Skip to main content
This is the heart of the tutorial. You will send six prompts to Claude Code, and by the end, you will have a fully working daily report bot. No coding required — just clear communication.
With Wispr Flow running, just start speaking. Your words appear as text in Claude Code automatically. Describe what you want naturally — Claude Code understands and writes the code for you. Speaking works especially well for long, descriptive prompts because you can talk through the requirements as if explaining to a colleague.

How to Talk to Claude Code

Think of Claude Code as a brilliant colleague who can code anything, but needs you to explain the goal clearly. The better you describe what you want, the better the result. Whether you speak or type, the approach is the same — just say what you need.
The conversation loop is always the same: Let’s start building.

Prompt 1: Describe the Whole Project

Before writing any code, give Claude Code the big picture. This helps it make better decisions at every step. Open your terminal, cd into your daily-report-bot folder, and type claude to start Claude Code. Then say or send this prompt:
Say this or copy this prompt
What happens: Claude Code creates a package.json, a main script file (e.g. index.js or src/index.js), and possibly a config file. It sets up the basic project structure without filling in the logic.
Communication skill: Setting context. Notice how the prompt starts with the big picture (“daily work report bot”), then lists specific requirements, then asks for a specific first step. This gives Claude Code enough context to make smart choices about project structure, naming, and dependencies.
Claude Code will typically create something like:
The exact structure may vary — that’s fine. Claude Code is making reasonable decisions based on your description.

Prompt 2: Build the Commit Collector

Now let’s build the first real piece — the script that reads your git commits.
Say this or copy this prompt
What happens: Claude Code writes a function that runs git log with the right format string, parses the output, and returns a clean array of commit objects.
Communication skill: Breaking work into steps. Instead of asking Claude Code to build everything at once, we’re doing one piece at a time. This makes each step easier to review, and if something goes wrong, you know exactly where.
Speaking technical prompts works well. Wispr Flow handles technical terms like “git log”, “API”, and “environment variable” accurately. If it mishears something, you can quickly correct the text before pressing Enter.

Prompt 3: Add the Smart Distribution (Commit Banking)

This is the cleverest part of the bot. If you do all your work on Monday, you don’t want Tuesday through Friday to report “nothing done.” Commit banking spreads your commits across the week.
Say this or copy this prompt
What happens: Claude Code creates the banking logic with functions to load, save, and distribute commits across weekdays.
Communication skill: Describing business logic in plain language. You didn’t write any algorithm — you described the behaviour you wanted. “Divide by remaining weekdays, round up, empty on Friday.” Claude Code translates this into working code. This is where voice really shines — just talk through the logic as if explaining it to someone.
Here’s what happens in a real week:Every day has something to report, even if you didn’t commit that day.

Prompt 4: Add the AI Summariser

Now we connect to OpenAI to turn raw commit messages into a friendly daily update.
Say this or copy this prompt
What happens: Claude Code creates a function that formats commits into a prompt, calls the OpenAI API, and returns the summary text.
You described the behaviour — take commits in, get a friendly summary out. You specified the model, tone, format, and how authentication works.
Communication skill: Specifying integrations and output format. When connecting to external services, tell Claude Code which API to use, what model, and what the output should look like. The more specific you are about the result, the less you’ll need to iterate.

Prompt 5: Add Slack Posting

Time to connect the output to Slack.
Say this or copy this prompt
What happens: Claude Code creates a small function that sends a POST request to the Slack webhook with a formatted message.
Communication skill: Building incrementally. Notice we didn’t try to build Slack posting in Prompt 1. By this point, Claude Code understands the whole project. It knows the summariser returns text, and it connects the pieces naturally.

Prompt 6: Wire It All Together and Test Locally

The last build step — connect all the pieces and add a dry-run mode for safe testing.
Say this or copy this prompt
What happens: Claude Code creates the main script that orchestrates all the pieces, with command-line flags and environment variable support.
Keep your API keys safe. Never commit .env files, API keys, or webhook URLs to git. We’ll store them as GitHub secrets in the next section.
Communication skill: Requesting integration and testing. This prompt brings everything together and asks for testing support (dry-run mode). Always ask for a way to test safely before connecting to real services.

Using Claude in Chrome to Research

Sometimes you need to look something up — Slack’s webhook format, GitHub Actions syntax, or an error message. That’s where Claude in Chrome comes in.
  1. Open the Slack API docs or any documentation page in Chrome
  2. Click the Claude in Chrome extension icon
  3. Ask it to explain what you’re reading, e.g.: “What format does Slack expect for incoming webhook messages?”
  4. Use the answer to refine your next prompt to Claude Code

Communication Tips Summary

Instead of “build a Slack bot”, say “build a function that sends a POST request to a Slack incoming webhook with a formatted message using blocks.” The more specific, the fewer iterations.
Start with the big picture. Tell Claude Code what the project is, who it’s for, and what tools you’re using. Context helps it make better decisions about architecture, naming, and dependencies.
When using Wispr Flow, don’t worry about speaking technical terms — it handles words like “API”, “webhook”, “JSON”, and “environment variable” accurately. Speaking is especially natural for describing business logic and desired behaviour.
If you don’t understand the code, ask: “Can you explain what this function does in plain language?” Understanding the code helps you spot issues and write better follow-up prompts.
Copy and paste the exact error message. Tell Claude Code what you expected to happen and what actually happened. Don’t try to diagnose the problem yourself — let the AI help.
Your first prompt rarely produces the perfect result. That’s normal. Review what Claude Code built, identify what’s not quite right, and send a follow-up prompt. Each iteration gets you closer.

Full Data Flow

Here’s how everything connects:
Your bot is built! Head to Deploy and test to set up GitHub Actions and see it run for real.