ai-tasks
Task extraction and management — the AI creates structured tasks from conversation, persisted to Postgres with a task list UI panel. Use this skill when the user says "add tasks", "task management", "todo list", "extract tasks", or "ai tasks".
What this skill does
# AI Tasks
Experience layer that extracts structured tasks from conversation and displays them in a task list panel with checkboxes, priority badges, and status management. Tasks are persisted to Postgres via Drizzle and linked to the authenticated user.
The AI creates, updates, and lists tasks via tool calls (`createTask`, `updateTask`, `listTasks`). The task list panel appears as a tab alongside the artifact panel (if installed) or as a standalone panel.
## Prerequisites
- Next.js app with `src/` directory and App Router
- `ai-core` skill installed (provides `getModel()`)
- `ai-chat` skill installed (provides chat UI, route pipeline, message renderer)
- `ai-tools` skill installed (provides tool calling framework)
- PostgreSQL with Drizzle ORM configured
- Auth skill installed (provides `requireAuth()` and `user` table reference)
## Installation
No additional packages required. Uses `ai`, `zod`, and `drizzle-orm` already installed by prerequisite skills.
## What Gets Created
```
src/
├── db/
│ └── schema/
│ └── task.ts # task table schema (Drizzle)
├── lib/
│ └── ai/
│ └── tools/
│ └── task.ts # createTask, updateTask, listTasks tool definitions
└── components/
└── ai/
└── task-list.tsx # Task list panel with checkboxes and priority badges
```
## What Gets Modified
```
src/
├── app/
│ ├── api/
│ │ └── ai/
│ │ └── chat/
│ │ └── route.ts # Register task tools + system prompt
│ └── (app)/
│ └── chat/
│ └── page.tsx # Add task list tab alongside artifacts panel
```
## Comment Slots
- **route.ts**: `// [ai-tasks]: add createTask, updateTask, listTasks` — spreads task tools into the tools object
- **route.ts**: `// [ai-tasks]: task instructions` — appends task management instructions to system prompt
- **chat/page.tsx**: `// [ai-tasks]: add panel tabs here` — adds task list panel alongside artifacts
## Database Migration
After applying this skill, create the `task` table:
```bash
bunx drizzle-kit push
```
## Setup Steps
### Step 1: Create `src/db/schema/task.ts`
```typescript
import { pgTable, text, timestamp, integer } from "drizzle-orm/pg-core";
import { user } from "./auth";
export const task = pgTable("task", {
id: text("id")
.primaryKey()
.$defaultFn(() => crypto.randomUUID()),
userId: text("user_id")
.notNull()
.references(() => user.id, { onDelete: "cascade" }),
sessionId: text("session_id"),
title: text("title").notNull(),
description: text("description"),
status: text("status", {
enum: ["todo", "in_progress", "done", "cancelled"],
})
.notNull()
.default("todo"),
priority: text("priority", {
enum: ["low", "medium", "high", "urgent"],
})
.notNull()
.default("medium"),
sortOrder: integer("sort_order").notNull().default(0),
createdAt: timestamp("created_at").notNull().defaultNow(),
updatedAt: timestamp("updated_at").notNull().defaultNow(),
});
export type Task = typeof task.$inferSelect;
export type NewTask = typeof task.$inferInsert;
```
### Step 2: Create `src/lib/ai/tools/task.ts`
```typescript
import { tool } from "ai";
import { z } from "zod";
import { db } from "@/db";
import { task } from "@/db/schema/task";
import { eq, and, desc } from "drizzle-orm";
type TaskResult = {
id: string;
title: string;
description: string | null;
status: string;
priority: string;
createdAt: Date;
updatedAt: Date;
};
type TaskListResult = {
tasks: TaskResult[];
total: number;
};
export function createTaskTools(userId: string, sessionId?: string) {
const createTask = tool({
description:
"Create a new task or to-do item. Use this when the user mentions something they need to do, a goal, an action item, or when they ask you to track tasks.",
inputSchema: z.object({
title: z
.string()
.describe("Short, actionable title for the task"),
description: z
.string()
.optional()
.describe(
"Detailed description with context, acceptance criteria, or notes"
),
priority: z
.enum(["low", "medium", "high", "urgent"])
.default("medium")
.describe(
"Task priority: low (nice-to-have), medium (normal), high (important), urgent (do now)"
),
}),
execute: async ({ title, description, priority }): Promise<TaskResult> => {
const maxOrder = await db
.select({ sortOrder: task.sortOrder })
.from(task)
.where(eq(task.userId, userId))
.orderBy(desc(task.sortOrder))
.limit(1);
const nextOrder =
maxOrder.length > 0 ? maxOrder[0].sortOrder + 1 : 0;
const [created] = await db
.insert(task)
.values({
userId,
sessionId,
title,
description: description ?? null,
priority,
sortOrder: nextOrder,
})
.returning();
return {
id: created.id,
title: created.title,
description: created.description,
status: created.status,
priority: created.priority,
createdAt: created.createdAt,
updatedAt: created.updatedAt,
};
},
});
const updateTask = tool({
description:
"Update an existing task's status or details. Use this when the user marks a task as done, changes priority, or modifies task details.",
inputSchema: z.object({
id: z.string().describe("The task ID to update"),
status: z
.enum(["todo", "in_progress", "done", "cancelled"])
.optional()
.describe("New status for the task"),
priority: z
.enum(["low", "medium", "high", "urgent"])
.optional()
.describe("New priority for the task"),
title: z
.string()
.optional()
.describe("Updated title"),
description: z
.string()
.optional()
.describe("Updated description"),
}),
execute: async ({
id,
status,
priority,
title,
description,
}): Promise<TaskResult> => {
const updates: Record<string, unknown> = {
updatedAt: new Date(),
};
if (status !== undefined) updates.status = status;
if (priority !== undefined) updates.priority = priority;
if (title !== undefined) updates.title = title;
if (description !== undefined) updates.description = description;
const [updated] = await db
.update(task)
.set(updates)
.where(and(eq(task.id, id), eq(task.userId, userId)))
.returning();
if (!updated) {
throw new Error(`Task ${id} not found or access denied`);
}
return {
id: updated.id,
title: updated.title,
description: updated.description,
status: updated.status,
priority: updated.priority,
createdAt: updated.createdAt,
updatedAt: updated.updatedAt,
};
},
});
const listTasks = tool({
description:
"List the user's current tasks. Use this when the user asks about their tasks, to-do list, or what they need to do.",
inputSchema: z.object({
status: z
.enum(["todo", "in_progress", "done", "cancelled", "all"])
.default("all")
.describe("Filter by status. Use 'all' to show everything."),
}),
execute: async ({ status }): Promise<TaskListResult> => {
const conditions = [eq(task.userId, userId)];
if (status !== "all") {
conditions.push(eq(task.status, status));
}
const tasks = await db
.select()
.from(task)
.where(and(...conditions))
.orderBy(task.sortOrder);
return {
tasks: tasks.map((t) => ({
id: t.id,
title: t.title,
description: t.description,
status: t.status,
priority: t.priority,
createdAt: t.createdAt,
updatedAtRelated 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.