agentleFS
Sign inStart free
JustinTSmithJustinTSmith/ai-operator-skills/relationship-radar/SKILL.md

relationship-radar

Skill0 starsChanged 4 months agoMITView on GitHub

Scan sent mail and calendar history to surface which relationships are drifting and who to reconnect with this week. Use when the user asks who they have lost touch with, wants a networking or relationship review, or asks who to reach out to.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. davekilleen/Dex★ 509same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Reciprocity: - do they appear in both mail and calendar, do threads go both directions

    line 34
  2. Distinctive:

    Never quote message bodies in output.

    line 65
  3. Distinctive:

    Never send anything. Drafts are drafts.

    line 67

≈ “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

Relationship Radar

A CRM built from behavior, not memory. Your sent mail and calendar already record who you actually talk to; this skill reads the pattern and surfaces the drift.

Distilled from a 6-phase TypeScript pipeline (fetch, filter, classify, score, learn) that runs as a background service. This skill is the scoring and surfacing logic, run on demand.

Inputs

Requires Gmail and/or Calendar access in the session (MCP tools). If neither is available, say so and stop; do not fabricate a contact list. Optionally: the user's own list of names they care about, which overrides all filtering.

Workflow

  1. Pull sent mail (not received - sent is the signal of investment) and calendar events for the last 6 months. Batch the queries; state the window used.
  2. Filter hard before scoring. Drop: role inboxes (support@, noreply@), commercial senders, scheduling tools, anyone appearing only once. Personal relationships survive the filter; vendors do not.
  3. Score each remaining person on three axes:
    • Recency - days since last outbound contact
    • Frequency trend - this quarter's contact rate vs the prior two
    • Reciprocity - do they appear in both mail and calendar, do threads go both directions
  4. Surface three lists, hard-capped:
    • Drifting (max 5): high historical frequency, sharp recent drop. These are the ones worth acting on this week.
    • Steady (max 5): healthy cadence, no action needed - shown so the user trusts the scan.
    • Gone quiet (max 5): meaningful past contact, silent 90+ days.
  5. For each drifting contact, draft a one-line reopener grounded in the last real exchange (subject line or event title only - never quote message bodies back).

Output format

# Relationship Radar - <date>, window: <months>

## Drifting - act this week
- <name> - last contact <n> weeks ago, was <cadence> - opener: "<draft>"

## Gone quiet
- <name> - silent since <month>

## Steady
- <name>

Privacy rules (non-negotiable)

  • Process everything in-session; never write contact data to files unless the user explicitly asks for an export.
  • Never quote message bodies in output. Metadata only: names, dates, subjects, event titles.
  • Never send anything. Drafts are drafts; the user sends.

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