meeting-brief-graph
Skill1 starsChanged 4 months agoApache-2.0View on GitHub
Before each meeting, a 200-word brief on the attendees from your own memory — every sentence cites the chunk it rests on, unknown names are reported, nothing is invented.
In this repository64 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- board-workerSkill
- board-triage-specifierSkill
- create-a-skillSkill
- execdesk-action-board-prepSkill
- execdesk-action-competitor-monitorSkill
- execdesk-action-competitor-positioningSkill
- execdesk-action-content-calendarSkill
- execdesk-action-decision-frameworkSkill
- execdesk-action-growth-hack-runnerSkill
- execdesk-action-icp-profileSkill
- execdesk-action-quarterly-goals-reviewSkill
- execdesk-action-twitter-thread-drafterSkill
- execdesk-action-weekly-briefSkill
- execdesk-ceoSkill
- execdesk-chief-of-staffSkill
- execdesk-cmoSkill
- think-deepSkill
- docker-compose-devSkill
- calendar-hold-approvalSkill
- chuck-norrisSkill
- email-send-approvalSkill
- graph-ask-demoSkill
- inbox-and-agendaSkill
- multi-mcp-testSkill
- schedule-badge-proofSkill
- stopping-point-testSkill
- turn-log-smokeSkill
- code-review-templateSkill
- custom-skill-templateSkill
- daily-research-briefSkill
- pr-review-pipelineSkill
- research-analysis-templateSkill
- ship-a-featureSkill
- autonomous-planSkill
- browser-toolsSkill
- code-reviewSkill
- deep-thinkingSkill
- first-skillSkill
- helloSkill
- implementation-planningSkill
- install-mcp-serverSkill
- masterySkill
- mcp-builderSkill
- mcp-installerSkill
- morning-briefSkill
- new-user-walkthroughSkill
- oauth-authenticationSkill
- onboardingSkill
- parallel-code-analysisSkill
- project-wizardSkill
- qa-reportSkill
- qa-testingSkill
- regression-testSkill
- self-improveSkill
- self-learningSkill
- skill-developmentSkill
- social-media-marketingSkill
- soulSkill
- The first 60 shown.
The file
Files
Meeting brief (graph form)
PLAN-PEOPLE-PAGES P2 — the graph form of the meeting brief. recipe.txt is the
source; actions.json is vodou-core recipe compile recipe.txt and is not edited
by hand.
What it does, in order:
- calendar — the next two hours of the primary Google calendar
(
{{NOW}}→{{NOW_PLUS_2H}}). - who — every attendee and organizer name is looked up in your memory with
vodou-memory.entities_lookup. Read-only: a name memory does not know comes back as no memory of, and no entity is ever created from an invite. - brief — at most 200 words. Every factual sentence ends with the
[chunk:<id>]it rests on; unknown attendees get a no memory of line; an empty window is exactlyNOTHING_TO_REPORT. - check —
has_source, in a fresh context: a brief with an unattributed claim line is blocked.
There is no ask me:. Nothing in this graph sends; the reply is delivered by
the skill's delivery mode, and a NOTHING_TO_REPORT reply is kept in the
console and never forwarded to a channel.
The scheduled twin. On 2026-09-10 the scheduler runs graph skills through
brain /skill with no delivery and no verdict beyond exit status, so the copy
that runs on the clock is the console skill meeting-brief (skills_meta,
delivery via delivery_mode, cron */30 12-22 * * 1-5 — the scheduler's
clock is UTC; that is weekdays 08:00–18:00 EDT). Its prompt asks for the same
shape, and the scheduler grades every reply with
memory::entities::grade_citations: zero citations after consulting memory is
could_not / no_sources, a cited chunk that does not exist is
degraded / partial_sources, NOTHING_TO_REPORT is did_the_job /
nothing_to_report. Flow 16 reads those grades.
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.

