agentleFS
slogsdonslogsdon/skills-vault-knowledge/skills/meeting/SKILL.md

meeting

Skill0 starsChanged 3 months agoMITView on GitHub

Turn a raw meeting / call / 1:1 transcript or notes into a structured Meetings note with key points and action items. Use when /meeting is invoked, when the user says "process this meeting", "clean up these notes", "extract action items from this", or pastes a raw conversation and asks for a summary. Reads from Obsidian Inbox by default; can take inline content. Do NOT use for general note-taking — use the obsidian skill or /log for that.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use commit and handoff.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SentrySkill

    commit

    Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't: use this for general note-taking — use /log for that.

    line 10
  2. Very specific:

    If the user named a note (e.g.

    line 15
  3. Very specific:

    If no name given, run ls "~/Library/Mobile Documents/iCloud~md~obsidian/Documents/Personal/Inbox/" and pick the most recently modified …

    line 16
  4. Distinctive:

    Read the full note content

    line 17
  5. Very specific:

    Run obsidian create name='Meetings/[original filename without .md]' silent with the following content:

    line 28
  6. Very specific:

    Run obsidian read file='PersonName' — if it errors or returns empty, the note doesn't exist

    line 47
  7. Very specific:

    If missing, run obsidian create name='People/PersonName' silent with this stub:

    line 48
  8. Very specific:

    Delete the raw note from Inbox/ using bash (obsidian CLI has no delete command): rm "~/Library/Mobile …

    line 68
  9. Distinctive:

    Default: delete unless user says otherwise

    line 71

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “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

Skill: /meeting

Process a raw Inbox note into a structured Meetings note with key points, actions, and a Person stub — the Inbox item is deleted (or archived) after.

Don't: use this for general note-taking — use /log for that. Don't archive instead of deleting unless Shane says so — default is delete.

Steps

  1. Find the raw note
    • If the user named a note (e.g. "Chat with Sean"), run: obsidian search query='Chat with Sean' to confirm it exists, then obsidian read file='Chat with Sean'
    • If no name given, run ls "~/Library/Mobile Documents/iCloud~md~obsidian/Documents/Personal/Inbox/" and pick the most recently modified non-fixture file, then obsidian read file='Note Name' (strip .md)
    • Read the full note content
  2. Extract structured content
    • Identify the other person(s) in the conversation
    • Extract key points: meaningful decisions, context shared, topics discussed — one tight bullet per point, no filler
    • Separate action items into two buckets:
      • Shane's actions (owner implied)
      • Their actions (prefix with PersonName:)
  3. Write the processed note

    • Determine the date from the filename or content (format: YYYY-MM-DD)
    • Run obsidian create name='Meetings/[original filename without .md]' silent with the following content:
    ---
    date: YYYY-MM-DD
    people: [[People/PersonName]]
    ---
    
    # [Title] — [Month Day]
    
    ## Key Points
    - (bullet per meaningful point, concise)
    
    ## Actions
    - [ ] (Shane's action items)
    - [ ] PersonName: (their action items)
  4. Check/create Person note

    • Run obsidian read file='PersonName' — if it errors or returns empty, the note doesn't exist
    • If missing, run obsidian create name='People/PersonName' silent with this stub:
    ---
    type: person
    role: 
    ---
    
    # PersonName
    
    ## Context
    - 
    
    ## Preferences & Working Style
    -
    
    ## Related
  5. Handle the raw Inbox note
    • Delete the raw note from Inbox/ using bash (obsidian CLI has no delete command): rm "~/Library/Mobile Documents/iCloud~md~obsidian/Documents/Personal/Inbox/[filename].md"
    • Or move to Archive/ if user prefers to keep it
    • Default: delete unless user says otherwise
  6. Commit vault changes
    VAULT="$HOME/Library/Mobile Documents/iCloud~md~obsidian/Documents/Personal"
    git -C "$VAULT" add '<the note paths you wrote>' && git -C "$VAULT" commit -m "docs: process meeting note [filename]"
  7. Confirm
    • Tell Shane what was written and where
    • Surface any action items that need immediate attention

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.