hashgraph-online/awesome-codex-plugins / plugins/beefiker/superloopy/skills/superloopy-frontend
superloopy-frontend
VerifiedUse only after explicit Codex `$superloopy:superloopy-frontend` or Claude Code `/superloopy:superloopy-frontend` invocation for supported screen-based application UI across browser-hosted Web, interactive deployed content-led Web, desktop, mobile/tablet, embedded/hybrid, Qt, custom-rendered, or mixed targets, such a task started with a leading `loopy` or `루피`, or an active Superloopy loop explicitly routing it here. Do not activate from UI, frontend, desktop, mobile, or framework vocabulary alone, or for TV, wearable, XR, automotive, game UI, TUI, static media/document artifacts, or non-UI work.
references/mobile.md
View on GitHub# Mobile and Tablet Application Contract
Use this after the shared UX contract for native or cross-platform phone and tablet UI. Resolve platform and API/OS version, form factors, current window size, orientation and posture, renderer/provider, package and update channel, supported inputs, permissions, restoration model, and validation devices.
## Navigation, windows, and input
Respect platform navigation and back behavior, system bars, insets and safe areas, edge-to-edge content, keyboard avoidance, multitasking, resizing, rotation, and foldable posture where supported. Do not infer layout from a device model or orientation alone; respond to the current window and content constraints.
Support touch, pointer, hardware keyboard, stylus, editable text, and the platform input method (IME) where applicable to the target and product. Preserve semantic outcomes across supported inputs without requiring identical gestures. Provide alternatives for drag, multi-touch, hover-only disclosure, and precision actions. Exercise selection, clipboard, composition, commit/cancel, and keyboard avoidance with representative scripts when text input is material.
Use platform or provider permission and picker contracts for photos, files, cameras, location, accounts, and other protected resources. Explain denial, limited access, cancellation, and recovery. A simulated picker or granted emulator permission does not prove physical-device integration.
## State, locale, and accessibility
Define process and scene restoration, background/foreground transitions, low-memory or process death behavior, migration, backup eligibility, and sensitive-value ownership. Name the durability boundary rather than promising that preferences survive every update, reinstall, transfer, or account change.
Use platform locale, per-app language, RTL, formatting, pluralization, dynamic type or text scaling, reduced motion or animation scale, and accessibility semantics. Test long and bidirectional content, larger text, focus/traversal order, labels/roles/states/actions, announcements, contrast, target size, and alternatives to gesture-only operations. Respect the system motion preference without removing the semantic outcome or essential progress and status feedback.
## Mobile evidence
Build a device and API matrix from integration risk, not market-share theater. Emulator or simulator evidence and physical-device evidence are complementary: use automation for deterministic state and broad API coverage, then physical devices for sensors, permissions, performance, input, accessibility services, rendering, and lifecycle risks that simulation cannot prove.
Keep a **minimum regression floor** that builds and launches the real target, executes the affected core journey, and covers the closest adjacent regression on a supported emulator, simulator, or device. Add install/first-run, navigation/back, interruption, permission denial/recovery, rotation/resizing, process recreation, locale/RTL, text scaling, accessibility services, offline or degraded service behavior, restart, physical-device integration, performance, and supported upgrade only when affected, claimed, release-critical, or selected by risk. Record which device, OS/API, build, account/state, input, and service conditions produced each artifact.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |