메뉴
Screenshot Drift on the iOS simulator across all five tabs + key sheets, dump the UI hierarchy for each, and report visible issues (invisible text, broken layout, dark holdovers). Run after any UI change before declaring done, and especially before publishing TestFlight.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | ui-review |
| description | Screenshot Drift on the iOS simulator across all five tabs + key sheets, dump the UI hierarchy for each, and report visible issues (invisible text, broken layout, dark holdovers). Run after any UI change before declaring done, and especially before publishing TestFlight. |
Boot/install before screenshotting:
xcrun simctl boot "iPhone 17 Pro" (idempotent — no-op if already booted)xcodebuild build -project /Users/ashishsadh/workspace/Drift/Drift.xcodeproj -scheme Drift -destination 'platform=iOS Simulator,name=iPhone 17 Pro' -quietxcrun simctl install booted <derived-data .app path>mobile_launch_app(bundleId: "com.drift.health") — or
xcrun simctl launch booted com.drift.health as a fallback.If the app is mid-launch (splash visible), wait 2s before the first screenshot.
Default sweep — every screen the user has flagged at least once:mobile_take_screenshot after launch.
Then scroll the dashboard: mobile_swipe_on_screen(direction: "up").
Take a second screenshot of the "Body" section + meal timeline area.mobile_click_on_screen_at_coordinates on the
"Weight" tab item via mobile_list_elements_on_screen to find its
identifier (tab-weight once IDs are backfilled). Screenshot.tab-food. Screenshot the meals
list. Don't enter any sub-sheets unless focus=food.tab-exercise. Screenshot the empty/templates
state + the muscle-group grid. The user has flagged this tab for
over-red palette — note any monochromatic red CTAs.tab-more. Screenshot the menu list. Open
Settings: tap the "Settings" row, screenshot the top section
(Apple Health, iCloud, Export). Back out.Then the key sheets:
goal-setup-save with no weight data to verify the alert fires.ai-floating-bubble). Screenshot the expanded panel. Confirm:
<context_rules>
mobile_list_elements_on_screen and
scan the dumped tree for surprises: elements with no label, elements
whose value is empty when it shouldn't be, duplicate tab items.tab-weight: x-axis date labels still rendering as
textTertiary on white, contrast ~2.8:1, below AA floor for small text.
→ fix: bump Theme.textTertiary or use textSecondary for axis.focus names one.
This is a regression scan, not an exploration session.
</context_rules><exit_condition> Return a markdown bullet list of findings, grouped by screen. End with a single-line verdict:
PASS — nothing to fix.FIX — 1+ findings; the implementer should address before commit/TestFlight.
Do not file issues, do not commit, do not push. Just report.
</exit_condition>TestFlight publish recipe. Invoked by the watchdog as its next-session slot when ≥3h since last publish AND is-clean-state passes (NOT by launchd cron — the watchdog already serializes one claude -p at a time, so slotting TF into that queue gives zero concurrency with senior/junior xcodebuild or main-branch commits). Skips quietly if not clean or <3h since last publish, otherwise bumps build, archives, uploads, stamps state, updates releases.json. Haiku model — recipe is deterministic.
Deep planning for Drift autopilot. Reads + drains feedback, triages P0 bugs, processes design-doc backlog, researches the next arc (Explore sub-agent + optional WebSearch), and emits ONE primary epic per cycle. Standalone sprint-tasks no longer filed — bugs auto-route to routine-fix; permanents continue via their lifecycle. Invoked headlessly by the watchdog as `claude -p "/planning"`. Harness phase 3c per Docs/refactor/harness-phase-2-workflows.md.
Reply to admin comments on report PRs that arrived since the last run. Sonnet model, ~5k tokens per cycle. Was bundled inside /planning step 3; now its own skill spawned by the watchdog when `~/drift-state/last-admin-replies-at` is older than 24h. Keeps planning focused on the next epic.
Junior task executor (Sonnet model) for Drift autopilot. Same shape as /senior but verifier-only-debate, no design-doc routing, no security-review. For sweeps of mechanical changes, invoked via /batch from planning. Watchdog spawns `claude -p "/junior" --model sonnet`.
Senior task executor for Drift autopilot. Claims one SENIOR sprint-task, reads its <done_when> block as ground truth, implements, runs verifier debate via debate-moderator, commits only on PASS. Abandons on context budget exhaustion (never WIP-commits to main). Invoked headlessly by the watchdog as `claude -p "/senior"`.
Evaluator-optimizer for Drift UI commits. Reads `<visual_criteria>` from the parent epic, captures simulator screenshots via mobile-mcp, scores each criterion against the rendered pixels, and emits `<visual_verdict decision="PASS|REJECT">`. On REJECT, files a refinement sub-task under the parent epic so the next senior session picks up the gap. Invoked post-commit by senior when the diff touches Drift/Views/**/*.swift; harness phase 2c per Docs/refactor/harness-phase-2-workflows.md.