meeting-agenda
Skill4 starsChanged 4 months agoMITView on GitHub
Invoked only by explicit /meeting-agenda right before the team's recurring meetings (e.g., Mon/Thu) to scan the **entire lore vault** and draft the agenda in the PM role — an extra meeting separate from daily/retro; **only items needing discussion or decision become agenda items** (not plain progress reports); this channel = this project only.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- jieun994/zinis_claude_skillstheir own version, first seen Nov 1, 2026
- tkcostello/pastor-ai-skillstheir own version, first seen Aug 27, 2026
- talgacapri/pm-ostheir own version, first seen May 23, 2026
- nbirkner/digital-braintheir own version, first seen Apr 12, 2026
- nandanosql/all_in_one_pm_skillstheir own version, first seen Feb 28, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- tkcostello/pastor-ai-skills★ 53same name
- jieun994/zinis_claude_skills★ 1same name
- nandanosql/all_in_one_pm_skills★ 1same name
- nbirkner/digital-brain★ 0same name
- talgacapri/pm-os★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- backlog-proposalSkill
- backlog-updateSkill
- conflict-detectionSkill
- daily-scrumSkill
- impact-analysisSkill
- loremaster-setupSkill
- refine-wikiSkill
- resolve-conflictsSkill
- sprint-planningSkill
- sprint-retroSkill
- wiki-qaSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Treat the god-nodes in graphify-out/GRAPH_REPORT.md (highly connected core concepts = large ripple effect if changed, likely contentious) …
- Distinctive: line 37
Only what needs "discussion/decision", not "reporting".
- Distinctive: line 40
Put the previous meeting's incomplete actions at the very top.
- Distinctive: line 53
If team members have not responded by a set time (e.g., 30 minutes before the meeting), post the draft with vault items only + note "raise …
“Common” is measured: kept by at least 6 in 10 of the 3 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.
Files
Regular Meeting Agenda Generation (PM)
Distill "what the team must judge and decide together" into agenda items. This is not plain progress reporting (that is the daily's job).
Behavior
- Extract agenda candidates from the entire lore vault (structured via graphify): the meeting covers the whole project, so look broadly — but do not read everything wholesale; narrow down the "discussion material" with graphify first:
- Treat the god-nodes in
graphify-out/GRAPH_REPORT.md(highly connected core concepts = large ripple effect if changed, likely contentious) and the surprising connections (unexpected cross-links = issues the team may miss) as first-priority agenda candidates. - Open conflicts in
conflicts/(the meeting = the venue for verdicts), unresolved backlog items, incomplete actions from the previous meeting. - Confirm each candidate concept's connections and evidence with
graphify explain "<concept>"and read only those sources. If graph.json is missing, fall back towiki/index.md+ a direct scan ofwiki/.
- Treat the god-nodes in
- Ask the PM-role team member and wait for the response:
- Show the vault-extracted candidates first, then ask (reduces duplicate input): "Anything to include in today's agenda? (beyond the automatic vault extraction — e.g., mentor meetings, external schedules, discussion topics not yet in the vault)"
- Do not finalize the agenda without a response.
- Merge: vault agenda items + team-member additions.
Agenda Generation Rules
- Only what needs "discussion/decision", not "reporting". Exclude areas that are going smoothly.
- Each item carries why it must be discussed now (evidence) + source links.
- Open conflicts must be included (the meeting = the venue for verdicts).
- Put the previous meeting's incomplete actions at the very top.
- Priority order (so the bottom can be cut if time runs short).
- Do not pre-draw conclusions. Phrase items as discussion questions.
Agenda Source Labels
[vault]auto-extracted item with evidence links.[PM added]direct team-member input (mentor meetings, etc.). Sources are not enforced.
Output & Scope
- Post the agenda draft to Slack (items + evidence + sources). Post-meeting decisions are recorded by a human as meeting notes in
raw/→ the normal pipeline. - No automatic meeting minutes. The scope ends at agenda "generation".
Fallback (operational adjustment)
- If team members have not responded by a set time (e.g., 30 minutes before the meeting), post the draft with vault items only + note "raise any additional items at the meeting".
Isolation
- This channel = this project only. No mentioning or referencing other projects.
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.

