CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

widgetkit

Implement, review, or improve WidgetKit widgets and controls. Use when building Home Screen, Lock Screen, StandBy, or CarPlay widgets with timeline providers; configurable widgets with AppIntentTimelineProvider; interactive widgets or Control Center controls with Button/Toggle wiring; WidgetKit push reloads, refresh budgets, deep links, Smart Stack relevance, Liquid Glass/accented rendering, widget extension setup, WidgetBundle, App Groups, and entitlements.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is dpearson2699/swift-ios-skills

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered body: executable Swift for every widget surface, clearly sequenced workflows with a genuine review checklist, and a real one-level-deep advanced reference. Scores hover just below top marks because the body carries some advanced detail (push reload mechanics) that duplicates the reference, a TOC that restates the headers, and creation workflows without inline validation checkpoints.

Suggestions

Trim the 18-item Contents TOC (or cut it entirely) and condense the 'iOS 26 Additions' push-reload bullet lists into a pointer to the advanced reference, which already documents push-based reloads — this removes duplication and tightens conciseness.

Add one inline validation step to the 'Create a new widget' workflow (e.g., 'Build the extension target and confirm the widget appears in the gallery before continuing') so creation, not just review, has a checkpoint.

Convert the 'Widget URL Handling' prose about Link hit areas into a one-line checklist rule in the Review Checklist to keep guidance actionable rather than discursive.

DimensionReasoningScore

Conciseness

The body is dense with WidgetKit-specific guidance (refresh budget behavior, rendering modes, push token mechanics) and assumes Claude's competence — no padding explaining what Swift or widgets are. Minor trims are possible: the 18-item Contents TOC duplicates the section headers, and prose in 'Widget URL Handling' and 'Smart Stack Relevance' restates rationale a checklist could carry. Not 5 because those small over-explanations exist; not 3 because nothing teaches concepts Claude already knows.

4 / 5

Actionability

Executable, copy-paste-ready Swift throughout: full TimelineProvider and AppIntentTimelineProvider implementations, StaticConfiguration/AppIntentConfiguration snippets, ControlWidgetButton/Toggle with StaticControlConfiguration, and exact APNs values ('apns-push-type: widgets', topic suffix '.push-type.widgets', 'aps.content-changed'). The examples cover the common cases (static, configurable, interactive, control, lock screen) end to end, matching the fully-executable anchor. Not 4 because no example is pseudocode and the concrete constants close the gaps the anchor-4 example leaves open.

5 / 5

Workflow Clarity

Four clearly sequenced workflows (create widget, integrate adjacent surfaces, add control, review code) with concrete steps, and the review workflow routes to an explicit 13-item Review Checklist that serves as a validation checklist ("Run through the Review Checklist at the end of this document"). Not 5 because the creation workflows (steps 1–3) have no validation checkpoints of their own — e.g., nothing verifies the extension built, the App Group matches, or families render — the checkpoints live only in the end-of-document checklist. No destructive/batch operations, so the workflow-clarity cap does not apply.

4 / 5

Progressive Disclosure

Structure is good and the single reference (references/widgetkit-advanced.md, verified to exist) is clearly signaled at the top, mid-body, and in References, exactly one level deep. Not 5 because the ~450-line body inlines some advanced material that the reference already carries — the iOS 26 'Push Reload Handlers' bullet list overlaps the reference's 'Push-Based Widget and Control Reloads' section — and the Contents TOC partially duplicates navigation the headers already provide, which fits anchor 4 ('most content is appropriately placed; references mostly clear; minor organization gaps') better than the cleanly-split anchor 5.

4 / 5

Total

17

/

20

Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, concrete, and rich with the natural surface names (Home Screen, Lock Screen, StandBy, CarPlay, Control Center) users actually say, plus an explicit 'Use when...' trigger clause. The only weakness is minor overlap risk with sibling App Intents/ActivityKit skills via the 'Button/Toggle wiring' and 'App Groups, and entitlements' terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with specific API names — "Implement, review, or improve WidgetKit widgets and controls", "configurable widgets with AppIntentTimelineProvider", "interactive widgets or Control Center controls with Button/Toggle wiring", "WidgetKit push reloads, refresh budgets, deep links, Smart Stack relevance, Liquid Glass/accented rendering, widget extension setup, WidgetBundle, App Groups, and entitlements" — comprehensive coverage of the domain with no vague filler. This matches the anchor for multiple specific concrete actions and is clearly above the 'several specific actions; minor gaps' level.

5 / 5

Completeness

It explicitly answers both questions: the 'what' is "Implement, review, or improve WidgetKit widgets and controls" and the 'when' is "Use when building Home Screen, Lock Screen, StandBy, or CarPlay widgets..." with concrete trigger phrases. This mirrors the anchor-5 example structure (action list followed by 'Use when...' with specific triggers), and exceeds anchor 4 because the 'when' clause enumerates specific triggering scenarios rather than being generic.

5 / 5

Trigger Term Quality

Natural user phrasings are comprehensively covered: "Home Screen, Lock Screen, StandBy, or CarPlay widgets", "Control Center controls", "deep links", "timeline providers", "widget extension setup", "App Groups". These are the exact surface names a user would mention when asking for this skill. Not below 5 because no common synonyms for the domain (widget, control, timeline, refresh) are missing.

5 / 5

Distinctiveness Conflict Risk

The WidgetKit niche is clear and triggers like "Home Screen widgets" or "WidgetBundle" are distinct, but the tail of the description — "interactive widgets... with Button/Toggle wiring", "App Groups, and entitlements" — overlaps territory owned by closely related sibling skills (app-intents, activitykit), so a query about App Intents or entitlements could pull this skill. Anchor 4 ('mostly distinct; minor overlap risk with closely related skills') fits better than 5, but 3 is too harsh since the core triggers are unambiguous WidgetKit surfaces.

4 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

dpearson2699/swift-ios-skills

Path

skills/widgetkit/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.