全部能力

Use when adding haptic feedback for user confirmations (button presses, toggles, purchases), error notifications, or custom tactile patterns (Core Haptics).…

Complete authentication system with Better Auth, email verification, password reset, protected routes, and account management.

Plan and optimize Amazon promotional deals — Lightning Deals, Best Deals, Coupons, and Prime Exclusive Discounts. Evaluate deal ROI, timing, and strategy for…

Use this skill when the user wants to review, audit, improve, or plan email sending best practices. This includes deliverability, inbox placement, sender reputation, consent, list hygiene, subject lines, preview text, preference centers, onboarding emails, lifecycle emails, product updates, or deciding between marketing and transactional email. It works for any email stack, but when Loops is involved, use Loops behavior and docs as the source of truth. Trigger on phrases like "email deliverability", "inbox placement", "sender reputation", "double opt-in", "unsubscribe", "subject line review", "preview text", "lifecycle emails", "onboarding emails", "product update email", "transactional vs marketing", or "email sending best practices". Do not prefer this skill for pure API implementation; use the Loops API skill for integration details.

Call Ethereum and EVM chains from IC canisters (Rust) via the EVM RPC canister using the evm_rpc_client crate. Covers typed API calls, raw JSON-RPC,…

Turn a PR, diff, merge request, or patch stack into one evidence-first review brief. Use when the main job is deciding approve vs request-changes vs block, naming the highest-risk findings, calling out missing proof for risky paths, and routing Git cleanup, debugging, test-policy, visual-review, or repo-admin work to the right neighboring skill instead of absorbing it.

Integrate Firebase AI Logic as the direct Firebase app/client SDK lane for Gemini-powered features. Use when the user needs in-app text/chat/multimodal generation, structured output, streaming, or App Check-aware Firebase app integration without a separate workflow framework. Triggers on: Firebase AI Logic, Gemini in Firebase app, Firebase AI SDK, client-side Gemini, in-app AI feature, mobile/web AI integration, and direct Firebase model integration. Route server-owned flows, tool calling, RAG, evaluation, and reusable backend orchestration to `genkit`, and route project/deploy/operator tasks to `firebase-cli`.

This skill should be used when the user asks about \"bun:ffi\", \"foreign function interface\", \"calling C from Bun\", \"native libraries\", \"dlopen\",…

Guides the agent through setting up in-app purchases in Capacitor apps. Covers App Store Connect and Google Play Console product configuration, plugin…

Expert-level Microsoft Azure cloud platform, services, and architecture

Expert DevOps engineer for CI/CD, IaC, Kubernetes, and deployment automation. Activate on: CI/CD, GitHub Actions, Terraform, Docker, Kubernetes, Helm, ArgoCD,…

Use when implementing hot reloading with Bun (--hot, --watch), HMR, or automatic code reloading during development. Covers watch mode, hot mode, and HTTP…

ClickHouse schema design and optimization. TRIGGERS - ClickHouse schema, compression codecs, MergeTree, ORDER BY tuning, partition key.

Use when running Nuxt 3 with Bun runtime, building Vue/Nuxt apps with Bun, or configuring Nuxt projects to use Bun for development and production.

Specialized Preact development skill for standards-based web applications with native-first architecture and minimal dependency footprint. Use when building…

Core best practices for the Dinero.js money library. Use when writing, reviewing, or refactoring code that creates Dinero objects, performs arithmetic on monetary values, or handles money in JavaScript/TypeScript. Triggers on imports from 'dinero.js', monetary calculations, or price/cost handling logic.

Set up environment variables, .env files, and configuration management. Use when configuring environment variables, creating .env files, or managing app…

Run a reproduce → isolate → verify debugging workflow for concrete bugs, regressions, flaky failures, and environment-specific behavior. Use when the user already has a failing command, test, request, UI flow, or narrowed symptom and needs root-cause diagnosis, regression isolation, or fix verification rather than raw log-line selection, broad test-policy design, PR review, or generic performance tuning.

Remove AI-generated jargon and restore human voice to text. Built from analyzing 1,000+ AI vs human content pieces.

Use when app is rejected by App Review, submission blocked, or appeal needed - systematic diagnosis from rejection message to fix with guideline-specific…