Meeting-Minutes
Meeting-Minutes是一款code方向的AI技能,核心价值是Generate concise, actionable meeting minutes for internal meetings,可用于解决开发者在code领域的实际问题,帮助用户提升效率、自动化重复任务或优化工作流。
Generate concise, actionable meeting minutes for internal meetings. Includes metadata, attendees, agenda, decisions, action items (owner + due date), and follow-up steps.
mkdir -p ./skills/meeting-minutes && curl -sfL https://raw.githubusercontent.com/github/awesome-copilot/main/skills/meeting-minutes/SKILL.md -o ./skills/meeting-minutes/SKILL.md Run in terminal / PowerShell. Requires curl (Unix) or PowerShell 5+ (Windows).
Skill Content
# Meeting Minutes Skill — Short Internal Meetings
Purpose / Overview
This Skill produces high-quality, consistent meeting minutes for internal meetings that are 60 minutes or shorter. Output is designed to be clear, actionable, and easy to convert into task trackers (e.g., GitHub Issues, Jira). The generated minutes prioritize decisions and action items so teams can move quickly from discussion to execution.
When to Use
Use this skill when:
- Internal syncs, standups, design reviews, triage, planning or ad-hoc meetings with short duration
- Situations that require a concise record of decisions, assigned action items, and follow-ups
- Creating a standardized minutes document from a live meeting, transcript, recording, or notes
---
Operational Workflow
Phase 1: Intake (before drafting)
- Obtain meeting metadata: title, date, start/end time (or duration), organizer, and intended audience.
- Confirm available inputs: agenda, slides, recording, transcript, or raw notes.
- If key details are missing, ask up to 3 clarifying questions before producing minutes (see "Discovery" below).
Phase 2: Capture (during / immediately after meeting)
- Record attendees and absentees.
- Capture brief notes per agenda item with time markers if available.
- Record explicit decisions, rationale summary (1–2 sentences), and action items (owner + due date).
Phase 3: Drafting
- Generate minutes following the **Strict Minutes Schema** (below).
- Ensure every action item includes owner, due date (or timeframe), and acceptance criteria when applicable.
- Mark unresolved issues or items requiring follow-up in the Parking Lot.
Phase 4: Review & Publish
- If possible, send draft to meeting organizer or a designated reviewer for quick verification (within 24 hours).
- Publish final minutes to the agreed channel (shared drive, repo, ticket, or email) and optionally create tasks in the team's tracker.
---
Discovery (required clarifying questions)
Before generating minutes, the agent **MUST** ask up to three clarifying questions if any of these are missing:
- What is the meeting title, date, start time (or duration), and organizer?
- Is there an agenda or transcript/recording to reference? If yes, please provide.
- Who should be assigned as the reviewer or approver for the minutes?
If the user responds "no transcript" or "no agenda," proceed but mark source material as "ad-hoc notes" and flag potential gaps.
---
Strict Minutes Schema (Output Structure)
You **MUST** produce meeting minutes following this exact structure. If information is unavailable, use `TBD` or `Unknown` and explain how to obtain it.
1. Metadata
- **Title**:
- **Date (YYYY-MM-DD)**:
- **Start Time (UTC)**:
- **End Time (UTC) or Duration**:
- **Organizer**:
- **Location / Virtual Link**:
- **Minutes Author** (agent or person):
- **Distribution List** (who receives the minutes):
2. Attendance
- **Present**: [list of names + roles]
- **Regrets / Absent**: [list]
- **Notetaker / Recorder**: [name or "agent"]
3. Agenda
Bullet list of agenda items, in order:
- Item 1: short title
- Item 2: short title
- ...
4. Summary
A concise one-paragraph summary (1–3 sentences) of the meeting's objective and high-level outcome.
5. Decisions Made
Each as a separate bullet:
- **Decision 1**: statement of decision.
- Who decided / approved: [name(s) or group]
- Rationale (1–2 sentences): brief reason.
- Effective date (if applicable): YYYY-MM-DD
- **Decision 2**: ...
6. Action Items
Table-style bullets; **must include owner and due date**:
- **[ID] Action**: short description
- **Owner**: Name (team)
- **Due**: YYYY-MM-DD or "ASAP" / timeframe
- **Acceptance Criteria**: (what completes this action)
- **Linked artifacts / tickets**: (optional URL or ticket id)
**Example:**
- [A1] Draft deployment runbook for feature X
- Owner: Alex (Engineering)
- Due: 2026-02-05
- Acceptance Criteria: runbook includes ste
🎯 Best For
- Developers scaffolding new projects
- Prototype builders
- Claude users
- GitHub Copilot users
- Software engineers
💡 Use Cases
- Bootstrapping React components
- Creating API route handlers
- Code quality improvement
- Best practice enforcement
📖 How to Use This Skill
- 1
Install the Skill
Copy the install command from the Terminal tab and run it. The SKILL.md file downloads to your local skills directory.
- 2
Load into Your AI Assistant
Open Claude or GitHub Copilot and reference the skill. Paste the SKILL.md content or use the system prompt tab.
- 3
Apply Meeting-Minutes to Your Work
Open your project in the AI assistant and ask it to apply the skill. Start with a small module to verify the output quality.
- 4
Review and Refine
Review AI suggestions before committing. Run tests, check for regressions, and iterate on the skill output.
❓ Frequently Asked Questions
Can I customize the generated output?
Yes — modify the skill's prompt instructions to match your project conventions and coding style.
Is Meeting-Minutes compatible with Cursor and VS Code?
Yes — this skill works with any AI coding assistant including Cursor, VS Code with Copilot, and JetBrains IDEs.
Do I need specific dependencies for Meeting-Minutes?
Check the install command and Works With section. Most code skills only require the AI assistant and your codebase.
How do I install Meeting-Minutes?
Copy the install command from the Terminal tab and run it. The skill downloads to ./skills/meeting-minutes/SKILL.md, ready to use.
Can I customize this skill for my team?
Absolutely. Edit the SKILL.md file to add team-specific instructions, examples, or workflows.
⚠️ Common Mistakes to Avoid
Using generated code without understanding
Understand what generated code does before shipping it to production.
Skipping validation
Always test AI-generated code changes, even for simple refactors.
Missing dependency updates
Check if the skill requires updated dependencies or new packages.