Copied to clipboard!
Module 5 Foundations beginner 32 min

The first ten prompts you'll reuse

What you'll be able to do

  • Keep ten workhorse prompts built on the four cores of summarize, sharpen, draft-reply, and audit-doc
  • Adapt a workhorse prompt to your own context and voice
  • Build the habit of saving prompts that worked so you never start from blank

Build Your First Reusable Workhorse Prompts

Most of your AI work is a handful of moves you repeat: summarize, sharpen, draft a reply, audit a document. Instead of retyping them from scratch every time, you build a small drawer of reusable prompts wired to your own context. In this exercise you pick the tasks you actually do each week and turn the four cores into prompts you keep. You stay the editor; the drawer just stops you from starting from blank.

Recommended tool

claude

Claude holds a longer thread and matches your voice well, which makes it a good home for building and tuning reusable prompts that should sound like you each time you run them.

Bring to the exercise

  • Three or four tasks you do at least weekly that AI could help with
  • Your AI Context Document (or the rough notes that will become it)
  • One real example of each task (a thread to summarize, a draft to sharpen, a message to reply to, a doc to audit)
Step 1

Name Your Repeat Tasks

Find the handful of moves worth turning into reusable prompts. Ten beats a thousand; start by naming yours.

What to substitute before pasting

  • [PASTE YOUR CONTEXT DOCUMENT] Your one-page AI Context Document. If you do not have one yet, paste a few lines about your role and your work.
  • [LIST 3-4 TASKS] Real recurring tasks, not aspirational ones. Weekly or more often.
I want to build a small drawer of reusable AI prompts for the work I actually repeat.

Here is my AI Context Document:
[PASTE YOUR CONTEXT DOCUMENT]

Here are tasks I do at least weekly:
[LIST 3-4 TASKS]

Sort them into the four cores: SUMMARIZE, SHARPEN, DRAFT A REPLY, AUDIT A DOC. If one does not fit a core, tell me which core it is closest to and why.
What good output looks like
  • Each task is mapped to one of the four cores.
  • It explains the mapping in a line, not just a label.
  • It flags anything that is really two tasks stuck together.

Verify before using AI's output

Step 2

Build the Summarize and Sharpen Prompts

Turn the two most common moves into reusable prompts wired to your context, with placeholders for what changes.

What to substitute before pasting

  • [PASTE A REAL THREAD OR DRAFT] A genuine thread to summarize or a draft to sharpen, with names removed if sensitive.
Write me two reusable prompts, each with clearly marked [BRACKET] placeholders for the parts that change each time.

1. SUMMARIZE: pull the key decisions and open questions out of a long thread or document. Tell it to use only what I paste.
2. SHARPEN: make a draft clearer and about 30 percent shorter without losing the ask.

For each, specify the exact output format so I get something usable, not something to reshape. Then show one filled-in example using this input:
[PASTE A REAL THREAD OR DRAFT]
What good output looks like
  • Both prompts have bracketed placeholders for the changing parts only.
  • Each names an exact output format (a short list, a tightened paragraph).
  • The filled-in example actually runs on your real input.

Verify before using AI's output

Step 3

Build the Draft-Reply and Audit-Doc Prompts

Finish the four cores. Draft-reply leans on your voice; audit-doc is the one that catches problems before they cost you.

What to substitute before pasting

  • [PASTE A MESSAGE TO REPLY TO] A real incoming message you owe a reply to, with names removed if sensitive.
  • [PASTE A DOC TO AUDIT] A document you want a second set of eyes on before it goes out.
Write me two more reusable prompts with [BRACKET] placeholders.

3. DRAFT A REPLY: given an incoming message plus my Context Document, draft a reply that sounds like me and ends with one clear next step. Use only the facts in the message and my context; if something is missing, ask rather than invent.
4. AUDIT A DOC: read a document looking for what is missing, ambiguous, or risky, and list it as questions I should resolve, not as fixes you silently make.

Show one filled-in example of each using these inputs:
[PASTE A MESSAGE TO REPLY TO]
[PASTE A DOC TO AUDIT]
What good output looks like
  • The reply sounds like you and ends with one clear next step.
  • The audit surfaces gaps as questions, not as silent rewrites.
  • Neither prompt invents facts you did not supply.

Verify before using AI's output

Step 4

Lock the Drawer

Assemble the four prompts into one clean drawer you will reopen, and set a habit for adding to it.

Pull my four reusable prompts into one clean, labeled list I can save: SUMMARIZE, SHARPEN, DRAFT A REPLY, AUDIT A DOC. Keep the placeholders.

Then give me a one-line rule for when a new prompt has earned a spot in this drawer, so it stays small and useful instead of becoming a junk pile.
What good output looks like
  • All four prompts are collected, labeled, and paste-ready.
  • The placeholders survived the cleanup.
  • The rule for adding new prompts keeps the drawer small on purpose.

Verify before using AI's output