CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dockkit

Control motorized camera docks and enable intelligent subject tracking using DockKit. Use when discovering DockKit-compatible accessories, implementing camera subject tracking for faces or bodies, controlling dock motors for pan and tilt, configuring framing behavior, setting regions of interest, or building video apps with automatic camera tracking.

Quality

92%

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

88%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 high-quality reference skill: executable Swift throughout, explicit lifecycle guards and recovery patterns, and a genuine one-level-deep bundle split. The main improvement opportunities are tightening the meta-review asides and moving more secondary sections into the existing references file.

Suggestions

Remove or reword the answer-reviewing meta-instructions ("In review answers, reject opaque optional `cameraInfo` placeholders", "When reviewing custom tracking, explicitly choose...") into neutral skill guidance, since they read as instructions for evaluating answers rather than for using DockKit.

Move secondary sections such as Battery Monitoring and the long trackingStates overlay example into references/dockkit-patterns.md to shorten the SKILL.md body, keeping the core API usage inline.

Surface the references/dockkit-patterns.md pointer earlier (e.g., a short line in the Contents or Setup section) so extended patterns are discoverable without scrolling to the References section.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious, DockKit-specific facts that earn their tokens ("Positive tilts down on iOS", "no more than twice per second; higher call rates can throw `.frameRateTooHigh`", tracking state "does not persist across app termination, reboots, or background/foreground transitions"), with no padding on concepts Claude already knows. Minor trimming is possible: meta-review asides like "In review answers, reject opaque optional `cameraInfo` placeholders" and some checklist items that restate earlier guidance keep it just below the lean-and-efficient anchor.

4 / 5

Actionability

Nearly every section carries copy-paste-ready Swift with correct API signatures: accessory discovery via `DockAccessoryManager.shared.accessoryStateChanges`, inline `DockAccessory.CameraInformation` construction, `setFramingMode` with a mode table, `setAngularVelocity`/`setOrientation`, the animation lifecycle with `Progress` polling, and guarded `trackingStates`/`batteryStates` loops. Concrete examples cover all the common cases; the only app-specific helpers (e.g., `detector.detect`) are unavoidable integration points and the skill still shows the required construction around them.

5 / 5

Workflow Clarity

The body is clearly sequenced (Setup → Discovering Accessories → System/Custom Tracking → Framing → Motor Control → Animations → Events → Battery), and multi-step processes carry explicit checkpoints: "Disable system tracking before animating", wait on `Progress` completion, then "Restore system tracking". The Common Mistakes section provides WRONG/CORRECT recovery patterns and the 17-item Review Checklist acts as a validation checklist for complex integrations, matching the top anchor including its feedback/recovery requirements.

5 / 5

Progressive Disclosure

The structure is good: a linked table of contents, a real one-level-deep bundle file clearly labeled ("Extended patterns (Vision integration, service architecture, custom animations): references/dockkit-patterns.md"), and a sensible core-vs-extended split. It falls short of the top anchor because the single reference is only surfaced at the bottom of the document, and a ~490-line body still inlines sections (e.g., the long trackingStates example, Battery Monitoring) that could be offloaded to the existing patterns file.

4 / 5

Total

18

/

20

Passed

Description

92%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 states concrete capabilities in third person, includes an explicit multi-clause "Use when" trigger, and is tightly scoped to the DockKit niche. The only gap is a few missing natural synonyms such as "gimbal" or "motorized stand" that users might use when searching for this skill.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the framework's full surface: "Control motorized camera docks", "implementing camera subject tracking for faces or bodies", "controlling dock motors for pan and tilt", "configuring framing behavior", "setting regions of interest", and "building video apps with automatic camera tracking". This matches the anchor for comprehensive concrete-action coverage, not the level below (which allows minor gaps).

5 / 5

Completeness

Both questions are answered explicitly: the "what" ("Control motorized camera docks and enable intelligent subject tracking using DockKit") and the "when" via a concrete "Use when" clause enumerating six trigger scenarios (discovering accessories, implementing tracking, controlling motors, configuring framing, setting regions of interest, building video apps).

5 / 5

Trigger Term Quality

Natural terms are well covered: "camera tracking", "subject tracking", "pan and tilt", "framing", "motorized camera docks", "video apps". A few natural synonyms users might say are missing (e.g., "gimbal", "motorized stand"), which fits the anchor for good coverage with a few natural terms missing rather than comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"DockKit" names a specific framework and the triggers ("motorized camera docks", "dock motors for pan and tilt") occupy a clear niche with minimal conflict risk against generic camera or AVFoundation skills.

5 / 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/dockkit/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.