integrate-todo-list
MUST be used whenever adding a task/todo list feature to a Flows app with Atlas chat. Do NOT manually create todo state management or tool definitions — this skill handles the full module (context, provider, tool, hooks, UI components) and all integration wiring. Prerequisite: integrate-atlas-chat must already be set up. Triggers: todo list, task list, task tracking, TodoWrite, todo panel, task panel, progress tracking, add todos, add tasks.
What this skill does
# Integrate Todo List
Add a structured task-tracking feature to this Flows app. The agent will use a `TodoWrite` tool
to create and update a task list as it works through multi-step queries, giving the user real-time
visibility into what the agent is doing and why.
**Prerequisite:** **`integrate-atlas-chat`** must already be complete — `useAtlasChat` must be wired (typically from `./atlas-agent/react`), `src/atlas-agent/` must contain the vendored atlas-agent sources, and `@sinclair/typebox`, `ajv`, `ajv-formats` must be installed per that skill.
---
## Step 1 — Read the app
Before writing anything, read:
- `package.json` — confirm `@tabler/icons-react` is installed; if not, install it with the app's package manager
- `src/App.tsx` — find where to add `TodoProvider`
- The file that calls `useAtlasChat` (likely `src/chat/useChatViewModel.ts` or `src/App.tsx`) — this is where the tool gets wired
- The chat view component that renders messages — this is where `TodoPanel` and `TodoToolResultCard` go
---
## Step 2 — Create the `src/todo/` module
Find the skill directory by running `find . -path "*/.agents/skills/integrate-todo-list/code" -type d` from the project root.
Read each file from `<skill-dir>/code/` and write it into `src/todo/` with the same filename:
| File | Purpose |
|------|---------|
| `types.ts` | `TodoItem` and `TodoList` types |
| `TodoContext.tsx` | React context + `TodoProvider` |
| `useTodoList.ts` | Hook to read/write the todo list |
| `todoWriteTool.ts` | `createTodoWriteTool` factory — `AtlasTool` with full CDF task-decomposition guidance |
| `useTodoWriteTool.ts` | Hook that memoizes the tool with current state access |
| `TodoPanel.tsx` | Card UI: progress bar + task rows |
| `TodoItemRow.tsx` | Single row with animated status icons |
| `TodoToolResultCard.tsx` | Compact summary card for tool call display |
All files use relative imports (`./types`, `./TodoContext`, etc.) — no changes needed.
---
## Step 3 — Wrap the app in `TodoProvider`
In `src/App.tsx` (or the root component), wrap the existing tree with `<TodoProvider>`:
```tsx
import { TodoProvider } from './todo/TodoContext'; // adjust path to match app conventions
function App() {
return (
<TodoProvider>
{/* existing children */}
</TodoProvider>
);
}
```
---
## Step 4 — Wire the tool into `useAtlasChat`
In the file that calls `useAtlasChat`, add the following. Adjust import paths to match the app's conventions.
```ts
import { useRef, useCallback } from 'react';
import { useTodoList } from './todo/useTodoList';
import { useTodoWriteTool } from './todo/useTodoWriteTool';
// Inside the hook/component:
const { todos, setTodos } = useTodoList();
const todoWriteTool = useTodoWriteTool();
// Keep a ref so getAppContext always reads fresh state without re-creating the callback.
const todosRef = useRef(todos);
todosRef.current = todos;
const getAppContext = useCallback(() => {
const t = todosRef.current;
if (t.length === 0) return undefined;
const lines = t.map((item, i) => `${i + 1}. [${item.status}] ${item.content}`);
return `Current todo list:\n${lines.join('\n')}`;
}, []);
// Add to useAtlasChat options:
const { messages, send, isStreaming, progress, error, reset, abort } = useAtlasChat({
client: isLoading ? null : sdk,
agentExternalId: AGENT_EXTERNAL_ID,
tools: [todoWriteTool], // add alongside any existing tools
getAppContext,
});
// In the reset handler, clear the todo list:
const handleReset = useCallback(() => {
reset();
setTodos([]);
}, [reset, setTodos]);
// Expose todos in the return value so the view can render TodoPanel:
return { ..., todos };
```
---
## Step 5 — Render `TodoPanel` in the chat view
In the component that renders the chat input area, add `<TodoPanel>` above the input field:
```tsx
import { TodoPanel } from './todo/TodoPanel'; // adjust path
// In the render:
<TodoPanel todos={todos} />
<YourChatInput ... />
```
`TodoPanel` returns `null` when the list is empty, so it's safe to always render it.
---
## Step 6 — Render `TodoToolResultCard` for tool call steps
In the component that renders per-message tool calls (typically a steps accordion or similar), branch on the tool name:
```tsx
import { TodoToolResultCard } from './todo/TodoToolResultCard'; // adjust path
{toolCalls.map((tc, i) =>
tc.name === 'TodoWrite' ? (
<TodoToolResultCard key={i} toolCall={tc} />
) : (
<YourDefaultToolCallCard key={i} toolCall={tc} />
)
)}
```
---
## Step 7 — Verify
Run the app's type-check command (typically `pnpm tsc --noEmit`) and confirm there are no errors.
If the project has tests, run them to confirm nothing regressed.
---
## Done
The agent can now use `TodoWrite` to create and track tasks. It will:
- Show a task panel as soon as it starts multi-step work
- Update task status in real-time (`pending` → `in_progress` → `completed`)
- Clear the list automatically when all tasks are done
- Inject the current task list into each prompt via `getAppContext` so it knows where it left off
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.