessing it. Read the file and follow it - what the script does, what it reports for you to apply by intent, and the one-time adoption of the guidelines block are all there.

Choose the operation from $ARGUMENTS

ArgumentsOperation
toolkit1 - bring the toolkit's own pins current
target <path>, or a path2 - sync that repository to the current toolkit: sh repo/sync.sh --plan <path>, read, then --apply
monorepo3 - convert a standalone repository to a monorepo
nothingask which; they touch different repositories

Operation 3 needs no toolkit checkout; run it from inside the repository being converted. Run from a toolkit checkout instead, it first checks that the two agree, and declines rather than mixing a payload delta into a layout change.

Then

The tree being changed must be clean - git status --porcelain empty, untracked included - or decline and say so; the document says why, and what the one-command undo is that a clean start makes possible.

Produce the plan first: what changed between the two commits, what it would do, and what is left for you to apply by intent. Apply as a second step, and let source-control.mode in the target's .agentics.yaml decide what may be committed without asking; the script itself never commits.

Operations 2 and 3 finish with dotnet build, dotnet test, and /scrub - the scrub checks are the post-upgrade checks. Operation 1 has nothing to build in the toolkit; the document says how a bump is proven.

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.