Claude Skills by Kaguara

Use when auditing a product, spec, pull request, or architecture for emerging-market viability, or when the user asks whether something will work on low-end devices, poor connections, or in a specific market. The entry point for this skill set — establishes the target market and device tier, dispatches to the specialist skills, and returns findings ranked by user impact. Invoke on "will this work in Kenya/India/Nigeria", "review this for low bandwidth", pre-launch checks, and architecture rev...

Use when building or reviewing signup, login, verification, KYC, biometric capture, OTP, sessions, or account recovery for emerging-market users. Covers phone-number-as-identity and SIM churn, designing around unreliable government ID authorities, status transparency, skin-tone-stratified evaluation of face capture, on-device quality gating, OTP deliverability, and shared devices. Invoke on auth flows, KYC integrations, selfie or document capture, and onboarding funnels.

Use when choosing or reviewing any paid integration or delivery channel — SMS, USSD, push, WhatsApp, identity and KYC APIs, geocoding, mobile-money rails, LLM and inference calls, CDN and egress. Covers cost per user action, channel selection, rate limiting paid sends, caching third-party lookups, AI token budgets with fallbacks, and fail-open versus fail-closed. Invoke on integration decisions, notification design, AI features, and specs with no cost line.

Use when building or reviewing any interface that will be translated, or used by people with limited literacy or limited prior exposure to software. Covers text expansion and flexible layout, ICU message formatting and plurals, locale-aware numbers and dates, right-to-left support, icon and label pairing, name and address and phone input, language selection, and error copy. Invoke on new UI, component libraries, forms, i18n setup, and copy review.

Use when building or reviewing anything that runs on entry-level hardware — 1–2GB RAM, ageing multi-core SoCs, degraded batteries, small and full storage. Covers memory ceilings, main-thread budgets, process death and state restoration, list virtualisation, background work and battery, animation cost, and server-versus-client computation. Invoke on new screens, list and feed implementations, client-side computation, background jobs, and any performance review.

Use when designing, building, or reviewing any feature that makes a network call for users on intermittent, slow, expensive, or metered connections. Covers offline queueing, idempotency, retry and backoff, sync conflict resolution, timeout sizing, data-saver handling, and graceful degradation on 2G/3G and congested LTE. Applies to mobile and web. Invoke on specs, PRs, API designs, and any code that fetches, posts, syncs, or retries.

Use when deciding what to ship over the wire, or reviewing anything that adds bytes — bundle size, APK and app-bundle size, images, fonts, third-party scripts, SDK footprint, and install-time versus on-demand delivery. Invoke on dependency additions, new screens, asset pipelines, build config, and any PR that grows the artifact. Covers Android, iOS, and web, with CI enforcement patterns.