CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

homekit

Control smart-home accessories and commission Matter devices using HomeKit and MatterSupport. Use when managing homes/rooms/accessories, creating action sets or triggers, reading accessory characteristics, onboarding Matter devices, or building a third-party smart-home ecosystem app.

Quality

88%

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

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, largely executable skill body: compact Swift recipes for every common operation, explicit setup and trigger sequences, a Common Mistakes table and Review Checklist, and clean one-level-deep disclosure into a real reference file. The main deductions are minor: a few undefined placeholder variables, one stubbed workflow step, and light padding from the TOC and obvious comments.

Suggestions

Replace undefined placeholders (e.g., 'livingRoomLight.powerCharacteristic', 'motionSensorCharacteristic') with a line showing how to obtain the characteristic from a service, so examples are copy-paste ready.

In the event-trigger example, replace the '// Add action sets as above' stub with the actual addActionSet and enable calls (or an explicit link to the timer-trigger sequence) so the workflow is complete inline.

Trim low-value tokens: drop or shorten the Contents TOC and remove comments that restate adjacent prose (e.g., '// Safe to access manager.homes now').

DimensionReasoningScore

Conciseness

The body is efficient and API-specific (delegate timing, entitlements, framework boundary, characteristic metadata) with no explanation of concepts Claude already knows. Minor over-padding keeps it at 4 rather than 5: the Contents TOC adds length, and a few comments like '// Safe to access manager.homes now' restate the obvious.

4 / 5

Actionability

Nearly all guidance is complete, executable Swift with error handling in every completion handler (setup, listing, room assignment, characteristic read/write/observe, action sets, timer and event triggers, Matter commissioning and filtering). Minor gaps hold it below 5: placeholders like 'livingRoomLight.powerCharacteristic' and 'motionSensorCharacteristic' are never defined, and the event-trigger example ends with the stub '// Add action sets as above'.

4 / 5

Workflow Clarity

Sequences are explicit and well ordered (numbered setup steps; addTrigger -> addActionSet -> enable nesting; isSupported checked before perform()), with error handling throughout and a Review Checklist plus Common Mistakes table serving as checkpoints and recovery guidance. It falls short of 5 because some flows are stubbed ('Add action sets as above') and validation lives in a checklist rather than inline in the workflows themselves; there are no batch/destructive operations that would cap it at 3.

4 / 5

Progressive Disclosure

Clear overview with TOC, sections, and a Framework Boundary table; one reference file (references/matter-commissioning.md) that exists in the bundle, is one level deep, and is signaled both at the point of need ('Load the complete [Advanced Matter Extension Handler](references/matter-commissioning.md#advanced-matter-extension-handler)') and in the References section with a content summary. Advanced material (SwiftUI, full delegate wiring, extension handler, simulator testing) is appropriately split out — matching the 5 anchor.

5 / 5

Total

17

/

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: concrete third-person capability statement paired with an explicit 'Use when' clause covering all major use cases of the skill. Trigger terms are domain-accurate and natural, with only minor synonym gaps (e.g., 'pairing', 'scenes').

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Control smart-home accessories and commission Matter devices', 'managing homes/rooms/accessories, creating action sets or triggers, reading accessory characteristics, onboarding Matter devices, or building a third-party smart-home ecosystem app' — covering the domain comprehensively in third-person voice. It matches the 5 anchor ('multiple specific concrete actions; comprehensive coverage') with no meaningful coverage gap that would drop it to 4.

5 / 5

Completeness

It explicitly answers both questions: what ('Control smart-home accessories and commission Matter devices using HomeKit and MatterSupport') and when ('Use when managing homes/rooms/accessories, creating action sets or triggers, reading accessory characteristics, onboarding Matter devices, or building a third-party smart-home ecosystem app'). This mirrors the 5 anchor example structure exactly; nothing is only implied.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'smart-home accessories', 'Matter devices', 'action sets', 'triggers', 'homes/rooms/accessories', plus both framework names users would mention. A few natural terms are missing (e.g., 'pairing', 'scenes', 'IoT'), matching the 4 anchor ('good keyword coverage; a few natural terms missing') rather than the 5 anchor's synonym-level comprehensiveness, and clearly above 3.

4 / 5

Distinctiveness Conflict Risk

Clear niche — Apple smart-home development — anchored by named frameworks (HomeKit, MatterSupport) and domain-specific triggers (action sets, characteristics, Matter commissioning). Minimal overlap risk with any other skill, matching the 5 anchor.

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/homekit/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.