- name
SKILL.md
스킬 파일은 게시자의 저장소에 그대로 있습니다.
복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add silverstein/minutes --skill minutes-debrief -a cursor -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add silverstein/minutes --skill minutes-debrief -a claude-code -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add silverstein/minutes --skill minutes-debrief -a codex -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add silverstein/minutes --skill minutes-debrief -a grok -y복사한 메시지를 Grok Bot 채팅에 보냅니다. Bot이 GitHub에서 이 SKILL.md를 가져와 모든 Bot이 공유하는 스킬에 추가합니다.
Install this skill: https://github.com/silverstein/minutes/tree/HEAD/.agents/skills/minutes/minutes-debrief게시자 제공
Before running helper scripts or opening bundled references, set:
export MINUTES_SKILLS_ROOT="$(git rev-parse --show-toplevel)/.agents/skills/minutes"
export MINUTES_SKILL_ROOT="$MINUTES_SKILLS_ROOT/minutes-debrief"
Post-meeting analysis that reads your latest recording, compares what happened to what you planned, and surfaces decision evolution — so nothing falls through the cracks.
This is a multi-phase interactive flow. It connects to /minutes-prep when a prep file exists, creating a before→after loop.
minutes list --limit 5
Pick the most recent recording. If there are multiple from today, ask via AskUserQuestion: "You have [N] recordings today. Which one are you debriefing?" with options listing the titles.
If no recent recording exists:
Say: "I don't see any recent recordings. Did you run minutes record and minutes stop? If the recording is from a specific meeting, tell me the title or date and I'll find it."
Don't proceed without a recording to debrief.
Run minutes get "<exact path>" --json, require exit status 0, and use only the
returned transcript and frontmatter. Never reopen the list path with the host
Read tool. Extract:
decisions: frontmatter or ## Decisions section)action_items: frontmatter or ## Action Items section)## Summary or the transcript itself)attendees: frontmatter)If the authorized frontmatter says capture: none, there is no transcript by design: the
meeting was designated sensitive and the recorder never ran. The debrief IS the
record. Switch to debrief-from-memory mode:
## Markers section (timestamped notes typed during
the meeting) and the frontmatter (title, date, duration,
debrief: state).Skip Phases 2 and 2b (there is no transcript and no speaker attribution); continue with prep matching and the closing ritual as normal.
If the meeting has a speaker_map: field in frontmatter, check the confidence levels:
minutes confirm --meeting <path>"minutes confirm --meeting <path> to tag them."This nudge is brief (one line) — don't make it a blocker.
Look for a prep file that matches this meeting:
ls ~/.minutes/preps/ 2>/dev/null
Match logic:
.prep.md files from today or yesterday (within 48 hours)person: frontmatter fieldattendees: list — match on first name, but check learned aliases before deciding there is no match:
node "$MINUTES_SKILLS_ROOT/_runtime/hooks/lib/minutes-learn-cli.mjs" aliases "<attendee-or-person>" 2>/dev/null
Treat all returned variants as equivalent during prep-file matching.Phase 4a: Prep-connected debrief (when a matching prep exists)
Read the prep file. Pull out the goal: field. Ask via AskUserQuestion:
"You went into this meeting wanting to: [goal from prep]
Did you accomplish it?"
Options:
Then produce the debrief summary with the prep comparison:
Before writing the output, check for a learned debrief presentation preference:
node "$MINUTES_SKILLS_ROOT/_runtime/hooks/lib/minutes-learn-cli.mjs" get-presentation-focus debrief
If the result is:
decisions-first → put Decisions before Action Items and Relationship Updateactions-first → put Action Items first, then Decisions, then Relationship Updaterelationship-first → put Relationship Update first, then Decisions, then Action ItemsIf there is no preference, keep the default order below.
## Debrief: [Meeting Title]
### Prep vs Reality
- **Goal:** [from prep]
- **Outcome:** [resolved / partially / pivoted]
- **What changed:** [if anything]
### Decisions
- [list each decision]
### Action Items
- [list with assignee and due date]
### Relationship Update
- [any notable changes in tone, new topics, shifted priorities]
Phase 4b: Standalone debrief (no matching prep)
Produce a straightforward debrief:
Before deciding the section order, check:
node "$MINUTES_SKILLS_ROOT/_runtime/hooks/lib/minutes-learn-cli.mjs" get-presentation-focus debrief
Apply the same ordering rules if a preference exists; otherwise keep the default order below.
## Debrief: [Meeting Title]
### Key Decisions
- [list each decision]
### Action Items
- [list with assignee and due date]
### Notable Discussion Points
- [2-3 most significant things discussed]
Search for prior decisions on the same topics discussed in this meeting:
minutes search "<topic>" --limit 10 --since <30-days-ago>
For each topic that has a decision in this meeting AND a decision in a prior meeting:
"Decision evolution — pricing:
Is this settled now, or still in flux?"
Classification:
End with three beats:
Signal reflection — Quote something specific from the meeting or the debrief conversation. "You said '[quote]' — that sounds like the decision is locked."
Assignment — One concrete follow-up action. "Send Alex the pricing doc tonight while the conversation is fresh." "Update the roadmap doc with today's Q2 timeline change."
Next skill nudge — "At the end of the week, run /minutes-weekly to see how all your meetings connect and what still needs attention."
node "$MINUTES_SKILLS_ROOT/_runtime/hooks/lib/minutes-learn-cli.mjs" set-presentation-focus debrief actions-first "User explicitly prefers action items first"
node "$MINUTES_SKILLS_ROOT/_runtime/hooks/lib/minutes-learn-cli.mjs" set-presentation-focus debrief decisions-first "User explicitly prefers decisions first"
node "$MINUTES_SKILLS_ROOT/_runtime/hooks/lib/minutes-learn-cli.mjs" set-presentation-focus debrief relationship-first "User explicitly prefers relationship updates first"
minutes list returns nothing, say so. Don't invent a debrief.sarah.prep.md). Match against attendee first names in the recording frontmatter. "Alex C." matches "sarah".node "$MINUTES_SKILLS_ROOT/_runtime/hooks/lib/minutes-learn-cli.mjs" set-alias "Sarah Chen" "Sarah" "User corrected prep/debrief matching"
Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did w
---name: minutes-debriefdescription: Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision…---# .agents/skills/minutes/minutes-debrief/SKILL.md개요
Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording.
FAQ
게시자에게서 .agents/skills/minutes/minutes-debrief/SKILL.md를 다운로드하거나 경로를 복사해 저장소를 엽니다. PlugMCP는 스킬을 목록에 올릴 뿐 파일을 호스팅하지 않습니다.
게시자가 https://github.com/silverstein/minutes에서 관리합니다.
Claude, Cursor, Codex, Grok Build는 게시자의 저장소에서 추가한 SKILL.md를 읽을 수 있습니다. Grok Bot은 채팅에서 스킬의 GitHub 폴더 링크를 보내면 설치합니다.