Skip to main content
skill CX Codex

app-intents-code-review — Claude Code skill: what it does, install

app-intents-code-review reviews Swift App Intents code for intent structure, shortcuts phrases, entity queries, and iOS deployment quirks.

Apache-2.0 124 installs ★ 89 updated 2026-09-15

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add existential-birds/beagle --skill app-intents-code-review -a claude-code
Open on GitHub

What app-intents-code-review does

This skill triggers during reviews of Swift files containing import AppIntents, @AppIntent, AppEntity, or AppShortcutsProvider. It audits the execution of perform() to ensure long tasks finish within the 30-second system timeout and UI interactions run under @MainActor. It also flags SwiftData models passed directly instead of using their persistentModelID.

Platform-specific pitfalls receive heavy focus: using @IntentParameterDependency crashes targets running iOS 16, and defining App Intents inside a Swift Package fails prior to iOS 17. The checklist also validates that shortcut phrases include .applicationName and live inside AppShortcuts.strings rather than standard localization catalogs.

Every finding must pass four hard validation gates before reporting: valid [FILE:LINE] references, a full read of the enclosing type, and project-level proof such as IPHONEOS_DEPLOYMENT_TARGET. If target membership or deployment settings cannot verify the issue, the finding drops to an open question.

What it helps with

  • catch long tasks exceeding the 30-second timeout inside perform()
  • flag iOS 16 crashes triggered by @IntentParameterDependency
  • ensure shortcut phrases reside in AppShortcuts.strings with application names
  • verify SwiftData instances pass through persistentModelID rather than raw models

Example prompts for the agent

  • Review my App Intents implementation in OrderIntent.swift against the checklist
  • Check our EntityQuery and AppEntity types for missing Siri voice input handlers
  • Inspect AppShortcutsProvider phrases and check if iOS 16 deployment breaks anything

How to install app-intents-code-review

1Skills CLI (Vercel)

npx skills add existential-birds/beagle --skill app-intents-code-review -a claude-code

2Manually: put the files in place

~/.claude/skills/app-intents-code-review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/app-intents-code-review/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about app-intents-code-review

How to install app-intents-code-review in Claude Code?

Run npx skills add existential-birds/beagle --skill app-intents-code-review -a claude-code in your terminal.

What does app-intents-code-review examine?

It reviews App Intents, @Parameter attributes, EntityQuery implementations, and Siri shortcuts for runtime errors and concurrency issues.

Why does the skill verify deployment targets?

Features like @IntentParameterDependency crash on iOS 16, while placing intents inside Swift Packages requires iOS 17.

Source text

SKILL.md · Apache-2.0
---
name: app-intents-code-review
description: Reviews App Intents code for intent structure, entities, shortcuts, and parameters. Use when reviewing code with import AppIntents, @AppIntent, AppEntity, AppShortcutsProvider, or @Parameter.
---

# App Intents Code Review

## Quick Reference

| Issue Type | Reference |
|------------|-----------|
| AppIntent protocol, perform(), return types | [references/intent-structure.md](references/intent-structure.md) |
| AppEntity, EntityQuery, identifiers | [references/entities.md](references/entities.md) |
| AppShortcutsProvider, phrases, discovery | [references/shortcuts.md](references/shortcuts.md) |
| @Parameter, validation, dynamic options | [references/parameters.md](references/parameters.md) |

## Review Checklist

- [ ] `perform()` marked with `@MainActor` if accessing UI/main thread resources
- [ ] `perform()` completes within 30-second timeout (no heavy downloads/processing)
- [ ] Custom errors conform to `CustomLocalizedStringResourceConvertible`
- [ ] `EntityQuery.entities(for:)` handles missing identifiers gracefully
- [ ] `EntityStringQuery` used if Siri voice input needed (not plain `EntityQuery`)
- [ ] `suggestedEntities()` returns reasonable defaults for disambiguation
- [ ] `AppShortcut` phrases include `.applicationName` parameter
- [ ] Non-optional `@Parameter` has sensible defaults or uses `requestValue()`
- [ ] `@IntentParameterDependency` not used on iOS 16 targets (crashes)
- [ ] Phrases localized in `AppShortcuts.strings`, not `Localizable.strings`
- [ ] App Intents defined in app bundle, not Swift Package (pre-iOS 17)
- [ ] `isDiscoverable = false` for internal/widget-only intents

## When to Load References

- AppIntent protocol implementation -> intent-structure.md
- Entity queries, identifiers, Spotlight -> entities.md
- App Shortcuts, phrases, discovery -> shortcuts.md
- Parameter validation, dynamic options -> parameters.md

## Review Questions

1. Does `perform()` handle timeout limits for long-running operations?
2. Are entity queries self-contained (no `@Dependency` injection in Siri context)?
3. Do phrases read naturally and include the app name?
4. Are SwiftData models passed by `persistentModelID`, not directly?
5. Would migrating from SiriKit break existing user shortcuts?

## Hard gates (before reporting)

Complete **in order** for each finding you intend to report. Do not advance until the pass condition is satisfied.

1. **Location artifact** — The finding includes `[FILE:LINE]` (or a line range) copied from the current file contents; the path resolves in this repo.
2. **Scope read** — You read the full surrounding type: the `AppIntent` / `AppEntity` / `EntityQuery` / `AppShortcutsProvider` (or equivalent) that contains the flagged code, not only a diff hunk or snippet.
3. **Platform or integration claim** (only if the finding depends on minimum iOS, Swift Package vs app target, `@IntentParameterDependency` availability, SiriKit migration, or `isDiscoverable` / extension placement) — You name one concrete artifact you inspected (for example `IPHONEOS_DEPLOYMENT_TARGET` or target membership in the Xcode project, `Package.swift` `platforms`, entitlements, or where the intent file lives) **or** you drop or downgrade the finding to an open question.
4. **Protocol** — Pre-report steps in [review-verification-protocol](../review-verification-protocol/SKILL.md) are satisfied for this item (no finding if they are not).

Use the issue format `[FILE:LINE] ISSUE_TITLE` for each reported finding. Hard gate 4 is the full pre-report checklist for this skill’s review type.

© existential-birds · Apache-2.0 · existential-birds/beagle

Similar skills

All skills for Code review and refactoring →

From the same set68

The whole set →
cloudkit-code-review cloudkit-code-review audits CloudKit code for custom zones, batching, error backoff, and asset size limits. CX Codex +1 127installs prometheus-go-code-review The prometheus-go-code-review skill reviews Prometheus instrumentation in Go, covering metric types, labels, naming, and registration. Use it when checking prometheus/client_golang code. CX Codex +1 126installs review-skill-improver review-skill-improver reviews code-review feedback logs, spots recurring rejection patterns, and proposes changes to review skills. Use it after feedback has accumulated and you want to refine review rules. CX Codex +1 125installs elixir-code-review elixir-code-review reviews Elixir files for OTP conventions, security caveats, and idiomatic style across .ex and .exs code. CX Codex +1 124installs review-feedback-schema review-feedback-schema — a skill for recording code review outcomes in CSV and checking the evidence behind each verdict. Use it when review decisions need a history. CX Codex +1 124installs combine-code-review combine-code-review is a Claude Code skill that checks Combine code for subscription, operator, memory, and error-handling issues during Swift code review. CX Codex +1 123installs receive-feedback receive-feedback takes review comments from another model, a human or a CI tool and checks each one against the real code before anything is edited. CX Codex +1 123installs reference-docs reference-docs is a Claude Code skill for writing API and symbol reference pages, with parameter tables, return values, errors, and runnable examples. CX Codex +1 121installs

Project sponsors

Companies that keep this analytics open