vault-prep
Skill179 starsChanged 8 months agoMITView on GitHub
Generate a pre-meeting agenda with context gathered from the knowledge base
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- elixir-expertSkill
- find-skillsSkill
- modern-cssSkill
- vault-auditSkill
- vault-checkinSkill
- vault-dashboardSkill
- vault-groomSkill
- vault-ingestSkill
- vault-meetingSkill
- vault-okrSkill
- vault-streamSkill
- vault-updateSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Create or update a meeting prep file with topics and auto-gathered context.
- Distinctive: line 24
If not: CREATE MODE — gather full context and create new prep
- Distinctive: line 50
Check for duplicate topics across contributors — note "(Also raised by {other person})" if similar.
- Distinctive: line 54
CREATE: Topics added, context gathered (follow-ups count, async updates, at-risk items) APPEND: Topics added, existing agenda summary, …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create or update a meeting prep file with topics and auto-gathered context.
Identify Contributor
Who is adding topics? Look for @mentions or ask.
Check for Existing Prep
vault_search(query: "prep", entry_type: "meeting") filtered to today's date.
- If exists: APPEND MODE — add this person's topics to the existing prep
- If not: CREATE MODE — gather full context and create new prep
Gather Context (CREATE MODE only)
- Recent meetings:
vault_search(query: "*", entry_type: "meeting")last 3- Extract discussion topics, open action items, decisions
- Open follow-ups:
vault_kanban(action: "list")filtered to items with meeting sources - Recent checkins:
vault_search(query: "*", entry_type: "checkin")since last meeting- Summarize as "async updates" — no need to rehash in the meeting
- At-risk OKRs:
vault_search(query: "*", tags: ["okr"])— check frontmatter for status - Upcoming milestones:
vault_search(query: "milestone", tags: ["in-progress"])
Parse Topics
From user input, extract:
- Topics they want to discuss
- Decisions that need to be made
- Questions they have
Create/Update Entry
CREATE: vault_create_entry(entry_type: "meeting", ...) with prep content, include prep_generated: true and contributors: ["{person}"] in extra_frontmatter
APPEND: vault_update_entry(append: "{person}'s topics:\n- [ ] Topic 1\n- [ ] Topic 2")
Also update contributors list in frontmatter.
Check for duplicate topics across contributors — note "(Also raised by {other person})" if similar.
Report
CREATE: Topics added, context gathered (follow-ups count, async updates, at-risk items) APPEND: Topics added, existing agenda summary, current contributors list
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
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.

