toss

Render-prop components for Jotai atoms: Atom ([value, setValue] like useAtom), AtomValue (read-only like useAtomValue), SetAtom (write-only like useSetAtom) from @suspensive/jotai. Load when reading or writing jotai atoms declaratively in JSX, when async…

Composition seam between @suspensive/react-query-4 and @suspensive/react: replacing removed QueryErrorBoundary with ErrorBoundary + useQueryErrorResetBoundary, resetting query errors so retries actually refetch, shouldCatch with API error classes around…

SuspenseQuery, SuspenseQueries, SuspenseInfiniteQuery render-prop components for fetching in JSX without hook wrapper components. Load when placing queries at the same depth as Suspense/ErrorBoundary, running parallel queries, using select, integrating…

Mutation render-prop component and mutationOptions for TanStack Query v4. Load when adding mutations inside list rows, loops, or conditionals where useMutation cannot be called, removing per-row wrapper components, or reusing mutation configs with…

Fire prefetches during render before Suspense boundaries with usePrefetchQuery/usePrefetchInfiniteQuery hooks and PrefetchQuery/PrefetchInfiniteQuery components. Load when avoiding request waterfalls, warming the cache for useSuspenseQuery/SuspenseQuery, or…

Root skill for @suspensive/react-query-4: render-prop components for TanStack Query v4 Suspense — SuspenseQuery, SuspenseQueries, SuspenseInfiniteQuery, Mutation, PrefetchQuery, PrefetchInfiniteQuery, QueriesHydration, createGetQueryClient,…

Server rendering and hydration for TanStack Query v4 in RSC frameworks: request-scoped QueryClient with createGetQueryClient, server prefetch + dehydrate + hydrate with QueriesHydration, skipSsrOnError, timeout, per-boundary HTML streaming,…

Composition seam between @suspensive/react-query-5 and @suspensive/react: replacing removed QueryErrorBoundary with ErrorBoundary + useQueryErrorResetBoundary, resetting query errors so retries actually refetch, shouldCatch with API error classes around…

Selects and applies react-simplikit hooks, components and utils (useDebounce, useThrottle, useToggle, useBooleanState, useCounter, useList, useMap, useSet, useInterval, useTimeout, usePrevious, usePreservedCallback, useOutsideClickEffect,…

Create commits following repo conventions. Use when committing changes, creating commit messages.

Migrates a codebase off the deprecated @react-simplikit/mobile package onto the react-simplikit root entry. Use when a project still imports @react-simplikit/mobile, when an install warns that the package is deprecated, or when someone asks how to migrate off…

Create branches following repo conventions. Use when creating branches, starting new features.

PR/code review. 100% coverage, SSR safety, JSDoc validation. Use when reviewing code, checking PRs.

Complete workflow from new Hook/Component/Util development to deployment. Use when starting new feature development.

JSDoc writing rules for AI-powered documentation generation. Use when writing JSDoc, documenting functions, or adding code comments.

React library public API design principles. Use when designing hooks, components, or utility APIs.

es-toolkit usage guide covering installation, import patterns, and setup for Node.js, Bun, Deno, and browsers. Use when the user asks how to install, import, or set up es-toolkit in their project.

Guide migrating lodash code to es-toolkit. Use when the user wants to migrate from lodash, replace lodash imports, reduce bundle size by switching to es-toolkit, or understand the difference between es-toolkit and es-toolkit/compat.

Analyze code or requirements and recommend the best es-toolkit functions. Use when the user asks which es-toolkit function to use, needs help finding a utility, or wants alternatives to manual implementations.

Classify and summarize a PR for efficient review

Create a new es-toolkit release (version bump, changelog, tag)

Verify compat PR claims by running lodash vs es-toolkit/compat at runtime

Suggest and apply GitHub labels to unlabeled issues

Review recent issues with labeling, context analysis, and duplicate detection

Scaffold a new Apps in Toss mini-app by driving the official `create-ait-app` CLI non-interactively (`--inline`, always `@latest`), then verifying the `@apps-in-toss/devtools` wiring (mock SDK + panel) the CLI performs so `npm run dev` runs in a plain browser…

Build and fix mini-app screens. Run it for "화면 만들어줘", "출석 체크 화면 그려줘", "화면이 구린데 예쁘게 해줘", "디자인 좀 봐줘" — it writes and edits the project's actual screen files, it is not a review-only pass and not a chat answer about design. Works from nothing: with no screen, no…

Wire the `ait-devtools` debug MCP server (`@apps-in-toss/debugger`) into the current project's MCP config (project scope, opt-in) — `.mcp.json` on Claude Code, `.cursor/mcp.json` on Cursor — so `/ait:debug` can run on-device CDP relay attach (environment 3).…

Print the harness entry-point map right after plugin install, and check the local environment/integration state (git, Node/npm/npx, cwd shape, MCP wiring) to suggest or hand off the next concrete step — since `/plugin install` itself prints no next step.…

Put the current mini-app on a real phone through the standard path — build the `.ait` bundle, upload it with console MCP (`bundle_upload` → `bundle_upload_complete`), confirm the compile with `miniapp_get_status`, and hand over the entry link the tools…

Debug an Apps in Toss mini-app across two environments — local browser (devtools panel, `window.__ait`, browser DevTools) and on-device intoss-private candidate (real Toss WebView via `ait-devtools` MCP relay-staging QR attach). Branches by what it observes,…

Patch an existing Apps in Toss mini-app's build setup. Three facets: `/ait:inject-devtools` adds the `@apps-in-toss/devtools` unplugin for browser dev ("기존 Vite 프로젝트에 devtools 붙여줘"); `/ait:inject-debug-console` installs `@apps-in-toss/debug-console`…

Rewrite mini-app screen copy against measurable UX writing principles. Use when the user asks "문구 다듬어줘", "카피 점검해줘", or "UX 라이팅 기준으로 봐줘" — invoke it right away even with no screen or file named yet, it surveys the current project's screen copy first, so do not…

Use when 한 기능 수정 시 여러 디렉토리를 건드리거나, 같은 숫자/상수가 여러 파일에 흩어져 있거나, import 경로가 `../../..`처럼 길어질 때

Use when props가 3개 이상 컴포넌트 계층을 통과하거나, 하나의 Hook이 5개 이상 값을 반환하거나, A 수정 시 관련 없는 B가 깨질 때

Use when `getX()`나 `fetchX()`에 숨은 부수 효과가 있거나, 같은 종류의 함수들이 서로 다른 반환 타입을 가지거나, 함수 이름과 실제 동작이 다를 때

Use when 삼항 연산자가 중첩되거나, 복잡한 조건식 `a && !b || c`가 이름 없이 사용되거나, 동시에 실행되지 않는 코드가 한 컴포넌트에 섞여 있을 때

Validates apps-in-toss project configuration and structure for both web and React Native apps. Use when checking if granite.config.ts is properly configured, verifying required files exist, validating package.json has framework dependencies, ensuring project…

Search and retrieve Toss / Apps-in-Toss documentation using the ax CLI via run-ax.sh. Supports docs, TDS React Native, and TDS Web sources. Use bash to execute run-ax.sh in this skill's directory.

E2E Tests 워크플로우 실패 시 사용 — 인프라 기인 flaky 판별, rerun-failed-jobs로 실패 job만 재실행, Unity 라이선스 2연속 실패 에스컬레이션, Sentry 노이즈/자동 resolve 처리 기준.