kit-components
/kit-components
Build or update React chat interfaces with OpenAgentPack Kit components, including message rendering, input attachments, prompts, feedback, session navigation, and tool approval UI. Use for component selection and composition; backend protocol adaptation belongs to kit-chat-provider.
- Author
- modelstudioai ↗
- Repository
- OpenAgentPack-Kit ↗
- Licence
- Apache-2.0
- Last repository change
- 13.11.2026
Assessment and security
- Files in this package
- 17
- Scripts
- 11
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
- 11 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: examples/agent-icon.tsx, examples/approval-card.tsx, examples/approvals.tsx, examples/attachment-sender.tsx, examples/chat-runtime.tsx, examples/content.tsx, examples/discovery-usage.tsx, examples/general.tsx
What it does and when to use it
Build or update React chat interfaces with OpenAgentPack Kit components, including message rendering, input attachments, prompts, feedback, session navigation, and tool approval UI. Use for component selection and composition; backend protocol adaptation belongs to kit-chat-provider.
Original author description
Build or update React chat interfaces with OpenAgentPack Kit components, including message rendering, input attachments, prompts, feedback, session navigation, and tool approval UI. Use for component selection and composition; backend protocol adaptation belongs to kit-chat-provider.
How it works
- Select the smallest composition
- Working rules
- Examples
SKILL.md preview
---
name: kit-components
description: "Build or update React chat interfaces with OpenAgentPack Kit components, including message rendering, input attachments, prompts, feedback, session navigation, and tool approval UI. Use for component selection and composition; backend protocol adaptation belongs to kit-chat-provider."
---
# Kit Components
Use the existing `@openagentpack/kit-chat-ui` public components to build the requested interface. The examples use package imports; a copy-in consumer should replace them with its local component imports.
## Select the smallest composition
- Complete conversation: `Chat` with `multiAgent={chat.multiAgent}` for main/child Agent views, or `MessageList` plus `Sender` when the input area needs custom behavior.
- Page frame: `Layout`, `AgentHeader`, `SessionList` or `SessionSidebar`, and the state helpers.
- Start a conversation: `Prompts`; choose whether selecting a prompt fills a draft or submits it.
- Compose input: `Sender`, `Sender.Header`, `Attachments`, and `Suggestion`.
- Render content: `Message`, `ReasoningBlock`, `ToolCallCard`, `ArtifactCard`, and `Markdown`.
- Feedback and review: `Actions`, `FileCard`, `CodeHighlighter`, `Mermaid`, and `ToolApprovalCard`.
- Discovery and usage: `CategoryTabs`, `PlazaCard`, `MeterBar`, and `ActivityHeatmap`.
Read [setup](references/setup.md) before integrating styles or copying component source. Read only the relevant section of [composition](references/composition.md) for behavior and ownership. The generated [API reference](references/api.md) covers every public runtime export, static subcomponent, and exported type. The generated [example reference](references/examples.md) contains the same code as the compilable examples below.
## Working rules
1. Feed components with `useChat` results and application callbacks. Core owns Stream, Request, Provider and Chat; React binds chat state to its lifetime. Components do not fetch, parse Bailian SSE, own credentials, or create sessions. `kit-chat-provider` is an optional separate Skill for backend integration; this folder contains everything needed for component composition.
2. Preserve `ChatMessage` and core-provided message/part IDs. Provider defines event-to-message conversion; Chat owns the rebuilt messages. Components render these props, not raw `SessionEvent`. Caller-owned data of the same shape is also valid. A cumulative snapshot can replace or remove parts; never key dynamic parts by their array positions.
3. Pass `submitDisabled={!chat.canSend}` while recovering a connection or waiting for tool approval. Keep the draft editable. `loading` represents generation; file uploads have separate state.
4. `Sender` does not clear input or upload files. Select, paste, and drop files through one caller-owned upload function. An uploaded file is not automatically mounted in a session.
5. Keep tool approval and destructive-operation confirmation explicit. `ToolApprovalCard` submits one reviewed decision and waits for authoritative state. The application owns plan retrieval and confirmation tokens for destructive operations.
6. Use Tailwind utilities and existing `--kit-*` tokens. Verify that Tailwind scans the component source, including when it lives behind a workspace or package link.
## Examples
- [Workspace Layout](examples/layout.tsx): desktop navigation, mobile drawer, compact header, and caller-owned dialogs.
- [Hook-driven Chat](examples/chat-runtime.tsx): multi-Agent history, a preserved default composer, and main Agent approvals.
- [Reasoning lifecycle](examples/reasoning.tsx): streaming expansion, terminal collapse, and manual disclosure.
- [Attachment composer](examples/attachment-sender.tsx): file selection, paste, drag/drop, upload callbacks, failed uploads, removal, draft preservation, and custom Sender actions.
- [General components](examples/general.tsx): Layout composition, headers, navigation, state helpers, confirmation preview, and the legacy ThreadPanel display.
- [Content and feedback](examples/content.tsx): individual message parts, complete messages, Markdown, code, diagrams, files, copy, and controlled feedback.
- [Prompts and suggestions](examples/prompts-suggestion.tsx): draft insertion and keyboard-safe slash commands.
- [Tool approvals](examples/approvals.tsx): caller-owned decisions, refresh, and stop callbacks.
- [Discovery and usage](examples/discovery-usage.tsx): controlled category selection, agent cards, quota meters, and activity summaries.
All authored examples and guidance are English. Some existing components have fixed Chinese labels and do not yet expose a locale API; do not invent one. Use existing label props where available, or localize copied source when the user requests it.
Files in this package (17)
- SKILL.md 5 KB
- agents/openai.yaml 1 KB
- examples/agent-icon.tsx 1 KB
- examples/approval-card.tsx 1 KB
- examples/approvals.tsx 1 KB
- examples/attachment-sender.tsx 6 KB
- examples/chat-runtime.tsx 2 KB
- examples/content.tsx 3 KB
- examples/discovery-usage.tsx 1 KB
- examples/general.tsx 8 KB
- examples/layout.tsx 3 KB
- examples/prompts-suggestion.tsx 3 KB
- examples/reasoning.tsx 1 KB
- references/api.md 96 KB
- references/composition.md 17 KB
- references/examples.md 30 KB
- references/setup.md 4 KB
Versions
The database has no other skills named kit-components.
Database snapshot: 13.11.2026 · package version ef55fcd090e1 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100react-component-patterns
Build modern React component architecture with composition patterns. Use when designing reusable React components, applying composition patterns, or structuring component hierarchies. - 95ai-elements
Install AI UI components from the Elements registry. Use when user needs chat interfaces, agentic UIs (tool calls, reasoning, plans), multi-agent dashboards, or AI devtools. Triggers on "AI component", "chat UI", "agent UI", "tool call component", "streaming text", "agentic",… - 95ai-elements
Maintains AI chat UI built from elements.ai-sdk.dev AI Elements components already copied into the project. Use when changing or debugging those components (conversations, messages, prompt inputs, attachments, reasoning, tool output, sources). New chat UI uses the shadcn/ui AI… - 100local-ai-elements-f31a5ceb
AI Elements component library guidance — pre-built React components for AI interfaces built on shadcn/ui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK. - 100react-patterns
Build React applications for PWA Kit — hooks, composition, SSR, Commerce SDK integration, Chakra UI components, getProps data fetching, and client-side state management. PWA Kit uses React (NOT Remix/Next.js). Use when building PWA Kit storefronts. - 95component-patterns
Implement React component patterns including composition, custom hooks, render props, HOCs, and compound components. Use when building reusable React components, implementing design patterns, or refactoring component architecture.