Your AI Installation Kit

Overview

What you're building

A repurposing workspace with your output formats defined (e.g. 3 LinkedIn posts, a newsletter blurb, show notes) and your voice examples. Drop in one source piece, get the full set, review, publish.

Why this setup

Repurposing is the same transformation every time. Defining each output format once, with your examples, gives consistent results and stops each piece from sounding like generic AI. A workspace keeps formats and voice together.

The workflow architecture

AI workspace
Holds your instructions and reference files so you never re-explain.
Reusable instructions
Output set definition and voice rules.
Reference document
Best-performing past examples of each format.
Repeat-use checklist
Pre-publish review.

You haven't picked a tool yet, so this kit is platform-neutral. Both Claude and ChatGPT support this setup.

Claude	ChatGPT
Claude Projects: instructions + project knowledge files	ChatGPT Projects: instructions + uploaded files
Optional Claude Skills for reusing a format across chats (plan-dependent)	Personalization settings can hold short preferences
Paid plan needed for Projects	Plan determines Project and file limits

What to prepare

□One recent source piece (transcript or article).
□2–3 of your best posts per channel.
□The list of outputs you actually publish.

Build it once

Create a dedicated workspace named "Content Repurposing" in the AI tool you choose. Both Claude and ChatGPT call this a "Project". Claude offers Projects on all plans; ChatGPT availability depends on your plan.
Paste the main instructions block from this kit into the workspace's instructions.
Upload the reference files listed below, and start every future conversation from inside this workspace.
Define your output set in the Output Set block.
Paste instructions; upload your examples file.
Run your most recent piece; compare to what you'd write.
Adjust formats and re-run until edits are light.

Copy-ready materials

Edit anything in [BRACKETS]. Changes are kept when you save the kit.

Project Instructions & Output Set

Paste into workspace instructions.

You repurpose my source content each week. Match the voice in "EXAMPLES".

FROM EACH SOURCE PRODUCE:
1. [3] LinkedIn posts: hook line, 3–5 short paragraphs, one question at the end. No hashtags unless asked.
2. Newsletter blurb: [80–120] words + link placeholder [LINK].
3. Show notes / summary: 5 bullet takeaways + timestamps if the transcript has them.
4. [Your format]

RULES
- Use only ideas present in the source. No invented statistics or stories.
- Each post must stand alone and use a different angle.
- Avoid: "game-changer", "unlock", "dive in", emoji strings, and [OTHER WORDS YOU DISLIKE].

Pre-Publish Checklist

Before posting.

□ Claims and numbers appear in the source
□ Names and quotes accurate and approved
□ Sounds like me read aloud
□ Links added
□ Platform rules / client approvals met

How Claude can help execute this

Primary pathRecommended where available

Why use this instead of a regular chat?

A task can take one transcript or article and produce the full set of outputs as separate documents in one go, all consistent with each other.

Task execution needs a paid Claude plan. Add your plan in My AI Setup for a more specific recommendation.

Availability depends on your Claude plan and device. Add them in My AI Setup for a more specific recommendation.

1. Set up once

· Create a Project with the output set and your voice examples.

2. Claude capabilities used

· Multi-step task execution (Cowork-style)
· Files saved to your Claude account
· Claude Docs & Slides (beta, paid plans)

3. Access, files & permissions

· The source transcript or article
· A paid Claude plan

4. What Claude can do

· Produce every format in your output set
· Keep claims tied to the source

5. What you review or approve

· Claims, names, and quotes
· Everything before it's published — Claude doesn't post for you here

6. What changes each run

· The source piece and angle

7. Test it safely

· Run a piece you've already repurposed and compare

8. If it doesn't work

Outputs blur together.: Ask for each output as a separate document with its own heading.

Run the task

If your Claude has one unified message box (no Chat/Cowork choice)

Open the Project, then describe the task in any conversation. Claude decides whether it's a quick answer or a task.

If you see separate “Chat” and “Cowork” options

In the message box, select “Cowork” in the bottom-left corner, then describe the task.
Projects work the same way in Cowork and in chat.

Task request

From the attached [TRANSCRIPT/ARTICLE], create every output in this project's output set as separate documents. Use only ideas from the source.

Fallback: Paste the source into the Project and ask for each format.

By default, Claude asks before taking an action. Keep that on for anything involving money, personal records, or files you can't replace.

How to test it

Run a past piece you already repurposed by hand.

Success looks like

✓ Outputs need only light edits.
✓ No invented content.

How to use it next time

Upload the new transcript or article.
Say 'Repurpose. Emphasize: [angle]'.
Edit and publish from your own tools.

Set up once — reuse

Output set · Voice examples · Checklist

Changes each time

The source piece · Any angle to emphasize

Troubleshooting

Sounds generic.: Add more of your real examples and a banned-words list.
Posts repeat the same point.: Ask for 'three different angles: lesson, story, contrarian take'.
Transcript too long.: Upload as a file rather than pasting; or split by segment.

Limitations, privacy & safety

· It doesn't post or schedule content in this setup.
· You're responsible for accuracy and rights to quoted material.

Privacy & safety

· Get permission before using guest or client material.
· Keep unreleased material out if your agreements restrict it.