agentleFS
Sign inStart free
CaskeyCodingCaskeyCoding/specself-starter/.claude/skills/upgrade/SKILL.md

upgrade

Skill0 starsChanged 4 months agoMITView on GitHub

Pull SpecSelf kit STRUCTURE improvements (templates, steering, personas, .claude) from upstream after your fork has diverged — proposing each change, never touching your-life/ corpus. Use when the starter has shipped updates you want.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use new, context and 10 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

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run a structure-only upgrade of this SpecSelf fork against the upstream starter.

    line 6
  2. Very specific:

    Confirm the upstream remote: Check git remote -v for an upstream.

    line 16
  3. Very specific:

    Diff structure only: Run the bundled script — it is the deterministic, corpus-safe diff (it hard-excludes your-life/): bash …

    line 20
  4. Very specific:

    Do not hand-roll a git diff that could include your-life/.

    line 23
  5. Distinctive:

    Record the upgrade: After applying, suggest the human note which CHANGELOG version they're now on (a line in their own notes or a fork …

    line 33
  6. Very specific:

    Never force-overwrite a diverged file.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 27 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

Run a structure-only upgrade of this SpecSelf fork against the upstream starter. Honor AGENTS.md and the one rule: you propose, the human decides and applies. Never read, diff, propose, or write anything under your-life/ — that is the human's corpus, not kit structure (steering/privacy.md).

Read first: UPGRADING.md (the full flow + the dry-run example), CHANGELOG.md (what changed upstream), steering/privacy.md (why corpus is out of scope).

Steps

  1. Confirm the upstream remote. Check git remote -v for an upstream. If it's missing, tell the human the one-time setup and stop until they run it: git remote add upstream <starter-url> && git fetch upstream. Otherwise git fetch upstream to refresh.
  2. Diff structure only. Run the bundled script — it is the deterministic, corpus-safe diff (it hard-excludes your-life/): bash .claude/skills/upgrade/upgrade-diff.sh upstream/main Do not hand-roll a git diff that could include your-life/; use the script.
  3. Read CHANGELOG.md for the upstream releases between the human's version and upstream/main, so each file change has a why, not just a diff.
  4. Propose, ranked. For each changed structure file, present: what changed, why (from CHANGELOG), and whether the human likely diverged on it (their edits should win). Rank by value: new/renamed skills and steering fixes first, cosmetic last. Recommend one of take upstream / merge by hand / skip — you diverged here.
  5. Apply only what the human accepts, one file at a time, with the commands the script prints (git checkout upstream/main -- <path> or a hand-merge). Make no change they did not confirm. Touch nothing under your-life/.
  6. Record the upgrade. After applying, suggest the human note which CHANGELOG version they're now on (a line in their own notes or a fork CHANGELOG entry).

Hard boundaries

  • your-life/** is out of scope, always — not compared, not proposed, not written. The script enforces this; you reinforce it.
  • Never force-overwrite a diverged file. Where the human edited a template or steering doc to taste, default to merge by hand and keep their intent.
  • This skill writes nothing on its own. Every apply is a human-confirmed command.

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.

Check your setup, free