Skip to main content
skill CX Codex

widgetkit-code-review — Claude Code skill: WidgetKit code review

widgetkit-code-review is a Claude Code skill that checks WidgetKit widget code against a checklist for timelines, view composition, configurable intents, and memory, before release or after an iOS 17 migration.

Apache-2.0 121 installs ★ 89 updated 2026-09-15

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

What widgetkit-code-review does

The skill walks widget code through a WidgetKit checklist. It wants placeholder(in:) returning straight away with no async work, timeline entries at least 5 minutes apart, getSnapshot honouring context.isPreview, and widgetURL rather than Link inside systemSmall. It also flags things that should not be there at all: Button, AsyncImage, UIViewRepresentable.

Behind the checklist sit four reference files: references/timeline.md, references/views.md, references/intents.md, references/performance.md. The skill opens whichever fits the problem at hand: refresh budget, Lock Screen families, an AppIntentConfiguration migration. It also asks whether data reaches the widget through App Groups and whether an intent parameter change would break widgets people already placed.

Every reported finding carries a [FILE:LINE] marker taken from the file as it stands, and the reviewer reads the whole TimelineProvider or widget bundle first, not a diff hunk. Claims about refresh budget, the ~30MB memory guidance, App Groups or an IntentConfiguration migration need a named artifact, such as an .entitlements entry, IPHONEOS_DEPLOYMENT_TARGET or a WidgetFamily switch; otherwise the finding drops to an open question. That is the useful part: no location, no finding in the report.

What it helps with

  • check placeholder(in:) for stray async work
  • trace timeline entries and the reload policy
  • move widget views onto containerBackground(for:)
  • downsample images under the widget memory limit (~30MB)
  • size up an IntentConfiguration to AppIntentConfiguration migration

Example prompts for the agent

  • Review the widget target in Sources/WeatherWidget against the WidgetKit checklist and tag each finding with [FILE:LINE].
  • Look at the TimelineProvider in Timeline.swift: are future entries filled in, or does it lean on frequent refreshes?
  • Check the configurable widget and tell me what breaks for existing users after an intent parameter changes.

How to install widgetkit-code-review

1Skills CLI (Vercel)

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

2Manually: put the files in place

~/.claude/skills/widgetkit-code-review/SKILL.md

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

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

Questions about widgetkit-code-review

How do I install widgetkit-code-review in Claude Code?

Run npx skills add existential-birds/beagle --skill widgetkit-code-review -a claude-code. The skill lands at ~/.claude/skills/widgetkit-code-review/SKILL.md.

What does widgetkit-code-review do?

It reviews widget code against a WidgetKit checklist: timelines, view composition, configurable intents, memory. It pulls the matching reference file from references/ as it goes.

What has to be true before a finding is reported?

The finding needs a [FILE:LINE] from the current file, and the reviewer must have read the full TimelineProvider or widget bundle. Anything about refresh budget, memory or App Groups without a named artifact is downgraded to an open question.

Source text

SKILL.md · Apache-2.0
---
name: widgetkit-code-review
description: Reviews WidgetKit code for timeline management, view composition, configurable intents, and performance. Use when reviewing code with import WidgetKit, TimelineProvider, Widget protocol, or @main struct Widget.
---

# WidgetKit Code Review

## Quick Reference

| Issue Type | Reference |
|------------|-----------|
| TimelineProvider, entries, reload policies | [references/timeline.md](references/timeline.md) |
| Widget families, containerBackground, deep linking | [references/views.md](references/views.md) |
| AppIntentConfiguration, EntityQuery, @Parameter | [references/intents.md](references/intents.md) |
| Refresh budget, memory limits, caching | [references/performance.md](references/performance.md) |

## Review Checklist

- [ ] `placeholder(in:)` returns immediately without async work
- [ ] Timeline entries spaced at least 5 minutes apart
- [ ] `getSnapshot` checks `context.isPreview` for gallery previews
- [ ] `containerBackground(for:)` used for iOS 17+ compatibility
- [ ] `widgetURL` used for systemSmall (not Link)
- [ ] No Button views (use Link or widgetURL)
- [ ] No AsyncImage or UIViewRepresentable in widget views
- [ ] Images downsampled to widget display size (~30MB limit)
- [ ] App Groups configured for data sharing between app and widget
- [ ] EntityQuery implements `defaultResult()` for non-optional parameters
- [ ] New intent parameters handle nil for existing widgets after updates
- [ ] `reloadTimelines` called strategically (not on every data change)

## When to Load References

- TimelineProvider implementation or refresh issues -> timeline.md
- Widget sizes, Lock Screen, containerBackground -> views.md
- Configurable widgets, AppIntent migration -> intents.md
- Memory issues, caching, budget management -> performance.md

## Review Questions

1. Does the widget provide fallback entries for when system delays refresh?
2. Are Lock Screen families (accessoryCircular/Rectangular/Inline) handled appropriately?
3. Would migrating from IntentConfiguration break existing user widgets?
4. Is timeline populated with future entries or does it rely on frequent refreshes?
5. Is data cached via App Groups for widget access?

## 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 implementation: the `TimelineProvider` (including `placeholder`, `getSnapshot`, and `getTimeline` when relevant), the `@main` `Widget` / widget bundle, or the configurable widget’s `AppIntentConfiguration` / intent types—not only a diff hunk or snippet.
3. **Platform or system claim** (only if the finding depends on refresh budget, ~30MB memory guidance, Lock Screen accessory families, iOS 17+ `containerBackground`, App Groups data sharing, or migration from `IntentConfiguration` to `AppIntentConfiguration`) — You name one concrete artifact you inspected (for example `.entitlements` / App Group id in project, `WidgetFamily` handling in source, `IPHONEOS_DEPLOYMENT_TARGET`, or the exact reference subsection you used) **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 →
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 pydantic-ai-model-integration pydantic-ai-model-integration guides LLM provider configuration, fallback model chains, streaming, and token limits in PydanticAI. CX Codex +1 120installs review-ai-writing review-ai-writing scans documentation, docstrings, commit messages, and pull request descriptions for machine-generated writing patterns. Useful for keeping project artifacts clear and natural. CX Codex +1 119installs wish-ssh-code-review wish-ssh-code-review inspects Go SSH server code using charmbracelet/wish for middleware order, session handling, host keys, and graceful shutdown patterns. CX Codex +1 119installs urlsession-code-review urlsession-code-review reviews the networking layer of iOS and macOS apps: status codes, caching, timeouts, background sessions. Findings come with file:line. CX Codex +1 116installs

Project sponsors

Companies that keep this analytics open