agentleFS
ohanyanohanyan/adulting/skills/shutdown-ritual/SKILL.md

shutdown-ritual

Skill1 starsChanged 7 months agoMITView on GitHub

Cal Newport end-of-workday close-out. Captures open loops, confirms tomorrow's top 1, then the user says "schedule shutdown complete" and stops thinking about work. Use at the hard stop time, not whenever work feels done.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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:

    Add each to their task system.

    line 29
  2. Distinctive:

    Look at tomorrow's calendar.

    line 39
  3. Distinctive:

    No work email after shutdown.

    line 51
  4. Distinctive:

    No work Slack after shutdown.

    line 52
  5. Distinctive:

    If a work thought arrives, write it on a pad and release it.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

/shutdown-ritual

From Cal Newport's Deep Work. The point is not to finish work, it is to stop. Cognitively stop. The ritual is how your mind learns to release.

Step 1: Inbox sweep

Walk through in order:

  1. Email inbox. Any unread? Either reply in under 2 minutes, schedule a reply for tomorrow, or capture into the task system.
  2. Slack / Teams / chat. Same rule.
  3. Text messages that are work-adjacent.
  4. Browser tabs. Close them or save to read-later.
  5. Physical desk. Papers into piles or away.

You are not trying to reach zero. You are trying to reach captured. Nothing important rattling around in your head unlogged.

Step 2: Task system review

Ask the user:

  • "Any open loops from today that you have not captured yet?"
  • "Any promises you made today that need to be on a list?"
  • "Anyone waiting on you that you need to follow up with tomorrow?"

Add each to their task system.

Step 3: Tomorrow's top 1

"If you only get one thing done tomorrow, what is it?"

One sentence. Not three. Write it where you will see it first thing.

Step 4: Calendar glance

Look at tomorrow's calendar. Any meeting that needs prep? If so, block 15 minutes before it and label the block with the prep task. Don't do the prep now. Just guarantee the space.

Step 5: The phrase

The user says out loud: "Schedule shutdown complete."

This is not a joke. The phrase is a conditioned trigger. Over time your brain learns: after those three words, work is done.

Step 6: The commitment

One evening rule, pick any:

  • No work email after shutdown.
  • No work Slack after shutdown.
  • Phone stays in a drawer until morning.
  • If a work thought arrives, write it on a pad and release it.

Output

Append a one-line log to ~/adulting-data/journal/shutdown-log.md:

<date> <time>  top1: <sentence>  status: shutdown complete

Print back a clean summary. End with: "Go be with the people in the house."

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.