CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

app-intents

Implement App Intents for Siri, Shortcuts, Spotlight, widgets, Control Center, and Apple Intelligence on iOS. Covers AppIntent actions, AppEntity and EntityQuery models, AppShortcutsProvider phrases, IndexedEntity Spotlight indexing, WidgetConfigurationIntent, SnippetIntent, and assistant schemas. Use when exposing app actions or entities to system surfaces.

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-structured overview skill: lean body, concrete protocol-level guidance, a clear triage workflow with verification and a review checklist, and exemplary progressive disclosure with verified one-level-deep task-routed references. The remaining gaps are a non-self-contained code example, no error-recovery guidance in the workflow, and unconsolidated version annotations.

Suggestions

Make the AppEntity snippet self-contained: declare the properties it references (e.g. `var orderNumber: String`) so it compiles as written, or show a minimal OrderQuery conformance alongside it.

Add a brief feedback loop to the Triage Workflow for when step 5 verification fails (e.g. which reference or Common Mistakes entry to check for missing surface registration).

Consolidate the scattered version references ("Swift 6.4 / iOS 26+", "iOS 26+", "iOS 27") into one place — e.g. a short version-support line or an old-patterns section — instead of repeating them across the matrix and Route by Task.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — an integration matrix table, one short code snippet, and terse checklists with no explanation of concepts Claude already knows. It is not 5 because the Contents list duplicates the section headers and time-sensitive version annotations ("Targets Swift 6.4 / iOS 26+", "iOS 26+", "iOS 27") are scattered rather than consolidated in an old-patterns/deprecated section.

4 / 5

Actionability

Concrete guidance dominates: specific protocols ("`AppIntent`", "`WidgetConfigurationIntent`", "`@Parameter`"), a real Swift snippet, and specific common mistakes and checklist items. It is not 5 because the sole snippet is not copy-paste ready — it references an undefined `orderNumber` property and omits the `EntityQuery` implementation it tells the reader to write — and no second executable example covers the common intent case.

4 / 5

Workflow Clarity

The Triage Workflow is a clear 5-step sequence with an explicit verification step ("Verify system surface: Test discovery in Shortcuts, Spotlight search, and widget configuration") plus a Review Checklist of checkpoints. It is not 5 because there is no error-recovery feedback loop (what to do when verification or a checklist item fails), leaving a minor validation gap.

4 / 5

Progressive Disclosure

The ~95-line body is a genuine overview, and all five referenced files (references/parameters-and-entity-queries.md, system-surfaces.md, assistant-focus-and-intent-behavior.md, url-and-spotlight-integration.md, ios27-annotations-and-testing.md) exist on disk, are substantial (106–473 lines), and are one level deep (they contain only external documentation URLs and internal anchors, no further skill-file references). The "Route by Task" section clearly signals which reference to load for which task, and the References section lists all of them — matching the clear-overview anchor exactly.

5 / 5

Total

17

/

20

Passed

Description

83%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: it enumerates concrete framework capabilities across all App Intents surfaces, includes an explicit 'Use when' clause, and uses naturally-spoken system-surface names as triggers. The main improvement would be making the trigger clause more concrete with user-sayable phrases and adding a few synonym variations.

DimensionReasoningScore

Specificity

"Covers AppIntent actions, AppEntity and EntityQuery models, AppShortcutsProvider phrases, IndexedEntity Spotlight indexing, WidgetConfigurationIntent, SnippetIntent, and assistant schemas" lists multiple specific concrete capabilities spanning every App Intents surface (Siri, Shortcuts, Spotlight, widgets, Control Center, Apple Intelligence), matching the comprehensive-coverage anchor. It is not score 4 because no noticeable capability gap remains in the enumeration.

5 / 5

Completeness

Both are answered: the 'what' is explicit ("Implement App Intents for... Covers AppIntent actions, AppEntity and EntityQuery models...") and the 'when' is an explicit "Use when exposing app actions or entities to system surfaces" clause. It is not 5 because the when-clause is abstract rather than concrete user-sayable trigger phrases, and not 3 because the 'when' is explicitly present, not merely implied.

4 / 5

Trigger Term Quality

Natural user-facing terms are present — "Siri", "Shortcuts", "Spotlight", "widgets", "Control Center", "Apple Intelligence" — which are the words a user would actually say. It falls short of 5 because no synonyms or common variations (e.g. "voice commands", "Siri shortcuts", "deep links") are included.

4 / 5

Distinctiveness Conflict Risk

The description is anchored to Apple's specific AppIntents framework with named protocols and system surfaces, giving it a clear niche with distinct triggers and minimal conflict risk. Only a slight overlap with a generic iOS-development skill is conceivable, which is not enough to drop to 4.

5 / 5

Total

18

/

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

thienqo/ios-skills

Path

skills/app-intents/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.