agentleFS
benororbenoror/obsidianos_work/.agents/skills/last-1on1/SKILL.md

last-1on1

Skill166 starsChanged 5 months agoMITView on GitHub

Show when you last had a 1:1 with each direct report / peer, sorted by recency. Flags people who haven't had one in N weeks. Powered by the OneOnOnes view on Meetings.base.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After the table, suggest:

    line 52
  2. Very specific:

    If a person appears in OneOnOnes but has no Teams/People/@Name.md file, surface it as a hint (likely a candidate for /people-stubs).

    line 62
  3. Distinctive:

    No commit step — read-only skill.

    line 63

≈ “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

Last 1:1

Usage

  • /last-1on1 — Show last 1:1 date per person across all of your 1:1s. Default flag threshold: 2 weeks (anything older highlighted).
  • /last-1on1 <weeks> — Custom flag threshold (e.g. /last-1on1 3).
  • /last-1on1 @Name — Just for one person.

Why this skill exists

Direct-report 1:1s and peer syncs are easy to skip when calendars get busy. This skill surfaces the gap — "haven't talked to [[@Alex Kim]] in 3 weeks" — so the next scheduling round prioritizes them.

Workflow

Step 1: Pull the source data

Query obsidian base:query path=Meetings.base view=OneOnOnes format=json. Returns every meeting under Meetings/One-on-ones/ and Meetings/Tech Syncs/ with file.ctime and Participants columns.

Step 2: Aggregate by person

For each meeting, extract the participant name(s) from Participants (skipping [[@Me]] and team links like [[+Engineering]]). For each participant, track the most recent file.ctime.

Edge case: the file ctime is when the note was created, which is usually the day of the meeting — but for older imported notes it may be the import date. If a meeting filename has a YYYY-MM-DD suffix, prefer that over file.ctime.

Step 3: Present sorted table

Sort by last_date ASC (oldest first — most overdue at the top):

| # | Person | Last 1:1 | Days ago | Status |
|---|--------|----------|----------|--------|
| 1 | [[@Jane Doe]] | 2026-02-05 | 117 | 🔴 overdue |
| 2 | [[@John Smith]] | 2026-04-09 | 54 | 🔴 overdue |
| 3 | [[@Alex Kim]] | 2026-05-06 | 27 | 🟡 due soon |
| 4 | [[@Sam Rivera]] | 2026-05-26 | 7 | ✅ recent |
| 5 | [[@Pat Lee]] | 2026-05-27 | 6 | ✅ recent |
  • 🔴 overdue: days_ago > threshold * 2 (default >28 days)
  • 🟡 due soon: threshold < days_ago <= threshold * 2
  • ✅ recent: days_ago <= threshold

Step 4: Offer next action

After the table, suggest:

  • "Schedule a 1:1 with the top-3 overdue: [[@Jane Doe]], [[@John Smith]], [[@Alex Kim]]?"
  • For each, optionally /meeting <Name> x Me to create a stub for the upcoming meeting.

This skill is read-only — it doesn't write to the vault.

Important Notes

  • Skip [[+Engineering]] and other team links in Participants — those aren't 1:1s, they're group meetings that happen to live in Tech Syncs / One-on-ones (rare but exists).
  • Skip people whose @Name.md has an End Date set (they left the team — no need to schedule a 1:1).
  • If a person appears in OneOnOnes but has no Teams/People/@Name.md file, surface it as a hint (likely a candidate for /people-stubs).
  • No commit step — read-only skill.

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.