integrate-atlas-chat
MUST be used whenever building a chat UI with Atlas agents in a Flows app. Do NOT manually write useAtlasChat integration code — this skill handles installation, component structure, and hook wiring. Triggers: useAtlasChat, atlas chat, streaming chat, agent chat, chat interface, chat component, chat UI. For a full chat app, run skills in order: (1) integrate-atlas-chat, (2) create-client-tool (per tool), (3) setup-python-tools (if Python tools needed).
What this skill does
# Integrate Atlas Agent Chat
Add a streaming Atlas Agent chat UI to this Flows app.
Agent external ID: **$ARGUMENTS**
## Dependencies
The atlas-agent library files (copied in Step 2) require these npm packages:
| Package | Version |
|---|---|
| `@sinclair/typebox` | `^0.33.0` |
| `ajv` | `^8.17.1` |
| `ajv-formats` | `^2.1.1` |
`@cognite/sdk` is assumed to already be present in Flows apps.
---
## Your job
Complete these steps in order. Read each file before modifying it.
---
## Step 1 — Understand the app
Read these files before touching anything:
- `package.json` — detect package manager (`packageManager` field or lock file) and existing deps
- `src/App.tsx` (or equivalent entry component) — understand current structure
---
## Step 2 — Copy the atlas-agent source files
The atlas-agent library lives in the `code/` directory next to this skill file. Read and copy
the following files into `src/atlas-agent/` inside the app:
- `code/types.ts`
- `code/validation.ts`
- `code/client.ts`
- `code/session.ts`
- `code/react.ts`
> The Python-related files (`python.ts`, `pyodide.ts`, `pyodide-react.ts`, `pyodide-runtime.ts`)
> are only needed if the agent uses Python tools. The `setup-python-tools` skill copies those.
---
## Step 3 — Install dependencies
Install the required peer packages (see **Dependencies** above) using the app's package manager:
- pnpm → `pnpm add @sinclair/typebox@^0.33.0 ajv@^8.17.1 ajv-formats@^2.1.1`
- npm → `npm install @sinclair/typebox@^0.33.0 ajv@^8.17.1 ajv-formats@^2.1.1`
- yarn → `yarn add @sinclair/typebox@^0.33.0 ajv@^8.17.1 ajv-formats@^2.1.1`
---
## Step 4 — Build the chat component
Replace (or create) the main `App.tsx` with a full chat UI. The component must:
1. **Import** `useAtlasChat` and `ChatMessage` from `./atlas-agent/react` (relative to the component)
2. **Get the SDK** via `useDune()` from `@cognite/dune`
3. **Pass `null` while loading** — `client: isLoading ? null : sdk`
4. **Show streaming text** in real time using `msg.isStreaming` with a blinking cursor
5. **Show tool call events** — when `progress.startsWith("Executing:")`, render it distinctly
(e.g. a ⚙ icon + monospace tool name) so tool calls are clearly visible
6. **Show tool calls** — each assistant `message.toolCalls` (after streaming completes)
should appear as expandable cards beneath the message
7. **Abort button** — show a "Stop" button while `isStreaming`, wired to `abort()`
8. **Reset button** — "New chat" button wired to `reset()`
9. **Auto-scroll** — scroll to bottom on new messages and progress updates
10. **Auto-resize textarea** — expand up to ~120px, submit on Enter, newline on Shift+Enter
### Key hook API
```ts
import { useAtlasChat } from "./atlas-agent/react";
import type { ChatMessage } from "./atlas-agent/react";
const { messages, send, isStreaming, progress, error, reset, abort } = useAtlasChat({
client: isLoading ? null : sdk, // null-safe — hook waits for a real client
agentExternalId: "...",
tools?: AtlasTool[], // optional client-side tools
});
// messages[n].role — "user" | "assistant"
// messages[n].text — full text (streams chunk-by-chunk via isStreaming)
// messages[n].isStreaming — true while this message is being written
// messages[n].toolCalls — ToolCall[] once response is complete (client + server-side, in call order)
// progress — e.g. "Agent thinking" or "Executing: get_timeseries"
// isStreaming — true for the entire duration of a response
```
### Tool call display pattern
```tsx
// During streaming — show as a distinct "tool call" bubble above the message
{isStreaming && progress?.startsWith("Executing:") && (
<div>⚙ {progress}</div>
)}
// After response — show tool calls on the assistant message
{msg.toolCalls?.map((tc, i) => (
<ToolResult key={i} name={tc.name} output={tc.output} details={tc.details} />
))}
```
---
## Step 5 — Python tools (optional)
If the agent has Python tools (type `runPythonCode` in its CDF config), run the
`setup-python-tools` skill to add Pyodide-based client-side execution:
```
/setup-python-tools $ARGUMENTS
```
That skill copies the Python-related source files from `@skills/integrate-atlas-chat/code`,
installs `pyodide`, sets up `usePyodideRuntime`, and wires the runtime into
`useAtlasChat` via `pythonRuntime`. The library fetches Python tool code from the agent
config automatically — no `PythonToolConfig` entries needed.
You don't need this if the agent only uses built-in or regular client tools.
---
## Done
Start the app and you should see a streaming chat UI connected to Atlas Agent `$ARGUMENTS`.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.