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

86%

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 strong, lean reference skill: it adds only non-obvious knowledge (async loading guard, exact Bonjour service names, framework boundaries, common pitfalls) with executable Swift examples and a genuinely useful mistakes/checklist pair. The main gaps are incomplete construction of trigger/write-action objects in examples and the absence of an explicit error-recovery loop.

Suggestions

Show how to construct an HMEventTrigger (e.g., with a characteristic/presence predicate) and an HMCharacteristicWriteAction before using them, so the action-set and trigger examples are fully copy-paste ready.

Add a short error-handling example for writeValue(_:) since the Review Checklist requires it but no code demonstrates catching and reacting to write failures.

Remove the 'Contents' TOC and the opening paragraph that restates the description, and drop the AccessorySetupKit item from Common Mistakes since Boundary Division already covers it.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no explanation of what HomeKit or Matter are) and keeps code examples compact, but the 'Contents' TOC duplicates the section headers, the opening paragraph restates the frontmatter description, and the 'Confusing HomeKit with AccessorySetupKit' mistake repeats the Boundary Division section. These are minor instances of over-content that could be trimmed.

4 / 5

Actionability

Concrete, executable Swift appears in every section ('try await characteristic.writeValue(isOn)', the exact Bonjour services '_matter._tcp, _matterc._udp, _matterd._udp', and the MatterAddDeviceRequest flow), and setup steps name exact keys. Minor gaps: 'addTrigger' and 'createNightScene' accept pre-constructed HMEventTrigger / HMCharacteristicWriteAction<Bool> parameters without showing how to build them, so the examples are not fully copy-paste ready.

4 / 5

Workflow Clarity

Sequences are clear (numbered entitlements setup; the explicit guard to 'await the homeManagerDidUpdateHomes(_:) delegate callback before accessing homes'), and the Review Checklist plus the 'Commissioning fails silently' mistake act as verification checkpoints. However, there is no validate-and-recover feedback loop, and no error-handling example despite the checklist requiring 'writeValue(_:) with error handling'.

4 / 5

Progressive Disclosure

The main file is a well-organized overview (TOC, clear section headers, compact examples) that points to one clearly-signaled, one-level-deep reference — 'Extended patterns (Matter extension, delegate wiring, SwiftUI): references/matter-commissioning.md' — which exists and contains exactly those advanced topics (SwiftUI integration, full delegate wiring, advanced extension handler, simulator testing). Content is appropriately split with easy navigation.

5 / 5

Total

17

/

20

Passed

Description

88%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 well-formed description with an explicit what/when pair, third-person voice, and concrete, framework-specific trigger phrases that comprehensively cover the skill's scope. The only improvement space is adding 'scenes'/'automations' as trigger synonyms and scoping out AccessorySetupKit-style device pairing.

DimensionReasoningScore

Specificity

It lists multiple concrete actions — 'Control smart-home accessories', 'commission Matter devices', 'creating action sets or triggers', 'reading accessory characteristics', 'onboarding Matter devices' — comprehensively covering every section of the skill body. Not 4: the action list maps one-to-one onto the skill's actual coverage with no meaningful gaps.

5 / 5

Completeness

Explicitly answers both questions: the 'what' ('Control smart-home accessories and commission Matter devices using HomeKit and MatterSupport') and an explicit 'Use when...' clause enumerating concrete trigger situations. Matches the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Good natural-term coverage ('homes/rooms/accessories', 'action sets', 'triggers', 'Matter devices', 'smart-home ecosystem app'), but common user phrasings like 'scenes' and 'automations' are missing even though the body covers scenes as action sets. Not 5: a few natural synonyms users would say are absent; not 3: coverage goes well beyond a single keyword.

4 / 5

Distinctiveness Conflict Risk

Clear niche — HomeKit/MatterSupport smart-home accessory control and Matter commissioning — with framework names that rarely collide. Minor overlap risk: a user asking about pairing nearby Bluetooth/Wi-Fi peripherals (AccessorySetupKit territory, per the body's own boundary division) could trigger this skill since the description does not scope that out. Not 5: that small boundary ambiguity exists; not 3: the ecosystem/commissioning triggers are clearly distinct from generic device-pairing skills.

4 / 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/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.