version
Bump the monorepo version using SemVer. Use when creating releases, updating the VERSION file, or syncing version across package manifests.
update
Upgrades an existing assistant-ui project to current releases and executes the resulting migrations. Use when the user wants to update, upgrade, bump, or migrate @assistant-ui/react, @assistant-ui/react-ai-sdk, ai, or @ai-sdk/react, hits peer-dependency conflicts or post-upgrade type errors, or must apply renamed APIs after a version jump. Detects installed versus latest versions via npm ls / npm view, then routes through breaking-change references for each jump (AI SDK v4/v5 to v6; assistant-ui 0.8.x to 0.14.x): useAssistantApi to useAui, runtime.threadList to runtime.threads, ThreadPrimitive.ViewportSlack removal, the primitives components prop to children render functions, toDataStreamResponse to toUIMessageStreamResponse, maxSteps to stopWhen: stepCountIs(n). Runs npx assistant-ui@latest upgrade, pnpm/npm add @latest, and npx tsc --noEmit to verify. For a first-time install or fresh scaffold (not an upgrade) use setup instead.
assistant-ui
Overview and router for assistant-ui, the React library for building AI chat interfaces from composable primitives. Use for high-level, cross-cutting, or architecture-overview questions: choosing packages, picking a runtime, or understanding the layered model (RuntimeCore, Runtime, context hooks, primitives) and message model. Covers the `@assistant-ui/react` core plus `@assistant-ui/react-ai-sdk`, `@assistant-ui/react-langgraph`, `assistant-stream`, and `assistant-cloud`; `AssistantRuntimeProvider`; the primitives `ThreadPrimitive`, `MessagePrimitive`, `ComposerPrimitive`; the hooks `useAui`, `useAuiState`, `useAuiEvent`; and runtime selection across `useChatRuntime`, `useExternalStoreRuntime`, `useLangGraphRuntime`, `useLocalRuntime`. For a specific area route to a focused sibling instead: setup, runtime, primitives, tools, streaming, cloud, thread-list, or update. Not for hands-on tasks already owned by those siblings.
copilots
Grounding an assistant in your app with assistant-ui copilots (@assistant-ui/react). Use when steering assistant behavior with useAssistantInstructions, feeding lazy app-state context via useAssistantContext({ getContext }), exposing rendered components with makeAssistantVisible(Component, { clickable, editable }), building two-way interactable state with useAssistantInteractable and Interactables(), or registering instructions and tools imperatively through useAui().modelContext().register({ getModelContext }). Reach for this when the assistant should read the current page, click or edit UI, or read and update component state through auto-generated update_{name} tools. For LLM tools and tool-call UI use the tools skill; for runtime and thread state use the runtime skill.
cloud
Sets up assistant-ui Cloud persistence and authorization with the assistant-cloud package and AssistantCloud client. Use when adding cross-session thread/message persistence, multi-device chat history, file uploads, or auth to an assistant-ui app: passing the cloud option to useChatRuntime (with AssistantChatTransport from @assistant-ui/react-ai-sdk), configuring AssistantCloud with authToken (JWT), apiKey plus userId/workspaceId (server-side), or anonymous mode, and wiring auth providers like NextAuth, Clerk, or Firebase. Covers cloud.threads.list/get/create/update/delete, cloud.threads.messages(threadId), cloud.files.generatePresignedUploadUrl, the aui/v0 message format, custom adapters (CloudMessagePersistence, createFormattedPersistence, ThreadHistoryAdapter, RemoteThreadListAdapter), auto title generation, external_id/metadata mapping, and env vars NEXT_PUBLIC_ASSISTANT_BASE_URL and ASSISTANT_API_KEY. For the thread-list sidebar UI itself use thread-list.
markdown
Render and customize assistant message text as markdown in assistant-ui. Use when displaying model output as formatted markdown with MarkdownTextPrimitive from @assistant-ui/react-markdown wired into the MessagePrimitive.Parts text branch, configuring remarkPlugins (remark-gfm, remark-math) and rehypePlugins (rehype-katex), or memoizing components with unstable_memoizeMarkdownComponents. Covers code-block syntax highlighting via react-shiki or react-syntax-highlighter registered as SyntaxHighlighter in components/componentsByLanguage, LaTeX math rendering with KaTeX, Mermaid diagrams gated on stream completion, custom math delimiters via preprocess, and the StreamdownTextPrimitive alternative from @assistant-ui/react-streamdown with built-in Shiki/KaTeX/Mermaid and block streaming. For general chat UI composition route to primitives.
observability
Adds tracing, telemetry, and observability to an assistant-ui backend. Use when wiring an AI SDK route handler (streamText/generateText, toUIMessageStreamResponse) to a tracing backend: Langfuse via OpenTelemetry (LangfuseSpanProcessor and NodeSDK in instrumentation.ts, experimental_telemetry isEnabled, propagateAttributes with traceName/userId/sessionId, langfuseSpanProcessor.forceFlush on serverless), LangSmith via wrapAISDK(ai) from langsmith/experimental/vercel (createLangSmithProviderOptions, awaitPendingTraceBatches), or Helicone via createOpenAI baseURL https://oai.helicone.ai/v1 with the Helicone-Auth header. Also covers rendering collected spans with @assistant-ui/react-o11y headless primitives (SpanResource, SpanPrimitive Root/Indent/CollapseToggle/StatusIndicator/TypeBadge/Name/Children, SpanByIndexProvider, SpanData/SpanState) mounted via useAui/AuiProvider from @assistant-ui/store. Use for missing or empty traces, edge vs nodejs runtime telemetry, serverless flush issues, or trace waterfalls.
setup
Installs and configures assistant-ui in a project via the CLI, and picks the right runtime for a backend. Use for first-time install, scaffold, or config: `npx assistant-ui@latest create my-app` (templates default, minimal, cloud, cloud-clerk, langgraph, mcp), `npx assistant-ui@latest init [--yes] [--overwrite]` in an existing Next.js app, or `npx assistant-ui@latest add` registry components (markdown-text, thread-list). Also use to choose a runtime hook for a backend: useChatRuntime (AI SDK), useLangGraphRuntime, useAgUiRuntime, useA2ARuntime, useLocalRuntime (custom streaming API), or useExternalStoreRuntime (Redux/Zustand). Covers Vite/TanStack Start setup, shadcn styling, the playground --preset flag, and avoiding the deprecated @assistant-ui/styles and @assistant-ui/react-ui packages. For upgrading an existing install or post-upgrade breakage use update; for building UI from raw parts use primitives.
primitives
Builds and customizes assistant-ui chat UI from composable, unstyled @assistant-ui/react primitives that follow Radix-style part composition. Use when assembling or styling a custom Thread, Composer, message rendering, action bar, or branch picker from building blocks: ThreadPrimitive (.Root, .Viewport, .Messages, .Empty, .ScrollToBottom), ComposerPrimitive (.Input, .Send, .Cancel, .Attachments), MessagePrimitive (.Parts/.Content, .Error), ActionBarPrimitive (.Copy, .Edit, .Reload, .Speak, feedback, .ExportMarkdown), BranchPickerPrimitive, AttachmentPrimitive, ThreadListPrimitive, ThreadListItemPrimitive. Covers MessagePrimitive.Parts children render functions for text, image, reasoning, and tool-call parts; conditional rendering with AuiIf (deprecated .If); and gotchas like wrapping in AssistantRuntimeProvider and adding className since primitives ship unstyled. For prebuilt drop-in UI and scaffolding use setup; for multi-thread sidebar behavior use thread-list.
react-mcp
Lets end users add, authenticate, and manage MCP servers from the browser in assistant-ui apps with @assistant-ui/react-mcp. Use when building user-managed MCP server UIs: mounting McpManagerResource via useAui({ mcp }), declaring presets with defineConnector, dropping in McpConfigDialog, or composing McpManagerPrimitive (Root, Connectors, CustomServers, AddCustomTrigger), McpServerPrimitive (Root, Name, Icon, Status, ConnectButton, DisconnectButton, OAuthLink, RemoveButton, Error), and McpAddFormPrimitive (NameField, UrlField, AuthSelect, AuthFields, Submit, Cancel). Covers auth modes none/bearer/oauth, the OAuth flow with McpOAuthCallback, connection states, storage via McpLocalStorage/McpMemoryStorage/McpCustomStorage, reading state with useAuiState (s.mcp, s.mcpServer), and imperative addCustomServer/connect/callTool. Distinct from developer-defined backend @ai-sdk/mcp tools in the tools skill. Reach for this when connected-server tools are missing, OAuth never completes, or servers do not persist.
streaming
Streaming backends and wire protocols for assistant-ui via the assistant-stream package. Use when building a custom (non-AI-SDK) streaming endpoint with createAssistantStreamResponse or createAssistantStreamController, emitting parts through appendText/appendReasoning/appendSource/appendFile/addToolCallPart and setResponse; choosing between the AI SDK Data Stream format (toUIMessageStreamResponse) and the native Assistant Transport format; encoding or decoding streams with DataStreamEncoder/DataStreamDecoder, AssistantTransportEncoder/AssistantTransportDecoder, PlainTextEncoder, or UIMessageStreamDecoder; or wiring streamed chunks into useLocalRuntime or useChatRuntime. Use specifically for debugging stream wire issues: text-delta, part-start, result events, text/event-stream content-type, SSE format, tool calls not rendering, or partial text not showing. For general non-stream debugging route to the relevant focused skill, not the parent overview.
thread-list
Implements multi-thread (conversation history) management in assistant-ui apps: rendering the prebuilt `ThreadList` next to `Thread`, or building a custom sidebar with `ThreadListPrimitive` and `ThreadListItemPrimitive` (Root, New, Items, Trigger, Title, Archive, Unarchive, Delete). Covers thread CRUD through the `useAui()`/`useAuiState()` API: `switchToThread`, `switchToNewThread`, and per item `rename`, `archive`, `unarchive`, `delete`, `generateTitle`, `initialize`, plus reading `s.threads.threadIds`/`archivedThreadIds`/`mainThreadId`. Includes cloud-backed persistence via `useChatRuntime` + `AssistantCloud` and a local `useRemoteThreadListRuntime` + `InMemoryThreadListAdapter` path. Use when a user wants a thread list/sidebar, switching, searching, sorting, drag-and-drop, or renaming/archiving/deleting conversations. For single-thread state, messages, or composer use runtime; for cloud auth/persistence setup use cloud.
tools
Registers LLM tools and renders custom tool-call UI in assistant-ui (@assistant-ui/react). Use when adding frontend-only tools with makeAssistantTool / useAssistantTool (browser actions like clipboard, navigation, localStorage, async-generator streaming, AbortSignal), rendering backend AI SDK tool() calls with makeAssistantToolUI / useAssistantToolUI (status.type running/complete/incomplete/requires-action, args, result, artifact via ToolCallMessagePartProps), building generative UI from tool results, or implementing human-in-the-loop and approval flows (addResult, resume with context.human(), respondToApproval for server-side needsApproval gates). Covers registering tool components inside AssistantRuntimeProvider and the case-sensitive toolName matching that connects a tool to its UI. Reach for this when tool UI is not rendering, a tool is not being called, or a result is not showing.
runtime
Guide to the assistant-ui runtime system, single-thread state, and the imperative runtime API in @assistant-ui/react. Use when creating a runtime (useLocalRuntime with a ChatModelAdapter, useExternalStoreRuntime for Redux/Zustand, useRemoteThreadListRuntime), wiring AssistantRuntimeProvider, or reading/mutating thread, message, and composer state and events. Covers the unified hooks useAui, useAuiState, useAuiEvent (composer.send, thread.runStart, thread.runEnd), legacy hooks (useAssistantRuntime, useThreadRuntime, useMessageRuntime, useComposerRuntime, useThread, useThreadMessages), the AssistantRuntime/ThreadRuntime/MessageRuntime/ComposerRuntime hierarchy, thread operations (append, cancelRun, message().edit/reload), capabilities, and types (ThreadMessage, MessagePart, MessageStatus, ChatModelRunResult). Use for provider \"Cannot read property of undefined\" errors or state not updating. For multi-thread list UI and switching between conversations use thread-list instead.
intent-assess
Assess if IDD fits your project and learn about Intent-Driven Development. Use /intent-assess to evaluate project suitability or /intent-assess --learn for IDD education.
intent-init
Initialize IDD structure in a project. Checks existing state, creates directory structure, and generates templates. Use /intent-init to set up Intent-driven development in current project.
intent-build-now
Start implementation from Intent. Validates Intent completeness, then either delegates to TaskSwarm (if available) or executes TDD phases directly. Use when you have an Intent ready and want to start building.
intent-changes
Manage structured change proposals for design documents with PR-like review experience. Use /intent-changes start <file> to begin, /intent-changes propose to suggest changes, /intent-changes accept/reject to decide, /intent-changes finalize to apply.
intent-check
Run Intent validation and sync checks. Triggers intent-validate and intent-sync agents. Use /intent-check for full check, or /intent-check --validate/--sync for specific checks.
intent-sync
After implementation is complete and tests pass, sync confirmed details back to Intent. Captures finalized interfaces, data structures, naming conventions, and architecture decisions. Use after development is done and user confirms the implementation.
intent-story
Share your IDD adoption story. Through structured interviewing, create blog posts about Intent-Driven Development experiences, lessons learned, and best practices. Supports multiple languages and formats.
intent-review
Interactive Intent approval. Review sections and mark status (locked/reviewed/draft). Use /intent-review <path> to review a specific file, or /intent-review to review Intent in current directory.
intent-report
Generate human-readable report from Intent files. Converts technical Intent specs into readable documents for stakeholders, team members, or documentation. Supports multiple output formats.
intent-plan
Transform approved Intent into executable phased plan with strict TDD. Each step requires tests first (happy/bad/edge/security cases), then implementation. Use after /intent-review when ready to start development.
intent-normalize
Scan and normalize existing intent/planning files to IDD standard. Auto-fixes mechanical issues (frontmatter, directory structure), tags content issues for pickup. Use /intent-normalize to scan current project, or /intent-normalize <path> for specific directory.
intent-interview
Transform vague ideas into implementation-ready specifications through structured interviewing. Use when user describes a new feature/product idea, has a problem to solve, or needs to document requirements. Two-phase process: Phase A produces decisions.md, Phase B composes INTENT.md under budget constraints.
intent-critique
Critical review of Intent design quality. Checks for over-engineering, YAGNI violations, premature abstraction, and simplification opportunities. Uses interactive discussion to refine design decisions.
Nano Banana Video Generation
Generate videos using Google Veo models via the nano-banana CLI. Use this skill when the user asks to create, generate, animate, or produce videos with AI. Supports text-to-video, image-to-video animation, dialogue with lip-sync, and scene extensions. Trigger on requests like "create a video", "animate this image", "make a video clip", "generate footage", "produce a short film", "add motion to this".
Nano Banana Image Generation
Generate and edit images using Google Gemini image models. Use this skill when the user asks to create, generate, make, or edit images with AI. Supports text-to-image, image editing, style transfer, and multi-image composition. Trigger on requests like "create an image", "generate a picture", "make me a logo", "edit this photo", "add X to this image".
things3-manager
Manage tasks, projects, areas, headings, and tags in the Things 3 macOS app via a local CLI (list Inbox/Today/Upcoming/Anytime/Someday/Logbook, search, create/update/complete/cancel items, open items in Things). Use when Codex needs to manage Things 3 on macOS.
django-knowledge-patch
Django changes since training cutoff (latest: 6.0) — composite primary keys, CSP middleware, template partials, background tasks, async paginator. Load before working with Django.
dnf5-security-updates-knowledge-patch
DNF5 security and package management changes since training cutoff — advisory command (replaces updateinfo), security upgrade flags, automatic updates, offline upgrades, versionlock TOML, config-manager subcommands, needs-restarting defaults, Ansible dnf5 module, replay command. This skill should be used when writing DNF5 commands, Ansible dnf5 playbooks, or configuring dnf5-automatic.
geodesy-wgs84-knowledge-patch
Geodesy & WGS84 reference (latest: 1.0.0) — ECEF↔geodetic/ENU/NED conversions, PROJ pipelines, Helmert transforms, pyproj patterns. Load before working with coordinate transformations.
gcp-knowledge-patch
GCP changes since training cutoff — Gen AI SDK replaces Vertex AI SDK, Gemini 2.5/3.x models, Cloud Run worker pools, Artifact Registry migration, ADK. Load before working with GCP.
dioxus-knowledge-patch
Dioxus changes since training cutoff (latest: 0.7.4) — Signals replacing use_state, RSX macro overhaul, server functions, asset!() system, dx CLI, Element-as-Result. Load before working with Dioxus.
gleam-knowledge-patch
Gleam changes since training cutoff (latest: 1.15) — echo debugging, assert testing, bit array improvements, JavaScript FFI API, dev directory, record update enhancements. Load before working with Gleam.
gnss-navigation-knowledge-patch
GNSS navigation since training cutoff (latest: latest) — RTK/RTCM 3.x, SPARTN v2.0.3 PPP, Galileo HAS/OSNMA, u-blox F9P UBX protocol, IGS products, Android GnssMeasurement API. Load before working with GNSS.
biome-knowledge-patch
Biome v2.0-2.4 changes since training cutoff — linter domains, includes replacing ignore/include, assists, GritQL plugins, type-aware linting, Vue/Svelte/Astro full support, embedded snippets. Load before writing Biome config or rules.
bun-knowledge-patch
Bun changes since training cutoff (latest: 1.3.10) \u2014 S3 client, built-in SQL/Redis, route-based HTTP server, CSS bundler, V8 compatibility. Load before working with Bun.
caddy-knowledge-patch
Caddy changes since training cutoff (latest: 2.11.2) — ECH, wildcard certs by default, file placeholders, log sampling, request_body set, SIGUSR1 reload, post-quantum TLS. Load before working with Caddy.
centos-stream-knowledge-patch
CentOS Stream changes since training cutoff (latest: 10) — x86_64_v3 minimum, Wayland-only (Xorg removed), Valkey replaces Redis, modularity removed, desktop apps to Flatpak. Load before working with CentOS Stream.
better-auth-knowledge-patch
Better Auth changes since training cutoff (latest: 1.5) — OAuth 2.1 provider, Agent Auth protocol, cookie cache strategies, organization hooks, MCP integration, Stripe billing, i18n, SSO/SAML SLO, Electron/Expo/Convex support. Load before working with Better Auth.
axum-knowledge-patch
Axum changes since training cutoff (latest: 0.8.5) — {param} path syntax, no async_trait, OptionalFromRequestParts, Utf8Bytes WS, HTTP/2 WebSockets, NoContent. Load before working with Axum.
aws-sdk-knowledge-patch
AWS SDK changes since training cutoff — S3 default checksums, S3 Vectors, Lambda Durable Functions, Bedrock AgentCore, CDK Mixins, SigV4a, SDK lifecycle. Load before working with AWS SDKs.
authjs-knowledge-patch
Auth.js v5 changes since training cutoff — Next.js 16 proxy.ts migration, idToken behavioral change, WebAuthn/Passkeys provider setup. Load before working with Auth.js v5.
astro-knowledge-patch
Astro changes since training cutoff (latest: 6.0) — Fonts API, live collections, CSP, route caching, ClientRouter, Zod 4/Vite 7/Shiki 4. Load before working with Astro.
arch-knowledge-patch
Arch Linux changes since training cutoff (latest: 2025.12) — pacman 7.0 alpm user, Valkey replacing Redis, Plasma 6.4 Wayland-only, NVIDIA 590 open modules, Dovecot 2.4, linux-firmware split. Load before working with Arch Linux.
chrony-knowledge-patch
Chrony NTP changes since training cutoff (latest: 4.8) — RTC refclock, PHC by interface name, opencommands, local waitsynced/activate, NTS AEAD, maxunreach failover. Load before working with chrony configuration.
clerk-knowledge-patch
Clerk changes since training cutoff (latest: 1.0.0) — Core 3 SDK, <Show> component, Clerk Elements, billing APIs, machine auth, Go/Python SDKs. Load before working with Clerk.
debian-knowledge-patch
Debian changes since training cutoff (latest: 13) — systemd run0, apt deb822 format, /tmp tmpfs default, wtmpdb/lastlog2, OpenSSH DSA removal, curl HTTP/3. Load before working with Debian.
Page 1038 of 1680 · 83970 results
