Create a 'stop doing' list with a prompt built for Claude and ChatGPT. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
4.9(55 ratings)909 copies
Updated By Author
44 words · v1.2
Fill in the blanks · 1 variable
Claude promptReplace every highlighted token before sending
<task>
Based on my commitments below, propose a stop-doing list of five items. For each explain the cost, who benefits if it stops, what to do instead and the risk of stopping. Be direct. Do not suggest stopping anything legally or ethically required.
Commitments:
{commitments}
</task>
Think carefully before answering. Keep any reasoning separate and put the final deliverable inside <answer> tags.
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open Claude and start a new chat. Paste the prompt exactly as written.
2
Replace each placeholder ({commitments}) with your own details. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. Calendar invites, owners and deadlines before you send the summary to anyone.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Commitments: Two recurring meetings, a weekly report.
Example output
**Three outcomes:** ship the pricing page, finish the hiring loop, close the quarter report.
**Schedule:**
- Mon 09:00-11:00 — pricing page deep work (no meetings)
- Tue 09:00-10:30 — hiring debrief, then async feedback
- Wed 09:00-11:30 — quarter report draft
- Thu — buffer + admin block
- Fri 14:00-15:00 — weekly review
**Not this week:** the newsletter redesign. **Risk:** the Tuesday debrief may overrun; cap it at 45 minutes and move the rest async.
Tips for a better result
Give the actual commitments and hours available; optimism is the enemy of a usable plan.
Protect one buffer block. Something always slips.
Use the model to extract decisions and actions from notes, not to generate more meetings.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Building an elaborate system you will abandon in two weeks.
Scheduling every hour with no room for the unexpected.
Letting the model invent commitments or deadlines you never agreed to.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the create a 'stop doing' list prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
A productivity prompt for write a project retrospective agenda. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
A productivity prompt for turn a checklist into a recurring routine. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
This copy-ready productivity prompt helps you build a personal knowledge system with fewer blank-page decisions. Paste it into ChatGPT and Claude, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
ChatGPTClaude
4.7(83)957 copies
A
Written and reviewed by Author
AIPrompt123 Contributor
Contributing author and prompt engineer at AIPrompt123.
Last reviewed 17 November 2026 · version 1.2 · tested on Claude, ChatGPT
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.