agentsclimarketplace

Email scheduling

Skill cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/schedule-planning/email-scheduling

Workflow for parsing meeting request emails, matching constraints to calendar availability, and generating reply files.From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill email-scheduling

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.5 KB, 425 tokens by cl100k_base, as published. Nobody here has run it

Email-Based Meeting Scheduling

Workflow

1. Parse Email Requests

Extract from each email:

  • Duration: e.g., "one-hour", "1.5 hour", "45-minute"
  • Date constraint: e.g., "March 9th, 2026"
  • Time window: e.g., "10:00am to 2:00pm", "1:00 PM and 5:00 PM PST"
  • Sender email: from the from_email field

2. Timezone Conversion

  • If the request specifies a timezone different from the calendar, convert:
    • PST to ET: add 3 hours (e.g., 1:00 PM PST = 4:00 PM ET)
    • CST to ET: add 1 hour
    • MST to ET: add 2 hours

3. Scheduling Strategy

  • Find the earliest available slot that satisfies all constraints
  • When multiple requests target the same day, schedule them so all can be accommodated
  • Blue (low-priority) calendar blocks can be overwritten
  • Never overlap with non-overwritable blocks

4. Reply Template Format

Hi,

    Thank you for your meeting request.

    I can be available:

    Date: {day_name}, {month} {DD}, {YYYY}
    Time: {HH:MM AM/PM} - {HH:MM AM/PM}
    Duration: {meetingDuration} hour(s)

    If this time doesn't work, please let me know your preferred alternatives.

    Best regards,
    ConSkillBench

5. Formatting Rules

  • Date: Monday, March 09, 2026 (zero-padded day, full month name)
  • Time: 09:00 AM - 10:30 AM (zero-padded hours, AM/PM with space)
  • Duration: use "hour(s)" as unit; for 45 min use "0.75 hour(s)"

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.