agentleFS
sreejithramansreejithraman/SreeStack/skills/app-intents/SKILL.md

app-intents

Skill1 starsChanged 16 days agoMITView on GitHub

App Intents work on Apple platforms. Use when exposing app actions or content to Apple Intelligence, Siri, Shortcuts, Spotlight, widgets, controls, or hardware entry points; designing AppEntity queries; or diagnosing intent discovery and execution.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the project's supported Xcode, Swift, and OS versions as the API boundary.

    line 18
  2. Distinctive:

    Add the smallest discovery surface that makes the action useful.

    line 37

“Common” is measured: kept by at least 6 in 10 of the 5 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

App Intents

Expose a small, stable action layer that reflects what people want to do with the app. Keep intents as adapters over existing domain services rather than a second implementation of product behavior. When designing intent inputs or service boundaries, read Type System Discipline and Boundary Discipline. For mutating actions that may be retried or interrupted, read Make Operations Idempotent and apply it at the domain service that owns the effect.

Use the project's supported Xcode, Swift, and OS versions as the API boundary. App Intents changes between SDK releases, so confirm version-sensitive APIs in the installed SDK or current Apple documentation before adopting them.

Workflow

  1. Inspect the relevant app and extension targets, deployment versions, existing intents, domain services, data stores, navigation, authentication, and entitlements. Identify which process can perform the action and which target must discover each declaration.
  2. Describe the user action in one sentence. Choose the system surfaces where it is useful and decide whether it can finish in the background, needs the foreground immediately, or may continue there later. Read Actions and execution before implementing or changing an intent.
  3. Model only the input and output the system needs. Use framework value types or an AppEnum for fixed choices. Read Entities and queries when app data must be selected, returned, searched, indexed, or shared across targets.
  4. Add the smallest discovery surface that makes the action useful. Read Discovery and system surfaces for App Shortcuts, Spotlight, widgets, controls, hardware entry points, and shared-package registration.
  5. Build every target that declares or consumes the changed types. Then follow Verification and exercise each requested system surface. Use verify when hands-on interaction adds confidence.

The work is complete when each requested action is discoverable from its target surface, resolves representative parameters, runs in its intended process and foreground mode, reports a useful result or failure, and preserves the app's authorization and domain rules.

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.