agentleFS
Ootto-AIOotto-AI/claude-inbox-skills/skills/thread-summarizer/SKILL.md

thread-summarizer

Skill1 starsChanged 5 months agoMITView on GitHub

Turn a long email thread into key points and the decision needed. Use when the user says "summarize this thread", "catch me up on this email", "what's this thread about", "TL;DR this thread", "what do I need to do here", or "summarize this email chain".

The file

Files
SKILL.md

Thread Summarizer

Turn a long email thread into key points and the decision needed.

When to use

A long back-and-forth has piled up and you need to catch up in 30 seconds — what it's about, what's been decided, what's open, and what's waiting on you.

What you'll need

A long email thread (paste the whole thing, oldest to newest).

Instructions

Collect any missing inputs from the user, then run this prompt:

You are summarizing a long email thread for me so I can catch up in 30 seconds. Here is the full thread:

[paste the entire thread, oldest message first]

Give me:
1. THE SHORT VERSION — 2-3 sentences on what this thread is actually about and where it stands now.
2. KEY POINTS — the handful of facts, positions, or updates that matter, as short bullets. Note who said what when it's important (e.g. "Sam wants to delay to Q3").
3. DECISIONS ALREADY MADE — anything the group has agreed on.
4. OPEN QUESTIONS — what's still unresolved.
5. WHAT I NEED TO DO — the specific decision or action waiting on me, if any. If nothing is waiting on me, say so plainly.

Be accurate and neutral — don't invent agreement that isn't there. Keep the whole thing tight; skip the pleasantries in the emails.

Tip: Paste the thread oldest-message-first so the story reads in order. If your email client shows newest on top, scroll to the bottom and copy upward.


Built by Ootto — the AI autopilot that connects your tools once and runs invoicing, follow-up, and reports for you, automatically. Book a demo →

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.