How the weekly ranking works
One vote per prompt, a fresh count every Monday, and a simple tie-break. Everything about how prompts reach the top three, in plain words.
Turn messy notes or a transcript into decisions, a task table with owners and dates, the open questions, and a message for the team channel.
These are my raw notes from a meeting. Turn them into something the team can act on. Meeting: [NAME OR PURPOSE] Date: [DATE] Who was there: [NAMES] <notes> [PASTE NOTES OR TRANSCRIPT] </notes> I need, in this order: 1. A summary, two sentences at most. 2. The decisions. Only things that were actually agreed. 3. A task table with Task, Owner, Due and Depends on. If nobody took a task or no date came up, write UNASSIGNED or NO DATE. Never make one up. 4. Open questions: what came up but wasn't settled, and who should answer it. 5. Any risks someone mentioned. 6. A short message I can paste into the team channel. Stick to what's in the notes. If something is unclear, put it under open questions.
Summary. The launch moves from 2 October to 9 October so the checkout bug can be fixed properly. Marketing keeps the original date for the teaser email.
| Task | Owner | Due | Depends on |
|---|---|---|---|
| Fix the Stripe webhook retry bug | Priya | 3 Oct | none |
| Update the pricing page to the 3 project cap | Marco | 1 Oct | none |
| Test the full checkout on staging | UNASSIGNED | 6 Oct | Stripe fix |
| Rewrite the teaser email | Lena | 27 Sep | none |
Quick recap: launch moves to 9 Oct, the teaser still goes out 30 Sep. Priya has the Stripe fix, Marco the pricing page, Lena the teaser. We still need someone to test checkout on staging. Who can take it?
NoteThis is an example. Results change between runs and model versions. Claude Prompts is a fan project and is not affiliated with Anthropic.
Run it while you can still spot mistakes. Weekly syncs, kick-offs, client calls, retros. It copes with scrappy bullet notes just as well as with an automatic transcript from Zoom, Meet or Teams.
It's the whole point of the prompt. Left alone, a model will happily fill a gap with a plausible name or date, and one invented deadline in a recap costs you more trust than an empty cell ever would. Read the decisions before you send them, too. Something nobody objected to isn't always something that was decided.
Use the copy button above. The full text is included, nothing is cut off.
Everything highlighted in yellow is a placeholder. Swap it for your own topic, audience or data.
If the result helped, press the heart. Votes decide which prompts make the weekly top 10.
One vote per prompt, a fresh count every Monday, and a simple tie-break. Everything about how prompts reach the top three, in plain words.
Wrapping parts of your prompt in simple tags is one of the easiest ways to get more reliable answers from Claude. A practical guide with examples.