From ai-brain-starter
Extracts action items from a meeting note and adds them to a to-do file, separating your tasks from others'. Invoke via /meeting-todos.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-brain-starter:meeting-todos [date like 2026-04-09, or meeting title keyword — omit for most recent][date like 2026-04-09, or meeting title keyword — omit for most recent]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
After a meeting, pull action items from the transcript/notes and update your to-do file.
After a meeting, pull action items from the transcript/notes and update your to-do file.
/meeting-todos — optionally followed by a meeting title or date, e.g.:
/meeting-todos → uses the most recent meeting note/meeting-todos 2026-04-09 → finds meeting from that date/meeting-todos Team Sync → finds meeting matching that titleRun this first, before searching for the meeting note. A fresh-install vault may not have a to-do file yet, and you don't want to do all the extraction work only to discover at Step 5 that there's no destination.
Glob or Read per location, stop on the first hit):
🏠 Home/✅ Get to-do.md (canonical layout)Home/✅ Get to-do.md✅ Get to-do.md (vault root)Home/TODO.md / TODO.md / tasks.mdCLAUDE.md for a vault-map / to-do location hint. If the hint resolves to an existing file, use it and proceed to Step 1.I don't see a to-do file in your vault. Want me to create
🏠 Home/✅ Get to-do.mdwith a basic structure (frontmatter + Inbox section) so the meeting items have somewhere to land? You can move or rename it later.
YYYY-MM-DD with today's date in both places):
---
type: todo
created: YYYY-MM-DD
updated: YYYY-MM-DD
---
# To-do
## Inbox
Tell the user where you put it, then proceed to Step 1./meeting-todos needs a destination file and ask them to create one (or point you at where their tasks live) before re-running.Cache the resolved to-do path mentally for Step 5 — don't re-search the filesystem there.
Check these locations for the most recent (or matching) meeting note:
[VAULT]/Meeting Notes/ (or wherever meeting notes live in this vault)If the user specified a date or title, find the matching file. If no argument, use the most recently modified file.
Tell the user which file you found before proceeding.
Read the full meeting note. It may contain:
From the content, identify:
Your tasks — anything where:
Others' tasks — anything assigned to someone else — list these separately for visibility but DO NOT add to your to-do.
Decisions pending — anything that was left unresolved and needs a meeting or decision soon.
Show the user a preview:
## From: [Meeting Name] — [Date]
### Your action items (going to to-do):
- [ ] [task 1]
- [ ] [task 2]
### Others' tasks (not going to to-do — just FYI):
- [Name]: [task]
### Open questions / decisions pending:
- [item]
Shall I add these to your to-do? (yes/no, or edit first)
Wait for confirmation before writing.
Use the to-do file path resolved (or created) in Step 0. Do NOT re-search the filesystem — you already did that.
Rules:
## 📋 From [Meeting Name] — [Date]
- [ ] [task 1]
- [ ] [task 2]
Place it after ## 🔥 Urgent / Active if the tasks are urgent, or at the bottom if they're not.
updated: field in frontmatter to today's date if it existsIf the meeting note did NOT already have a structured summary, add one at the top of the meeting file (above the Transcript section):
## Summary
**Date:** [date]
**Attendees:** [names]
**Key decisions:** [bullet points]
**Your action items:** [bullet points]
**Others' action items:** [bullet points]
**Next steps:** [bullet points]
Ask the user if they want this added before writing.
npx claudepluginhub mycelium-hq/ai-brain-starter --plugin ai-brain-starterExtracts action items from non-meeting notes (class notes, book notes, podcast transcripts) and routes them to the correct to-do file with wikilinks and owner tags.
Writes structured meeting summaries with action items from notes, transcripts, or agendas. Enriches context using project files and automates action items via discovered tools.
Processes raw meeting transcripts into structured Obsidian notes with YAML frontmatter, action items, summary, and formatted transcript. Useful for Granola transcripts or direct pastes.