Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.
.claude/skills/hig-technologies/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 26 |
| gemini-3.1-pro-preview | 100% | 1 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 45% | 0% |
Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.
| Reference | Topic | Key content | |---|---|---| | siri.md | Siri | Intents, shortcuts, voice interaction, App Shortcuts | | apple-pay.md | Apple Pay | Payment buttons, checkout flow, security | | tap-to-pay-on-iphone.md | Tap to Pay | Merchant flows, contactless payment | | in-app-purchase.md | In-app purchase | Subscriptions, one-time purchases, transparency | | healthkit.md | HealthKit | Health data access, privacy, permissions | | carekit.md | CareKit | Care plans, tasks, health management | | researchkit.md | ResearchKit | Studies, informed consent, data collection | | homekit.md | HomeKit | Smart home control, device state, scenes | | augmented-reality.md | ARKit | Spatial context, surface detection, setup | | machine-learning.md | Core ML | Predictions, smart features, confidence handling | | generative-ai.md | Generative AI | Attribution, editing, responsible AI, uncertainty | | icloud.md | iCloud | CloudKit, cross-device sync, conflict resolution | | sign-in-with-apple.md | Sign in with Apple | Authentication, privacy, button styles | | id-verifier.md | ID Verifier | Identity verification, document scanning | | shareplay.md | SharePlay | Shared experiences, participant presence | | airplay.md | AirPlay | Media streaming, Now Playing, wireless display | | carplay.md | CarPlay | Driver safety, permitted app types, large targets | | game-center.md | Game Center | Achievements, leaderboards, multiplayer | | voiceover.md | VoiceOver | Screen reader, labels, traits, accessibility | | wallet.md | Wallet | Passes, tickets, loyalty cards | | nfc.md | NFC | Tag reading, quick interactions, App Clips | | maps.md | Maps | Location display, annotations, directions | | mac-catalyst.md | Mac Catalyst | iPad to Mac, menu bar, keyboard, pointer | | live-photos.md | Live Photos | Motion capture, playback, editing | | imessage-apps-and-stickers.md | iMessage apps | Messages extension, stickers, compact UI | | shazamkit.md | ShazamKit | Audio recognition, music identification | | always-on.md | Always-on display | Dimmed state, power efficiency, reduced updates | | photo-editing.md | Photo editing | System photo editor, filters, adjustments |
Built by Raintree Technology · More developer tools
This skill is applicable to execute the workflow or actions described in the overview.
User request:
> Check for .claude/apple-design-context.md before asking questions.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 43,471 | 43,335 | -0% | 1 | 1 | 0% | 6,855 | 4,927 | -28% | 0 | 0 | — |
case-02 | pass→pass | 30,759 | 21,977 | -29% | 1 | 1 | 0% | 4,623 | 4,643 | +0% | 0 | 0 | — |
case-03 | pass→pass | 73,513 | 15,658 | -79% | 1 | 1 | 0% | 3,722 | 4,263 | +15% | 0 | 0 | — |
case-04 | fail→fail | 28,843 | 19,100 | -34% | 1 | 1 | 0% | 3,820 | 4,627 | +21% | 0 | 0 | — |
case-05 | fail→pass | 23,519 | 20,370 | -13% | 1 | 1 | 0% | 2,907 | 4,288 | +48% | 0 | 0 | — |
case-06 | fail→pass | 44,517 | 23,780 | -47% | 1 | 1 | 0% | 6,696 | 4,386 | -34% | 0 | 0 | — |
case-07 | pass→pass | 33,386 | 22,491 | -33% | 1 | 1 | 0% | 4,371 | 5,196 | +19% | 0 | 0 | — |
case-08 | fail→pass | 50,025 | 23,650 | -53% | 1 | 1 | 0% | 6,304 | 5,193 | -18% | 0 | 0 | — |
case-09 | fail→fail | 42,239 | 24,768 | -41% | 1 | 1 | 0% | 5,596 | 4,934 | -12% | 0 | 0 | — |
case-10 | fail→pass | 35,724 | 37,900 | +6% | 1 | 1 | 0% | 3,706 | 5,362 | +45% | 0 | 0 | — |
case-11 | fail→fail | 33,486 | 27,627 | -17% | 1 | 1 | 0% | 4,479 | 4,744 | +6% | 0 | 0 | — |
case-12 | fail→pass | 92,594 | 25,559 | -72% | 1 | 1 | 0% | 5,445 | 5,076 | -7% | 0 | 0 | — |
case-13 | pass→pass | 36,049 | 53,471 | +48% | 1 | 1 | 0% | 5,626 | 5,599 | -0% | 0 | 0 | — |
case-14 | fail→pass | 35,953 | 30,527 | -15% | 1 | 1 | 0% | 4,700 | 4,574 | -3% | 0 | 0 | — |
case-15 | fail→fail | 50,039 | 31,130 | -38% | 1 | 1 | 0% | 6,608 | 5,450 | -18% | 0 | 0 | — |
case-16 | pass→pass | 46,567 | 23,109 | -50% | 1 | 1 | 0% | 6,775 | 5,100 | -25% | 0 | 0 | — |
case-17 | pass→pass | 31,770 | 32,085 | +1% | 1 | 1 | 0% | 4,002 | 4,553 | +14% | 0 | 0 | — |
case-18 | fail→pass | 29,530 | 26,356 | -11% | 1 | 1 | 0% | 3,995 | 4,803 | +20% | 0 | 0 | — |
case-19 | fail→pass | 44,477 | 30,294 | -32% | 1 | 1 | 0% | 6,143 | 5,270 | -14% | 0 | 0 | — |
case-20 | pass→pass | 25,696 | 30,080 | +17% | 1 | 1 | 0% | 2,770 | 5,283 | +91% | 0 | 0 | — |
case-21 | fail→fail | 50,160 | 34,659 | -31% | 1 | 1 | 0% | 8,240 | 5,891 | -29% | 0 | 0 | — |
case-22 | pass→pass | 40,894 | 32,898 | -20% | 1 | 1 | 0% | 5,717 | 5,743 | +0% | 0 | 0 | — |
case-23 | fail→fail | 32,718 | 24,806 | -24% | 1 | 1 | 0% | 4,093 | 4,504 | +10% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +39 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/28/2026 | +18% |
Other measured skills in the registry, with their headline benchmark lift.