agentleFS
JakeschincariolJakeschincariol/closer-skill/scheduler/SKILL.md

scheduler

Skill33 starsChanged 11 days agoMITView on GitHub

Scheduler. Puts every booked call on your calendar. Reads a reply like "Thursday at 2 works" and turns it into the right date and time, checks your calendar for a clash, offers open slots when they ask "when are you free?", creates the invite with a Google Meet link from your own calendar after your yes, confirms by email, and moves the deal to call-booked so follow-ups stop. Use when the user says "book it", "schedule a call", "put it on my calendar", "send an invite", "when am I free", "they said Thursday works", or when /follow-up shows a reply with a time.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup, research and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never books, moves or cancels an event without the user's yes for that exact event.

    line 55
  2. Distinctive:

    Never double-books over something already on the user's calendar.

    line 56
  3. Distinctive:

    Never reads calendar details beyond free and busy times to find a slot.

    line 57
  4. Distinctive:

    Stop at the first "no" or any sign of disinterest.

    line 64
  5. Distinctive:

    Never invent a time someone agreed to.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

scheduler

The moment someone says yes to a call, the Scheduler gets it on both calendars before the moment passes. One booked call is worth more than ten more follow-ups.

${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).

python3 "${CLAUDE_SKILL_DIR}/slots.py" parse --text "Sorry, crazy week! Thursday at 2 works." --today 2026-10-27
python3 "${CLAUDE_SKILL_DIR}/slots.py" free --busy closer/busy.json --from 2026-10-28 --days 3 --length 30
python3 "${CLAUDE_SKILL_DIR}/slots.py" invite --contact dana-harbor-lane --start 2026-10-29T14:00 --minutes 30
python3 "${CLAUDE_SKILL_DIR}/slots.py" book --contact dana-harbor-lane --start 2026-10-29T14:00 \
    --minutes 30 --approval "yes" --busy closer/busy.json

Steps

  1. When. slots.py parse on their reply. "at 2" with no am or pm is read as 2 PM (1 to 7 is afternoon, 8 to 12 is morning). If it prints "No clear time", ask them for one; never guess a day. Say the full date back to the user: "Thursday, October 29 at 2:00 PM your time. Right?"
  2. Clash. With the calendar connector, read the user's events for that day and write them to closer/busy.json as [{"start": "...", "end": "..."}]. If they asked for options instead, slots.py free lists open slots in working hours; offer two or three.
  3. Ask. "Book Harbor Lane Dental x Your Agency, Thursday October 29, 2:00 to 2:30 PM, Google Meet, with Dana Ortiz invited? Reply yes or no."
  4. Book. On a yes, create the event on the user's calendar with the calendar connector (title, time, Google Meet, Dana as a guest). No calendar connector: slots.py invite writes an .ics the user can open or attach.
  5. Log. slots.py book --approval "<their yes>". The deal moves to call-booked and /follow-up stops.
  6. Confirm. Draft the reply with /follow-up's confirm-time template ("Thursday at 2 works, Dana. Sending the invite now."), and send it only on its own yes.
  7. Prep. Remind the user to run /researcher before the call.

Example from the reel

Tue Oct 27, 11:48 AM: "Sorry, crazy week! Thursday at 2 works." parse gives Thursday, October 29, 2:00 PM. The user is free, says yes, and the calendar shows "Harbor Lane Dental x Your Agency, Thursday, October 29, 2:00 to 2:30 PM, Google Meet, guests Dana Ortiz and You". (Illustrative: Dana and Harbor Lane Dental are fictional.)

What it never does

  • Never books, moves or cancels an event without the user's yes for that exact event.
  • Never double-books over something already on the user's calendar.
  • Never reads calendar details beyond free and busy times to find a slot.

Consent and truth

  • Nothing is sent, booked or signed without the user's explicit yes for that exact message, invite or document. Claude drafts, the user says "yes", then it goes out from the user's own accounts: calendar invites through the user's own calendar. One yes per message. Never "yes to all".
  • Stop at the first "no" or any sign of disinterest. A request to stop is honoured forever, across every skill.
  • Never invent a time someone agreed to. When it is unclear, ask.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.