agentsclimarketplace

Inbox triage

Skill thefiredev-cloud/meshvault-skills-starter/skills/inbox-triage

Free open agent skills from MeshVault. Plain Markdown, approval-gated, MIT. Private AI staff on hardware you own.

Install
npx -y skills add thefiredev-cloud/meshvault-skills-starter --skill inbox-triage

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

2 things to look at

  • 15 days oldThe repository was created 15 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

This skill should be used when the user asks to "triage my inbox", "what needs a reply", "clean up my email", or wants unread mail sorted into act, reply, and archive with a short summary.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.8 KB, 343 tokens by cl100k_base, as published. Nobody here has run it

Inbox Triage

Sort unread email into three buckets and hand back a summary the owner can act on in two minutes. Never reply, never delete, never unsubscribe without approval.

Required Inputs

  • Access to the inbox (read scope is enough for triage)
  • The owner's list of VIP senders, if one exists (clients, family, key vendors)
  • Any standing rules the owner has stated (for example "receipts go to the receipts folder")

Steps

  1. Read unread messages from newest to oldest. Do not mark anything read unless the owner has said that is fine.
  2. Put each message in exactly one bucket:
    • Act: money, deadlines, clients, anything with a date attached, anything from a VIP sender
    • Reply: real people waiting on an answer where a short reply closes it
    • Archive: newsletters, notifications, receipts, promotions
  3. For each Act item, write one line: who, what they need, by when.
  4. For each Reply item, draft a suggested reply in the owner's voice. Keep drafts short.
  5. Present the summary: Act list first, then Reply drafts, then the Archive count.
  6. Only after approval: send approved replies and archive the Archive bucket.

Approval Gate

Replies are outbound client-facing text. Nothing sends until the owner approves each draft. Archiving is reversible, but still wait for the single "archive those" confirmation before touching anything.

Output

  • A triage summary the owner can read in under two minutes
  • Approved replies sent, archive bucket cleared
  • A count of what moved where, appended to the daily log

Gives 0 of the 12 instructions most debug triage skills give in 343 tokens

Counted across 839 of the 1,149 authors here whose files we hold, read 2026-08-07

  • investigate root cause before proposing any fixin 102 of 839, across 67 files
  • read error messages completelyin 89 of 839, across 49 files
  • create a failing test case before fixingin 84 of 839, across 46 files
  • reproduce the issue consistentlyin 82 of 839, across 41 files
  • change one variable at a timein 82 of 839, across 42 files
  • check recent changesin 74 of 839, across 36 files
  • write the regression test before fixingin 74 of 839, across 40 files
  • fix the root cause not the symptomin 60 of 839, across 45 files
  • implement a single fix at a timein 59 of 839, across 20 files
  • trace data flow backward to the sourcein 50 of 839, across 20 files
  • remove all debug instrumentationin 49 of 839, across 13 files
  • form a single hypothesisin 48 of 839, across 18 files

Said here and by no other author read

  • read unread messages newest to oldest
  • put each message in exactly one bucket
  • write one line per act item
  • draft suggested replies in the owner's voice
  • present the summary act first then reply then archive
  • send replies only after approval

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. 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.