AGENT SKILL

speak-hello-world

Create a minimal working Speak language learning example. Use when starting a new Speak integration, testing your setup, or learning basic Speak API patterns for language tutoring. Trigger with phrases like "speak hello world", "speak example", "speak quick start", "simple speak lesson".

适用职业教师与教育
License 许可
MIT
最近更新
2026-11-15
Stars
★ 2.0k
Forks
233

01 前言 Front Matter

name
speak-hello-world
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
version
1.0.0
description
Create a minimal working Speak language learning example. Use when starting a new Speak integration, testing your setup, or learning basic Speak API patterns for language tutoring. Trigger with phrases like "speak hello world", "speak example", "speak quick start", "simple speak lesson".
allowed-tools
Read, Write, Edit

03 SKILL.md 正文

Speak Hello World

Overview

Minimal working example demonstrating core Speak functionality for AI-powered language learning.

Prerequisites

  • Completed speak-install-auth setup
  • Valid API credentials configured
  • Development environment ready
  • Microphone access for speech input (optional for testing)

Instructions

Step 1: Create Entry File

Create a new file for your hello world lesson.

Step 2: Import and Initialize Client

// src/speak-hello-world.ts
import { SpeakClient, LessonSession, AITutor } from '@speak/language-sdk';

const client = new SpeakClient({
  apiKey: process.env.SPEAK_API_KEY!,
  appId: process.env.SPEAK_APP_ID!,
  language: 'es', // Learning Spanish
});

Step 3: Create Your First Lesson Session

async function startFirstLesson() {
  // Initialize AI tutor
  const tutor = new AITutor(client, {
    targetLanguage: 'es',
    nativeLanguage: 'en',
    proficiencyLevel: 'beginner',
  });

  // Start a conversation practice session
  const session = await tutor.startSession({
    topic: 'greetings',
    duration: 5, // 5 minutes
  });

  // Get AI tutor's opening prompt
  const opening = await session.getPrompt();
  console.log('AI Tutor says:', opening.text);
  console.log('Audio URL:', opening.audioUrl);

  // Simulate user response (in production, use speech recognition)
  const feedback = await session.submitResponse({
    text: 'Hola, me llamo Juan',
    audioData: null, // Optional: audio buffer for pronunciation scoring
  });

  console.log('Feedback:', feedback.message);
  console.log('Pronunciation:', feedback.pronunciationScore);
  console.log('Grammar:', feedback.grammarCorrections);

  return session;
}

startFirstLesson().catch(console.error);

Step 4: Run Your First Lesson

npx tsx src/speak-hello-world.ts

Output

  • Working code file with Speak client initialization
  • Successful lesson session creation
  • AI tutor prompt and feedback displayed
  • Console output showing:
AI Tutor says: Hola! Welcome to your Spanish lesson. Let's practice greetings. Can you say "Hello, my name is..." in Spanish?
Audio URL: https://speak.com/audio/abc123.mp3
Feedback: Great job! Your pronunciation was clear.
Pronunciation: 85
Grammar: [No corrections needed]

Error Handling

Error Cause Solution
Import Error SDK not installed Verify with npm list @speak/language-sdk
Auth Error Invalid credentials Check environment variables are set
Session Timeout Exceeded lesson duration Extend session or start new one
Rate Limit Too many requests Wait and retry with exponential backoff
Language Not Supported Invalid language code Use supported language codes

Examples

TypeScript: Pronunciation Practice

import { SpeakClient, PronunciationPractice } from '@speak/language-sdk';

const client = new SpeakClient({
  apiKey: process.env.SPEAK_API_KEY!,
  appId: process.env.SPEAK_APP_ID!,
  language: 'ko',
});

async function practicePronunciation() {
  const practice = new PronunciationPractice(client);

  // Get a phrase to practice
  const phrase = await practice.getPhrase({
    difficulty: 'easy',
    category: 'daily_conversation',
  });

  console.log('Practice this phrase:');
  console.log('Korean:', phrase.text);
  console.log('Romanization:', phrase.romanization);
  console.log('English:', phrase.translation);
  console.log('Listen:', phrase.audioUrl);
}

practicePronunciation();

Python: Basic Lesson

from speak_sdk import SpeakClient, AITutor

client = SpeakClient(
    api_key=os.environ.get('SPEAK_API_KEY'),
    app_id=os.environ.get('SPEAK_APP_ID'),
    language='ja'
)

async def first_lesson():
    tutor = AITutor(client, target_language='ja', native_language='en')
    session = await tutor.start_session(topic='self_introduction')

    prompt = await session.get_prompt()
    print(f"Tutor: {prompt.text}")

    # Submit response
    feedback = await session.submit_response(text="Hajimemashite, watashi wa John desu")
    print(f"Feedback: {feedback.message}")

asyncio.run(first_lesson())

Vocabulary Quiz Example

async function vocabularyQuiz() {
  const quiz = await client.vocabulary.createQuiz({
    language: 'es',
    topic: 'food',
    questionCount: 5,
    type: 'multiple_choice',
  });

  for (const question of quiz.questions) {
    console.log(`Q: ${question.prompt}`);
    console.log(`Options: ${question.options.join(', ')}`);

    // In production, get user input
    const answer = await quiz.submitAnswer(question.id, 'answer_a');
    console.log(`Correct: ${answer.correct}`);
  }

  console.log(`Final Score: ${quiz.score}/${quiz.total}`);
}

Resources

Next Steps

Proceed to speak-local-dev-loop for development workflow setup.

04 同仓库更多 Skills

Dicklesworthstone
Dicklesworthstone/pi_agent_rust

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

视觉设计
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

neuropixels-analysis

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

notebooklm

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Skill与智能体开发
★ 2.0k