Speak Local Dev Loop

What it does

When your agent uses it

• Setting up a development environment
• Configuring test workflows
• Building language learning features locally
• With phrases like speak dev setup

Example prompts

• “speak dev setup”
• “speak local development”
• “speak dev environment”
• “/speak-local-dev-loop”

Requirements

• Node.js
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(npm:*), Bash(pnpm:*), Grep

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Project Structure
2. 2Mock Tutor for Offline Development
3. 3Audio Test Fixtures
4. 4Development Scripts
5. 5Debug Mode

What it can do on your machine

Read from SKILL.md and the folder at commit 80f86df. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash(npm:*)
  • Bash(pnpm:*)
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • ffmpeg
  • brew
  • apt
  • npm

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • vitest.dev
  • ffmpeg.org
  • developer.mozilla.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Speak Local Dev Loop loads about 1.2k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 84 tokens; SKILL.md has 211 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~84

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:53

  .env.development        # Dev credentials

• NoteMentions a .env fileSKILL.md:54

  .env.test              # Test credentials (mock mode)

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit 80f86df, republished under its MIT licence (© jeremylongshore). 211 words, ~1,215 tokens.

name

speak-local-dev-loop

description

Configure Speak local development with mocked tutors and audio testing. Use when setting up a development environment, configuring test workflows, or building language learning features locally. Trigger with phrases like "speak dev setup", "speak local development", "speak dev environment", "develop with speak".

allowed-tools

Read, Write, Edit, Bash(npm:*), Bash(pnpm:*), Grep

compatibility

Designed for Claude Code

version

1.14.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, speak, testing, workflow

speak-app/
  src/
    speak/client.ts       # Speak API client
    speak/tutor.ts        # AI tutor conversation manager
    speak/pronunciation.ts # Pronunciation assessment
    speak/audio.ts        # Audio recording and preprocessing
  tests/
    mocks/                # Mock responses for offline dev
    fixtures/             # Sample audio files for testing
    unit/                 # Unit tests with mocked API
    integration/          # Integration tests (needs API key)
  .env.development        # Dev credentials
  .env.test              # Test credentials (mock mode)

// tests/mocks/mock-speak-client.ts
export class MockSpeakClient {
  async startConversation(config: any) {
    return {
      id: 'mock-session-123',
      firstPrompt: {
        text: 'Hola! Bienvenido. Como te llamas?',
        audioUrl: null,
      },
    };
  }

  async sendTurn(sessionId: string, input: any) {
    return {
      tutorText: 'Muy bien! Tu pronunciacion es buena.',
      pronunciationScore: 85,
      corrections: [],
      vocabularyNotes: ['llamo = I call myself'],
    };
  }

  async assessPronunciation(config: any) {
    return {
      score: 82,
      words: [
        { text: 'Hola', score: 95, phonemes: [] },
        { text: 'como', score: 78, phonemes: [
          { symbol: 'o', score: 65, suggestion: 'Round lips more' }
        ]},
      ],
    };
  }
}

# Generate test audio files using text-to-speech
# macOS:
say -v "Paulina" "Hola, como estas" -o tests/fixtures/hola-es.wav
# Linux:
espeak -v es "Hola, como estas" -w tests/fixtures/hola-es.wav

# Convert to required format
ffmpeg -i tests/fixtures/hola-es.wav -ar 16000 -ac 1 tests/fixtures/hola-es-16k.wav

{
  "scripts": {
    "dev": "tsx watch src/index.ts",
    "dev:mock": "SPEAK_MOCK_MODE=true tsx watch src/index.ts",
    "test": "vitest run",
    "test:watch": "vitest",
    "lesson:test": "tsx src/test-lesson.ts"
  }
}

// Enable detailed scoring output
const DEBUG = process.env.SPEAK_DEBUG === 'true';

function logAssessment(result: PronunciationResult) {
  if (!DEBUG) return;
  console.log('=== Pronunciation Debug ===');
  for (const word of result.words) {
    const flag = word.score < 70 ? 'WEAK' : 'OK';
    console.log(`  [${flag}] "${word.text}": ${word.score}/100`);
    for (const p of word.phonemes || []) {
      if (p.score < 70) {
        console.log(`    phoneme "${p.symbol}": ${p.score} - ${p.suggestion}`);
      }
    }
  }
}

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/.curated/speak-local-dev-loop of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/implementation-guide.md

Open the folder on GitHubat commit 80f86df