Relationship Status Summarizer logo

Relationship Status Summarizer

Community
latour-ai
relationship-status-summarizer

Surface where a professional relationship stands by pulling from Gmail — last touchpoint, what was discussed, open threads, commitments, and a suggested next move. Use whenever a user wants to re-engage someone, prep for outreach, or get a quick status check before reaching out. Trigger on "where do I stand with [Name]", "catch me up on my history with [Name]", "what's my relationship with [Name]", "when did I last talk to [Person]", "what was the last thing discussed with [Name]", "should I reach out to [Person]", "help me re-engage [Name]", "what do I owe [Person]", "any open threads with [Company]", "what's my history with [Name]", or any variation of wanting to understand a relationship's current state before making a move. Also trigger when the user mentions a person's name and asks about follow-ups, last contact, or relationship warmth. Designed for BD, fundraising, and IR professionals managing large networks who need a fast, honest read on where things stand.

Overview

Publisherlatour-ai
Repositoryskills
Skill namerelationship-status-summarizer
Stars
69
Forks
4
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by latour-ai on GitHub. Read the source before you install it.

Installation

Install the Relationship Status Summarizer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/latour-ai/skills/tree/main/relationship-status-summarizer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/latour-ai/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/relationship-status-summarizer .claude/skills/relationship-status-summarizer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Relationship Status Summarizer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Relationship Status Summarizer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Relationship Status Summarizer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Relationship Status Summarizer

Pull from Gmail to give the user an honest, fast read on where a specific relationship stands — and what to do next.

Why This Skill Exists

Managing a large professional network in BD, fundraising, or IR means dozens of relationships in various states of warmth, dormancy, or momentum. Before re-engaging someone — a prospective LP, a potential partner, an intro target — you want to know: When did we last talk? What was discussed? Did I leave anything open? Is it weird to reach out now? This skill answers those questions from the email record so the user can move quickly and confidently.

What This Skill Does Not Do

  • It only reads Gmail. It cannot check CRM records, calendar history, LinkedIn messages, or other communication channels unless those integrations are explicitly available.
  • It does not fabricate relationship history. If there are no emails with this person, say so clearly.
  • It does not ghost-write the outreach message — that is the intro-email-generator skill's job. This skill ends with a suggested next move, not a drafted email.
  • It cannot assess relationship quality beyond what the email record shows. A warm email thread does not guarantee a warm relationship — use judgment.

Inputs

The user provides at minimum:

  • A person's name, email address, or company name

Optionally helpful:

  • Context on why they're asking (re-engagement, LP meeting prep, warm intro, deal follow-up)
  • Approximate timeframe to search ("last year", "last 6 months")
  • The user's goal in re-engaging this person

If no timeframe is specified, default to searching the last 18 months.

Workflow

Step 1 — Search Gmail for relevant threads

Run targeted searches to surface all meaningful email history with this person. Use the Gmail connector tools for all email operations.

Primary search — by name or email:

  • Query: from:[name or email] OR to:[name or email]
  • maxResults: 50
  • newer_than: 18 months (or user-specified range)

Secondary search — by company (if name alone is ambiguous):

  • Query: [company name] -category:promotions -category:social
  • maxResults: 20
  • newer_than: 18 months

Deduplicate by thread ID. If the name is common and returns many unrelated threads, use company name or any additional context the user provided to filter.

Step 2 — Filter to signal threads

Discard threads that are clearly noise: newsletters, automated notifications, marketing emails, calendar accept/decline responses with no personal content, automated receipts, confirmations, DocuSign completions, and CC-only threads where neither party initiated anything meaningful.

Keep threads where either party wrote something substantive, there was a clear ask, commitment, or follow-through, the relationship was being actively developed (intros, meetings, deals, pitches), or there is an unanswered message from either side.

Step 3 — Read the surviving threads

For each surviving thread, read enough to understand what the conversation was about, what was asked or offered, whether it was resolved or left open, and the tone and warmth of the exchange.

Step 4 — Produce the relationship brief

Use this exact output structure:

## Relationship Brief: [Name] — [Title / Company if known]

### Last Contact
Date: [Most recent email date]
Direction: [You reached out / They reached out / Mutual]
Subject: [Subject line of most recent thread]
Summary: [1-2 sentences on what was discussed or exchanged]

### Relationship History
[3-6 bullet chronological summary of meaningful touchpoints]
- [Date] — [What happened and outcome]

### Open Threads
[List any unanswered emails, pending commitments, or explicitly flagged follow-ups.
If none: "No open threads identified."]

### Relationship Temperature
One-line honest read:
- **Warm** — Recent, engaged, mutual exchange
- **Cooling** — Last contact 6-12 months ago, ended well
- **Cold** — Last contact 12+ months ago, or ended without resolution
- **Never started** — No meaningful email history found

### Suggested Next Move
One specific, actionable recommendation. Not a drafted message — just the right move.

### Email Record Summary
[X threads found | Most recent: [date] | Oldest: [date] | Time since last contact: X months]

Tone and Judgment Principles

Be honest, not flattering. If the relationship is cold, say it's cold. If the user left something open and didn't follow through, flag it — that's the most useful thing you can surface.

Recency matters most. A warm thread from 3 years ago and nothing since is a cold relationship.

Direction signals intent. If the user has been doing all the reaching out, note that pattern explicitly.

Open threads are critical. An unanswered email is the single most important thing to surface — it shapes both the temperature and the next move.

No email history is a clear answer. Say so directly: "No meaningful email history found." Don't pad with speculation.

CC-only threads are weak signal. Only count direct, substantive exchange.

When the Person Is Ambiguous

If the name is common and returns multiple people, ask the user to clarify with an email address, company, or more context. Do not guess which person is meant.

Quality Checks

Before delivering, verify:

  • Threads cited are actually with the target person (not a different person with a similar name)
  • No invented history — every data point traces to an actual email
  • Relationship Temperature is calibrated to recency, not volume
  • Open threads are surfaced even if uncomfortable (especially if the user dropped the ball)
  • Suggested Next Move is specific to this relationship, not generic advice

Important Reminder

This brief is only as good as the email record. Relationships that live primarily in phone calls, LinkedIn, or in-person meetings will appear colder than they actually are. Flag this caveat when the email record is sparse but the user's context suggests the relationship may be richer than what's visible in Gmail.

Frequently asked questions

What does the Relationship Status Summarizer AI skill do?

Surface where a professional relationship stands by pulling from Gmail — last touchpoint, what was discussed, open threads, commitments, and a suggested next move. Use whenever a user wants to re-engage someone, prep for outreach, or get a quick status check before reaching out. Trigger on "where do I stand with [Name]", "catch me up on my history with [Name]", "what's my relationship with [Name]", "when did I last talk to [Person]", "what was the last thing discussed with [Name]", "should I reach out to [Person]", "help me re-engage [Name]", "what do I owe [Person]", "any open threads with...

Why use Relationship Status Summarizer on TypingMind?

Because you install it once and use it with any model. Relationship Status Summarizer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Relationship Status Summarizer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/latour-ai/skills/tree/main/relationship-status-summarizer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Relationship Status Summarizer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Relationship Status Summarizer?

As many as you like. As long as a model supports skills, you can use Relationship Status Summarizer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Relationship Status Summarizer AI skill free?

Yes. It is published on GitHub by latour-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇