meeting-notes
Skill0 starsChanged 3 months agoMITView on GitHub
Turn notes or a transcript into decisions, action items with owners and deadlines, and a parking lot. Use when summarizing meetings, tracking decisions, or extracting action items.
55 other projects use a version of this.
Adopted by
Most recently taken up by
- t128n/skillstheir own version, first seen Nov 8, 2026
- desertcache/agent-ostheir own version, first seen Nov 1, 2026
- juliomrqz/skillstheir own version, first seen Nov 1, 2026
- AgnesAI-Labs/agnet-skills-cntheir own version, first seen Nov 1, 2026
- Works-HQ/ai-brain-starter-packtheir own version, first seen Nov 1, 2026
- Rome-1/obsidian-claude-startertheir own version, first seen Nov 1, 2026
Used with
Projects with it also use email-draft, status-report and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
yakatotechSkillemail-draft
Create business email drafts. Use when asked to draft emails
Also in 3 projects that use this
AnthropicSkillstatus-report
Generate a status report with KPIs, risks, and action items. Use when writing a weekly or monthly update for leadership, summarizing project health with green/yellow/red status, surfacing risks and decisions that need stakeholder attention, or turning a pile of project tracker activity into a readable narrative.
Also in 3 projects that use this
QuixiAISkillweekly-review
Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week
Also in 8 projects that use this
vijpatel7Skillcold-outreach
Write highly effective cold emails and LinkedIn messages to recruiters, hiring managers, founders, and engineers at target companies. Based on Ben Lang's proven cold outreach framework (Next Play). Use when the user wants to: (1) write a cold email to someone at a company they want to work for, (2) craft LinkedIn messages or InMail to recruiters or hiring managers, (3) reach out about unadvertised positions, (4) follow up on outreach or applications, (5) network with founders or executives for job opportunities, (6) prepare an outreach campaign to multiple companies. Triggers on: cold email, outreach, reach out to, contact recruiter, email founder, write to hiring manager, job email, networking email, LinkedIn message, InMail.
Also in 3 projects that use this
LangChainSkillweb-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research
Also in 4 projects that use this
jacobraskSkillcalendar
Interact with Apple Calendar via AppleScript. Use when the user asks to check calendar, view events, create events, manage schedule, find free time, or list calendars. Triggers include "my calendar", "my schedule", "calendar events", "create event", "add to calendar", "what's on my calendar", "free time", "available slots", "upcoming events", "today's events". Requires macOS with Calendar.app.
Also in 3 projects that use this
Other versions55 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 55
- mergisi/awesome-openclaw-agents★ 4.1ksame name
- shiwenwen/hope-agent★ 1.9ksame name
- claude-office-skills/skills★ 433same name
- zrosenfield/sharepoint-ai-skills★ 96same name
- duncan-buildroom/freeskills★ 65same name
- jezweb/vite-flare-starter★ 49same name
- nimadorostkar/Claude-Skills-collection★ 33same name
- charlie947/life-automation-skills★ 25same name
- arezous/pm-pilot★ 20same name
- codeApe-7/ai-agent-workflowGroup★ 18same name
45 more not listed
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 repository19 other files it gives its agents.
- book-writingSkill
- executive-summarySkill
- feedback-writingSkill
- grant-writingSkill
- historical-accuracySkill
- job-descriptionsSkill
- line-editingSkill
- longform-book-authorSkill
- marketing-copywriterSkill
- screenplay-writerSkill
- screenwritingSkill
- sop-writingSkill
- talk-writingSkill
- technical-docsSkill
- technical-writerSkill
- thread-to-articleSkill
- thread-to-blog-converterSkill
- translationSkill
- writing-tasteSkill
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 43 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 26
Document decisions made as unambiguous declarative statements:
- Distinctive: line 32
Every action item must have exactly ONE individual owner (shared ownership means zero ownership).
- Distinctive: line 33
Must include an explicit, deterministic due date (never "soon" or "next sprint"):
“Common” is measured: kept by at least 6 in 10 of the 43 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-notes
Core Philosophy
Dumping an unedited, 10-page raw automated audio transcription into Slack or Notion after a meeting is not helpful; it is an abdication of editorial responsibility. Raw transcripts are filled with conversational tangents, stuttering, and half-formed thoughts. High-impact meeting notes represent executive synthesis: extracting binding decisions, assigning clear action items with single accountable owners and due dates, capturing critical debate context, and shelving off-topic discussions in a parking lot.
4-Step Executive Meeting Synthesis Protocol
Step 1: Real-Time Listening & Signal Filtering
- Filter the 90% Noise:
- Ignore pleasantries, small talk, scheduling back-and-forths, and circular debates.
- Listen aggressively for trigger verbs: "We agreed that...", "I will own...", "The deadline is...", "We decided not to..."
Step 2: The Decision Ledger (What Was Decided)
- Binding Outcomes First:
- Document decisions made as unambiguous declarative statements:
- Decision: We will deprecate the v1 REST API on October 31, 2026.
- Decision: Approved $15,000 budget for Q3 security penetration test.
- Document decisions made as unambiguous declarative statements:
Step 3: The DRI Action Item Register (Who Does What by When)
- Directly Responsible Individual (DRI) Model:
- Every action item must have exactly ONE individual owner (shared ownership means zero ownership).
- Must include an explicit, deterministic due date (never "soon" or "next sprint"):
- Format:
[ ] [Action Verb + Deliverable] — @OwnerName (Due: YYYY-MM-DD) - Example:
[ ] Draft RFC for OAuth token exchange — @Sarah (Due: 2026-09-12)
- Format:
Step 4: Critical Context & The Parking Lot
- Key Debate Rationale:
- Capture why a decision was reached (the trade-offs considered):
- "Considered AWS DynamoDB vs PostgreSQL; chose Postgres due to team familiarity and lower transactional cost."
- Capture why a decision was reached (the trade-offs considered):
- The Parking Lot (Scope Defense):
- Record valuable off-topic ideas parked for future discussion so participants feel heard without derailing the meeting.
Deliverable Format: Executive Meeting Notes (MEETING-NOTES.md)
# Executive Meeting Notes: [Meeting Title]
*Date: [YYYY-MM-DD HH:MM] | Facilitator: [Name] | Note Taker: [Name]*
*Attendees: [Name 1], [Name 2], [Name 3] | Absent: [Name 4]*
## 1. Decisions Made
1. **Database Selection**: Standardized on PostgreSQL 16 for the billing microservice.
2. **Sprint Timeline**: Delayed Sprint 15 launch by 3 days to accommodate external SOC 2 audit.
3. **Budget Approval**: Approved $8,000 annual spend for Datadog APM expansion.
## 2. Action Items (DRI Register)
| Action Item / Deliverable | Single Owner (DRI) | Due Date | Status |
|---|---|---|---|
| Provision staging RDS Postgres cluster | @Dave (DevOps) | 2026-09-09 | Pending |
| Update OpenAPI specification with new `/billing` schema | @Elena (Backend) | 2026-09-11 | Pending |
| Schedule follow-up compliance sync with Legal | @Marcus (PM) | 2026-09-08 | Completed |
## 3. Key Discussion Rationale & Trade-offs
- **Postgres vs MongoDB**: MongoDB was evaluated for schema flexibility, but discarded due to lack of ACID transactional guarantees across multi-tier billing subscriptions.
- **Audit Preparedness**: Security team confirmed all IAM roles must be pruned before Friday.
## 4. Parking Lot (Deferred Topics)
- *Topic*: Migration from REST to gRPC for internal worker communication.
- *Next Action*: Deferred to Q4 architecture offsite.Worked Example: Executive Product Steering Committee Notes
- Meeting Duration: 60 minutes of high-stakes heated debate across 8 engineering leads.
- Deliverable: Condensed into a 1-page markdown memo distributed to
#leadershipwithin 15 minutes of call completion. - Outcome: 3 major strategic decisions ratified; 4 action items completed on time; zero confusion regarding owners.
Verification Checklist
- Notes published and distributed within 60 minutes of meeting completion.
- Decisions made are prominently listed at the top.
- Every action item has exactly one designated individual owner and an explicit date.
- Summary captures underlying rationale and trade-offs, not verbatim speech.
- Off-topic discussions are captured in a structured Parking Lot.
Anti-Patterns
- The Unedited Transcript: Pasting 15 pages of Otter.ai raw speech text into a channel.
- Multiple Owners: Writing "Action: Team will review API docs" (guarantees nobody does it).
- Vague Deadlines: Assigning action items with deadlines like "ASAP" or "ongoing".
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.

