CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

carplay

Builds eligible CarPlay navigation, audio, communication, EV charging, parking, or ordering apps with template scenes. Use for entitlements, scene delegates, interface-controller hierarchies, lists, maps, Now Playing, dashboard displays, or CarPlay Simulator verification.

Quality

94%

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

85%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.

The body is a well-structured, lean routing skill: a clear sequenced workflow with explicit verification, API-specific mistakes and invariants, a comprehensive review checklist, and clean two-file progressive disclosure. The only deductions are minor — some repeated boundary/reference mentions and no inline executable snippets, with concrete recipes living in the reference file.

Suggestions

State the WidgetKit/ActivityKit boundary once (the scope-boundary paragraph) and remove the duplicate DON'T section and checklist item, or compress them to a single checklist line, to save tokens.

Cite references/carplay-patterns.md once (in Route by Task or References) instead of three times, keeping the annotated References entry as the canonical pointer.

Move the "Swift 6.4, iOS 26+" version pin into the core-implementation reference or a dedicated scope note so time-sensitive version numbers don't age the entrypoint.

DimensionReasoningScore

Conciseness

The body is lean and imperative with no explanations of concepts Claude already knows, but there is minor redundancy: the widget/Live Activity boundary is stated three times (scope-boundary paragraph, a DON'T section, and a checklist item), carplay-patterns.md is linked three times, and the version pin "Swift 6.4, iOS 26+" is time-sensitive information not placed in a deprecated/old-patterns section. This matches "efficient; minor instances that could be trimmed" rather than the fully lean top anchor.

4 / 5

Actionability

Guidance is concrete at the API level — exact delegate signatures ("templateApplicationScene(_:didConnect:to:)" vs. the no-window variant), "setRootTemplate(_:animated:completion:)", "CPNowPlayingTemplate.shared", "CPSessionConfiguration.limitedUserInterfaces", and exact Info.plist keys — with concrete recipes delegated to core-implementation.md. Per the scoring notes an instruction-only skill is not penalized for absent code, but nothing in the body itself is copy-paste ready, placing it at "mostly executable guidance" rather than fully executable.

4 / 5

Workflow Clarity

The Workflow section gives a clearly sequenced five-step process with an explicit verification step ("Verify reconnect, day/night appearance, multiple display sizes, driving restrictions"), and the 17-item Review Checklist provides checkpoints for the complex process — matching the anchor requiring explicit validation steps and checklists. No destructive or batch operations are involved, so the feedback-loop cap does not apply.

5 / 5

Progressive Disclosure

The entrypoint is a genuine overview with implementation detail split into two real, one-level-deep reference files, each clearly signaled with its content scope in both "Route by Task" and the annotated References section; the reference files contain no further nested references, and a Contents TOC aids navigation.

5 / 5

Total

18

/

20

Passed

Description

100%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.

This is an exemplary description: concise, third-person, concrete about what the skill builds, and explicit about when to use it. Trigger terms are natural and domain-comprehensive with minimal conflict risk against neighboring skills.

DimensionReasoningScore

Specificity

"Builds eligible CarPlay navigation, audio, communication, EV charging, parking, or ordering apps with template scenes" plus "entitlements, scene delegates, interface-controller hierarchies, lists, maps, Now Playing, dashboard displays, or CarPlay Simulator verification" lists multiple concrete capabilities with comprehensive coverage across app categories and technical surfaces, matching the top anchor; a 4 would require minor coverage gaps that are not evident.

5 / 5

Completeness

It explicitly answers both questions: the "what" ("Builds eligible CarPlay ... apps with template scenes") and the "when" ("Use for entitlements, ... or CarPlay Simulator verification") with concrete trigger phrases, and uses third person ("Builds"), so no cap or penalty applies.

5 / 5

Trigger Term Quality

Natural terms a developer would actually say — "CarPlay", "entitlements", "scene delegates", "lists", "maps", "Now Playing", "dashboard displays", "CarPlay Simulator" — comprehensively cover the domain's trigger vocabulary, matching the comprehensive-coverage anchor rather than the "a few natural terms missing" anchor at 4.

5 / 5

Distinctiveness Conflict Risk

A clear niche (category-entitled CarPlay template apps) with distinct triggers like "Now Playing", "CarPlay Simulator", and "interface-controller"; it would not collide with adjacent skills such as WidgetKit/ActivityKit or general iOS development.

5 / 5

Total

20

/

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/carplay/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.