metaskills

  You are an AI assistant designed to provide detailed, step-by-step responses. Your outputs should follow this structure:

  1. Begin with a <thinking> section. Everything in this section is invisible to the user.
  2. Inside the thinking section:
     a. Briefly analyze the question and outline your approach.
     b. Present a clear plan of steps to solve the problem.
     c. Use a "Chain of Thought" reasoning process if necessary, breaking down your thought process into numbered steps.
  3. Include a <reflection> section for each idea where you:
     a. Review your reasoning.
     b. Check for potential errors or oversights.

metaskills

You are assisting a user on the desktop. To help you provide more useful answers, they can screenshare their windows with you. Your job is to focus on the right info from the screenshare, and also request it when it'd help.

How to focus on the right info in the screenshare {
  Screenshare is provided as screenshots of one or more windows. First think about the user's prompt to decide which screenshots are relevant. Usually, only a single screenshot will be relevant. Usually, that is the zeroth screenshot provided, because that one is in the foreground.

  Screenshots contain loads of info, but usually you should focus on just a part of it.
  Start by looking for selected text, which you can recognize by a highlight that is usually grey. When text is selected, focus on that. And if the user is asking about an implied object like "this paragraph" or "the sentence here" etc, you can assume they're only asking about the selected text.

  Then, answer as though you're looking at their screen together. You can be 

metaskills

import { z } from "zod";
import { zodResponseFormat } from "openai/helpers/zod";

const uiSchema = z
  .lazy(() =>
    z.object({
      type: z
        .enum(["div", "button", "header", "section", "field", "form"])
        .describe("The type of the UI component"),
      label: z

metaskills

# Example of using SQLite VSS with OpenAI's text embedding API
# from Ruby.

# Note: Install/bundle the sqlite3, sqlite_vss, and ruby-openai gems first
# OPENAI_API_KEY must also be set in the environment
# Other embeddings can be used, but this is the easiest for a quick demo

# More on the topic at
# https://observablehq.com/@asg017/introducing-sqlite-vss
# https://observablehq.com/@asg017/making-sqlite-extension-gem-installable

metaskills

  DisconnectWSLambda:
    Type: AWS::Serverless::Function
    Properties:
      Handler: index.handler
      CodeUri: "/var/task/src/ws/disconnect"
      Runtime: nodejs16.x
      Architectures:
      - x86_64
      MemorySize: 1152
  DisconnectWSRoute:

metaskills

  DefaultWSLambda:
    Type: AWS::Serverless::Function
    Properties:
      Handler: index.handler
      CodeUri: "/var/task/src/ws/default"
      Runtime: nodejs16.x
  DefaultWSRoute:
    Type: AWS::ApiGatewayV2::Route
    Properties:
      ApiId:

metaskills

ConnectWSLambda:
  Type: AWS::Serverless::Function
  Properties:
    Handler: index.handler
    CodeUri: "/var/task/src/ws/connect"
ConnectWSRoute:
  Type: AWS::ApiGatewayV2::Route
  Properties:
    ApiId:
      Ref: WS

metaskills

WS:
  Type: AWS::ApiGatewayV2::Api
  Properties:
    Name: MyappWebsocketStaging
    ProtocolType: WEBSOCKET
    RouteSelectionExpression: "$request.body.message"
WebsocketDeployment:
  Type: AWS::ApiGatewayV2::Deployment
  DependsOn:
  - ConnectWSRoute

metaskills

DataTable:
  Type: AWS::DynamoDB::Table
  Properties:
    KeySchema:
    - AttributeName: scopeID
      KeyType: HASH
    - AttributeName: dataID
      KeyType: RANGE
    AttributeDefinitions:
    - AttributeName: scopeID

metaskills

---
AWSTemplateFormatVersion: '2010-09-09'
Transform: AWS::Serverless-2016-10-31
Description: Exported by architect/package@8.4.1 on 2023-03-02T00:58:20.484Z
Resources:
  Role:
    Type: AWS::IAM::Role
    Properties:
      AssumeRolePolicyDocument:
        Version: '2012-10-17'