agentleFS
Rome-1Rome-1/obsidian-claude-starter/.claude/skills/inbox-triage/SKILL.md

inbox-triage

Skill5 starsChanged 34 days agoMITView on GitHub

Processes everything in the vault's Inbox/ folder, one item at a time, filing each into the right place (an existing project or person note, a new research note, a task checkbox) or archiving it, and leaves the inbox empty. Use when the user says "triage my inbox", "process the inbox", "clear my captures", "file these notes", runs /inbox-triage, or when the session-start summary shows inbox items waiting and the user asks what to do with them. Not for email inboxes.

53 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use aeon-update, auto-workflow and 10 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.
  • aaronjmarsSkill

    aeon-update

    Pull framework updates from the upstream Aeon repo into this instance - 3-way merges canon's new commits into a PR, never clobbering operator config.

    Also in 4 projects that use this

  • aaronjmarsSkill

    auto-workflow

    Two-mode aeon.yml workflow builder - analyze inspects URLs and emits a tiered, signal-verified skill-enablement plan plus an aeon.yml diff; enable flips slugs to enabled:true and opens a PR.

    Also in 4 projects that use this

  • Yugpat1835Skill

    branded-deck-builder

    Builds PowerPoint decks on the user's own company template and checks every slide against written brand rules (colours with hex codes, fonts, logo placement, banned visuals). Use when the user asks for a branded, on-brand, CI-compliant or corporate-template presentation, or wants a deck that follows company design guidelines. Confirms an outline first, then builds slide by slide and saves a DRAFT deck to OneDrive.

    Also in 4 projects that use this

  • Yugpat1835Skill

    cmo-reviewer

    Reviews a proposal, business case, deck or plan in character as a Chief Marketing Officer archetype, producing a structured DRAFT review document with a verdict, findings cited to specific passages, risks and five interrogation questions. Use when the user asks for a CMO review, a marketing executive's read on a document, or wants to pressure-test positioning, messaging, pricing or a launch plan before a real executive review.

    Also in 4 projects that use this

  • +5 more from aaronjmars
  • +3 more from Yugpat1835

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 46 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If there are more than about 15, say how many and propose doing the oldest batch first.

    line 13
  2. Very specific:

    Search for existing notes before creating new ones (Grep the name or topic across Projects/, People/, Knowledge/).

    line 29
  3. Distinctive:

    Ask before acting when the destination is unclear, or when an item would create a new folder or a new note type.

    line 31
  4. Distinctive:

    Keep the user's original wording.

    line 36
  5. Very specific:

    Remove the inbox file only after its content is in the new place.

    line 38
  6. Very specific:

    Commit with vault: triage inbox - N items if the user has agreed to agent commits.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 46 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

Inbox triage

Inbox/ holds raw captures. The job is to give each one a home, keeping the user's words, and leave Inbox/ holding nothing but its README.md.

1. List

List files in Inbox/ except README.md, oldest first. If there are more than about 15, say how many and propose doing the oldest batch first.

2. Decide, item by item

For each item, read it, then pick one destination:

The item is...Do this
About an existing projectAppend to that project's note (## Log or ## Next actions), or to Current-State.md for a folder project
About a personAdd a dated line under ## Interactions or ## Things to remember in their note; update last_contact / next_action if it changes them
Something to doA - [ ] checkbox in the relevant project note (or a bead, if .beads/ exists)
Something learned, or a link worth keepingA note in Knowledge/ from System/Templates/Research-Note.md, or a line in an existing one. For anything substantial, follow the research-capture skill
A new project ideaA new project note with status: idea
Meeting notesFollow the meeting-notes skill
No longer relevantMove to Archive/

Search for existing notes before creating new ones (Grep the name or topic across Projects/, People/, Knowledge/).

Ask before acting when the destination is unclear, or when an item would create a new folder or a new note type. Batch the questions: show a short table of item → proposed destination, and let the user correct it in one reply.

3. File

  • Keep the user's original wording; add a link back to context if useful.
  • Set updated: on every note you change.
  • Remove the inbox file only after its content is in the new place. A file that is a pure link or a single line can be deleted once filed; anything longer, move into Archive/ if the user prefers to keep originals.

4. Check and report

  • Run python3 scripts/check_vault.py.
  • Report: how many items, where each went (one line each, with links), and anything left in Inbox/ and why.
  • Commit with vault: triage inbox - N items if the user has agreed to agent commits.

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.