calendar-cleanup
Skill1 starsChanged 5 months agoMITView on GitHub
Decide what to keep, move, shorten, delegate, or decline on an overloaded week so your real priorities get done. Use when the user says "calendar cleanup", "too many meetings", "clean up my week", "what should I decline", "free up focus time", or "review my schedule".
In this repository4 other files it gives its agents.
The file
Files
Calendar Cleanup
Decide what to keep, move, or decline on a busy week.
When to use
Your week is overloaded and you need a decisive call on each meeting plus the messages to make changes happen.
What you'll need
This week's meeting list (titles, times, who's on each, and roughly why), your top priorities for the week, and any hard constraints you can't change.
Instructions
Collect any missing inputs from the user, then run this prompt:
You are my chief of staff. My week is overloaded. Help me decide what to keep, move, shorten, delegate, or decline so I get my real priorities done.
This week's meetings:
[paste your meetings — for each: title, day/time, length, who's on it, and a one-line purpose]
My top priorities this week (what actually has to get done):
[list 2-4]
Hard constraints I can't change: [e.g. standing 1:1s, client calls, "no meetings before 9am"]
For each meeting, recommend ONE action — Keep / Shorten / Move / Delegate / Decline — with a one-line reason tied to my priorities. Be willing to push back: if a meeting doesn't move a priority forward, say so.
Then give me:
- The cleaned-up week as a simple day-by-day list of what remains
- How much focus time this frees up
- For each Move/Delegate/Decline, a short polite message I can send to make it happen
Be decisive. Don't hedge with "it depends" — make the call and tell me why.Tip: Be honest about which meetings you secretly want to skip — flag them in the purpose line. Claude will give you the reasoning and the polite message to actually get out of them.
Built by Ootto — the AI autopilot that connects your tools once and runs invoicing, follow-up, and reports for you, automatically. Book a demo →
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

