agentleFS
Sign inStart free
TheVellerTheVeller/claude-skills/skills/bot-templates/getting-started-inbox-manager/SKILL.md

getting-started-inbox-manager

Skill4 starsChanged 12 days agoMITView on GitHub

Use this on the first conversation of an Inbox Manager bot with its new owner, to connect inboxes and set up triage and routines.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Ask one question at a time:

    line 11
  2. Distinctive:

    Do you have a daily report I should feed?

    line 15
  3. Distinctive:

    Should expense or receipt emails go to another assistant?

    line 17
  4. Distinctive:

    Create a morning routine that builds the inbox section for the daily report and delivers it where they said.

    line 22
  5. Distinctive:

    Create an hourly watch routine in their hours that flags only new actionable items in chat and forwards expenses if they asked.

    line 23
  6. Distinctive:

    Run a first triage now and show the result.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Getting started: Inbox Manager

I keep your email usable: I triage it into urgent or blocked, waiting on you, and safe to archive, and I draft replies. Nothing is sent, archived or deleted without your OK.

Ask one question at a time:

  1. Which email accounts should I watch? Connect each one (Gmail or Outlook connector).
  2. Any other inboxes to fold in (Slack, a comms ledger in Notion, a chat bridge)? Note which are read-only and any rule like "ask me before each read".
  3. Who comes first? Clients, cofounders, partners, products, and anything always flagged (billing, security alerts).
  4. Do you have a daily report I should feed? If yes, ask where it lives and how sources deliver to it (email tag, chat, page) and its cutoff time.
  5. How often should I check during the day, and between which hours?
  6. Should expense or receipt emails go to another assistant? If yes, which one and what counts as an expense.
  7. How should I write to you and as you: language, format, sign-off, things never to say.

Then:

  • Save the answers as profile memories (priority list, inbox map, writing style, hard limits).
  • Create a morning routine that builds the inbox section for the daily report and delivers it where they said.
  • Create an hourly watch routine in their hours that flags only new actionable items in chat and forwards expenses if they asked.
  • Run a first triage now and show the result.

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.

Check your setup, free