agentleFS
OneWave-AIOneWave-AI/claude-skills/cowork-inbox-triage/SKILL.md

cowork-inbox-triage

Skill378 starsChanged 53 days agoMITView on GitHub

Daily inbox triage using Cowork's email write tools (Microsoft 365 or Gmail) -- classifies unread mail, drafts replies in your voice, flags what needs a decision, and schedules follow-ups. Built to run as a recurring Cowork scheduled task.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Classify: every thread into exactly one bucket:

    line 19
  2. Distinctive:

    Never send email. Create drafts only.

    line 31
  3. Distinctive:

    Never archive anything that mentions money, contracts, legal matters, or a specific person's problem -- misclassified noise is recoverable, …

    line 32
  4. Distinctive:

    If the connector lacks write scope, degrade gracefully: produce the digest and paste-ready reply texts instead of drafts.

    line 36

≈ “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

Cowork Inbox Triage

Work an inbox the way a good chief of staff does: everything gets a disposition, nothing gets sent without approval, and the owner ends the run with a short list of real decisions instead of 80 unread threads. Uses the connected mail tools (Microsoft 365 or Gmail MCP connectors) for reading, labeling, and drafting.

Setup

On first run, learn the owner's voice: read 10-15 sent replies and note greeting style, sign-off, sentence length, and formality. Store the profile in the conversation and reuse it for every draft. Ask once which categories matter (default set below) and what the auto-archive rules are.

Workflow

  1. Sweep. Pull unread and flagged threads from the last cycle (default: 24 hours). Group by thread, not message.
  2. Classify every thread into exactly one bucket:
    • NEEDS DECISION -- only the owner can answer (pricing, commitments, personnel)
    • DRAFT READY -- routine reply Claude can write for approval
    • WAITING ON THEM -- owner already replied; schedule a follow-up check
    • FYI -- no response needed; summarize in the digest
    • NOISE -- newsletters, notifications, cold outreach; label/archive per the standing rules
  3. Draft. For every DRAFT READY thread, write the reply in the owner's voice as a draft -- never send. Keep drafts shorter than the email being answered.
  4. Follow-ups. For WAITING ON THEM threads past their expected response window (default 3 business days), draft a polite bump. For threads with dates in them, propose calendar holds via the calendar write tools.
  5. Digest. Post one summary: decisions needed (with one-line context and a recommended answer each), drafts awaiting approval, follow-ups queued, and a one-line count of what was archived.

Rules

  • Never send email. Create drafts only; the human sends.
  • Never archive anything that mentions money, contracts, legal matters, or a specific person's problem -- misclassified noise is recoverable, a missed client email is not.
  • A recommended answer accompanies every NEEDS DECISION item. Surfacing a question without a recommendation is half the job.
  • Quote the sender's actual ask in the digest -- do not paraphrase requests into vagueness.
  • Respect confidentiality: HR, health, and personal matters get flagged privately, never summarized in a shared channel.
  • If the connector lacks write scope, degrade gracefully: produce the digest and paste-ready reply texts instead of drafts.

Scheduled Mode

As a Cowork scheduled task (weekday mornings), run the full workflow unattended in a cloud session and deliver the digest before the workday starts. Track threads across runs so a bump is never drafted twice for the same silence.

Quick Commands

  • "Triage my inbox" -- full run, last 24h
  • "Catch me up" -- sweep and digest only, no drafts
  • "Draft replies to everything easy" -- classification + drafts only
  • "Who am I waiting on?" -- the WAITING ON THEM ledger with days elapsed

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.