Productivityv1.0.0By uristocratVerified

Meeting Memo

A recurring-meeting notes skill that writes against the operator's frozen section template (Commentary, Observations, To-Dos by default), carries forward unresolved action items from the prior meeting, and supports scheduled auto-run. Not a generic transcript summarizer: it earns its slot through the frozen template, cross-meeting carry-forward, and the discipline to flag rather than fabricate. Every action item traces to the transcript; missing owners are flagged as 'owner?' rather than guessed; no decisions are invented. Includes an eval contract with four self-tests covering owner flagging, carry-forward, completion detection, and the draft-not-send boundary.

meeting notesaction itemscarry forwardrecurring meetingsproductivity
Install

Simple install — no setup required

1

Download the skill file below

2

Add it to Claude — pick your platform:

Claude desktop app

  1. Open the Claude desktop app
  2. Go to Code, then Customize
  3. Click Create a new skill
  4. Upload the skill file you downloaded

claude.ai (web)

  1. Go to Customize, then Skills
  2. Click +, then Create a new skill
  3. Upload the skill file you downloaded
3

Say a trigger phrase to activate it

Download skill file

What this skill does

This is an overview of the skill from the site, not the skill's real instructions. The full SKILL.md Claude reads when this skill is active lives on GitHub at the pinned source below.

A recurring-meeting notes skill with structure that a generic chatbot prompt won’t give you. It writes against your team’s frozen section template — Commentary, Observations, To-Dos by default — so the output lands in the exact shape you circulate every time. It carries forward unresolved action items from the prior meeting automatically, deciding each prior to-do’s state (open, done, dropped, or superseded) from the new transcript rather than silently dropping things. It flags missing owners as “owner?” rather than assigning a name, and it does not invent decisions that were not in the transcript. Includes a built-in eval contract with four self-tests covering owner flagging, carry-forward, completion detection, and the draft-not-send boundary.

View full SKILL.md on GitHub