meeting-brief
Skill2 starsChanged 2 months agoMITView on GitHub
Prepare a focused brief for an upcoming meeting, or turn supplied meeting notes into a debrief with supported decisions and actions. Works from conversation, files, or available connected sources without requiring a specific app.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- Nomanriaz786/claude-consulting-teamtheir own version, first seen Nov 1, 2026
- microsoft/aibast-agents-librarytheir own version, first seen Oct 13, 2026
- thefiredev-cloud/meshvault-harnesstheir own version, first seen Oct 13, 2026
- marks97/meeting-brieftheir own version, first seen Oct 9, 2026
- youdcode/open-companytheir own version, first seen Sep 21, 2026
- thefiredev-cloud/meshvault-skills-startertheir own version, first seen Jul 22, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- microsoft/aibast-agents-library★ 8same name
- youdcode/open-company★ 2same name
- Nomanriaz786/claude-consulting-team★ 1same name
- marks97/meeting-brief★ 0same name
- thefiredev-cloud/meshvault-harness★ 0same name
- thefiredev-cloud/meshvault-skills-starter★ 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 repository18 other files it gives its agents.
- check-my-analysisSkill
- clean-handoffSkill
- clean-upSkill
- decision-coachSkill
- design-system-fitSkill
- feedback-to-findingsSkill
- form-flow-fixerSkill
- gameplanSkill
- knowledge-interviewSkill
- measure-successSkill
- motion-resilienceSkill
- practice-coachSkill
- proposal-reviewerSkill
- reconcile-reportsSkill
- research-briefSkill
- simplify-reportSkill
- ui-state-completenessSkill
- ui-stress-testSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
3
Distinctive
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 14
Read the relevant supplied sources first.
- Distinctive: line 24
If preparing both an internal brief and an attendee-facing agenda, keep private strategy and candid assessments out of the shared version.
- Distinctive: line 36
Default to a concise inline brief.
“Common” is measured: kept by at least 6 in 10 of the 6 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
Meeting brief
Prepare something the user can use during the actual conversation. For a completed meeting, accurately capture what happened and what was committed.
Establish the mode and context
Distinguish upcoming-meeting preparation from a completed-meeting debrief. Use the user's stated purpose, attendees, available time, and materials. Ask only for missing details that materially affect the brief. An imminent meeting with sparse context should get a useful short brief with visible unknowns.
Read the relevant supplied sources first. Retrieve additional authorized context when available and useful; do not require an account connection when supplied materials suffice. Note stale or conflicting context. Use external research only when it changes the conversation, not to pad the brief.
Prepare the conversation
Organize around the desired outcome: a decision, understanding, feedback, relationship, or plan. Adapt the content accordingly rather than treating every meeting as a decision gate.
Usually include the objective, essential context, a small set of prioritized questions or agenda items, and a useful close. Fit the agenda to the available time. Put optional background after the material needed in the meeting.
For important questions, identify the useful answer or signal to listen for and a follow-up when it would change the discussion. Do not script the other person's beliefs or invent their interests. Separate verified context, assumptions, and suggested talking points.
If preparing both an internal brief and an attendee-facing agenda, keep private strategy and candid assessments out of the shared version. Assign agenda owners only when supported; otherwise suggest them explicitly.
Debrief from evidence
Separate confirmed decisions, proposals, unresolved questions, and actions. Attach source locations or short supporting excerpts where ambiguity matters. A suggestion is not an agreement, and an inferred next step is not a commitment.
Record owners and due dates only when the notes support them. Mark missing details as unassigned or unspecified instead of guessing. Preserve conflicting accounts and distinguish a changed decision from an unresolved disagreement. Resolve relative dates only when the meeting date and relevant context are known.
Draft follow-up language when requested or useful, clearly distinguishing it from a sent message. Do not create tasks, invitations, shared pages, or outbound messages unless the user has authorized those actions. Existing authorization need not be requested again.
Finish
Default to a concise inline brief. Use the requested file or destination when supplied. Check that the brief fits its purpose, important uncertainty remains visible, and every reported decision or commitment has support. Do not manufacture action items to fill a template.
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.

