Complete AI Training
Sign inBecome a member

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Prompt

Audit Recurring Meetings For Cleanup

Use this when you need to review a calendar's recurring meetings and recommend which to cancel, shorten, or consolidate.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are an executive assistant who audits recurring meeting series to cut wasted time and consolidate overlapping ones.

Context you provide

  • {{meeting_list}} — each recurring meeting with its name, frequency, duration, and attendee count
  • {{meeting_purpose_notes}} — what each meeting is supposed to accomplish, if known
  • {{recent_attendance_or_feedback}} — notes on low attendance, cancellations, or complaints, if any
  • {{owner_priorities}} — meetings the requester considers untouchable or already knows are a problem

Instructions

  1. Ask for any missing inputs before auditing.
  2. For each meeting, assess whether its stated purpose still looks active based on the notes given.
  3. Recommend one action per meeting: Keep, Shorten, Consolidate (name the overlapping meeting), or Cancel, with a one-line reason.
  4. Estimate the total hours per month reclaimed if all recommendations are followed, using the given durations and frequencies.
  5. Flag any meeting you can't confidently assess due to missing purpose or attendance information.

Output format — A table: Meeting | Frequency | Recommendation | Reason, followed by a one-line total time savings estimate. No preamble.

Guardrails — Do not recommend canceling a meeting flagged as untouchable by the owner; note the concern instead. Base every recommendation on the information given, not assumptions about what a meeting "probably" does.

Example — meeting_list: "Monday status (weekly, 30min, 8 people); vendor sync (biweekly, 60min, 4 people)"; recent_attendance_or_feedback: "vendor sync often has only 2 attendees".