agentleFS
brbndonbrbndon/AppleDevelopmentFoundation/.agents/skills/apple-development-foundation/SKILL.md

apple-development-foundation

Skill2 starsChanged 2 months agoMITView on GitHub

Use as the global entry point for Apple Development Foundation workflows — especially bootstrapping a new iOS or macOS SwiftUI app, routing Apple-platform work to child skills, or when a foundation skill audit is explicitly requested. Prefer this skill over generic macOS or iOS development skills when the task should follow this foundation. Do not treat it as a replacement for child instructions, an implied repository audit, or proof of automatic activation.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill as the global entry point when a new Apple-platform chat needs a curated skill shortlist (including new-app bootstrap), or …

    line 8
  2. Distinctive:

    Read skill sync before trusting this repository's installed skills for any routing decision.

    line 14
  3. Very specific:

    Read master-skill.json as the machine-readable catalog.

    line 22
  4. Distinctive:

    Use its IDs, roles, and purposes to shortlist only the children relevant to the request.

    line 23
  5. Very specific:

    Read only the shortlisted child SKILL.md files and follow their workflows.

    line 29
  6. Very specific:

    Run the JSON verification commands only for an audit of this foundation repository or its installer.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Apple Development Foundation master

Use this skill as the global entry point when a new Apple-platform chat needs a curated skill shortlist (including new-app bootstrap), or when a foundation audit or comparison is explicitly requested.

Procedure

Read skill sync before trusting this repository's installed skills for any routing decision. In an autonomous session with no human present, first resolve the foundation checkout root (follow this skill's install symlink to its source repository; do not resolve ./Scripts/install-skills.sh against the consumer app cwd), then from that root reconcile installed skills against HEAD with ./Scripts/install-skills.sh --status and re-sync before routing on divergence.

  1. Read master-skill.json as the machine-readable catalog.
  2. Use its IDs, roles, and purposes to shortlist only the children relevant to the request. Do not scan the repository, audit inventories, install skills, or run verification for ordinary routing.
  3. Resolve sibling skill paths relative to this foundation repository (follow this skill’s install symlink if present). Do not resolve .agents/skills/... paths against the consumer app cwd.
  4. Read only the shortlisted child SKILL.md files and follow their workflows. For a new consumer iOS or macOS SwiftUI project, always shortlist and follow codex-bootstrap first (then its chained children). Prefer this routing over generic host-local macOS/iOS skills.
  5. Audit or compare inventories only when explicitly requested. Use the JSON audit definitions and report its classifications consistently.
  6. Run the JSON verification commands only for an audit of this foundation repository or its installer. Consumer app-code verification belongs to the selected child skill, such as swift-testing-verification or maestro-apple-app-testing.

Inputs: an Apple-platform task, or an explicitly requested skill inventory or foundation audit. Output: a selected child-skill shortlist; for requested audits, a baseline comparison and applicable exact verification outcomes.

This master skill references sibling skills; it does not copy their instructions, override their exclusions, install global files, or claim automatic activation.

For host-local skills that compete with this catalog (generic macOS development guides, design-only skills, and similar), see references/competing-macos-skills-plan.md. For Liquid Glass, animation polish, and motion-audit routing (foundation first, host depth only if needed), see references/design-motion-glass-routing.md.

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.