
meeting-record-system
Record and manage meeting notes with intelligence. Organizes meeting documentation with action items, decisions, and follow-ups.
- Installs
- 135
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/qodex-ai/ai-agent-skills --skill meeting-record-system- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads meeting-record-system automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Meeting Intelligence
Prepares you for meetings by gathering context from Notion, enriching it with Claude research, and creating comprehensive meeting materials. Generates both an internal pre-read for attendees and an external-facing agenda for the meeting itself.
Quick Start
When asked to prep for a meeting:
- Gather Notion context: Use
Notion:notion-searchto find related pages - Fetch details: Use
Notion:notion-fetchto read relevant content - Enrich with research: Use Claude's knowledge to add context, industry insights, or best practices
- Create internal pre-read: Use
Notion:notion-create-pagesfor background context document (for attendees) - Create external agenda: Use
Notion:notion-create-pagesfor meeting agenda (shared with all participants) - Link resources: Connect both docs to related projects and each other
Meeting Prep Workflow
Step 1: Understand meeting context
Collect meeting details:
- Meeting topic/title
- Attendees (internal team + external participants)
- Meeting purpose (decision, brainstorm, status update, customer demo, etc.)
- Meeting type (internal only vs. external participants)
- Related project/initiative
- Specific topics to cover
Step 2: Search for Notion context
Use Notion:notion-search to find:
- Project pages related to meeting topic
- Previous meeting notes
- Specifications or design docs
- Related tasks or issues
- Recent updates or reports
- Customer/partner information (if applicable)
Search strategies:
- Topic-based: "mobile app redesign"
- Project-scoped: search within project teamspace
- Attendee-created: filter by created_by_user_ids
- Recent updates: use created_date_range filters
Step 3: Fetch and analyze Notion content
For each relevant page:
1. Fetch with Notion:notion-fetch
2. Extract key information:
- Project status and timeline
- Recent decisions and updates
- Open questions or blockers
- Relevant metrics or data
- Action items from previous meetings
3. Note gaps in information
Step 4: Enrich with Claude research
Beyond Notion context, add value through:
For technical meetings:
- Explain complex concepts for broader audience
- Summarize industry best practices
- Provide competitive context
- Suggest discussion frameworks
For customer meetings:
- Research company background (if public info)
- Industry trends relevant to discussion
- Common pain points in their sector
- Best practices for similar customers
For decision meetings:
- Decision-making frameworks
- Risk analysis patterns
- Trade-off considerations
- Implementation best practices
Note: Use general knowledge only - don't fabricate specific facts
Step 5: Create internal pre-read
Use Notion:notion-create-pages for internal doc:
Title: "[Meeting Topic] - Pre-Read (Internal)"
Content structure:
- **Meeting Overview**: Date, time, attendees, purpose
- **Background Context**:
- What this meeting is about (2-3 sentences)
- Why it matters (business context)
- Links to related Notion pages
- **Current Status**:
- Where we are now (from Notion content)
- Recent updates and progress
- Key metrics or data
- **Context & Insights** (from Claude research):
- Industry context or best practices
- Relevant considerations
- Potential approaches to discuss
- **Key Discussion Points**:
- Topics that need airtime
- Open questions to resolve
- Decisions required
- **What We Need from This Meeting**:
- Expected outcomes
- Decisions to make
- Next steps to define
Audience: Internal attendees only
Purpose: Give team full context and alignment before meeting
Step 6: Create external agenda
Use Notion:notion-create-pages for meeting doc:
Title: "[Meeting Topic] - Agenda"
Content structure:
- **Meeting Details**: Date, time, attendees
- **Objective**: Clear meeting goal (1-2 sentences)
- **Agenda Items** (with time allocations):
1. Topic 1 (10 min)
2. Topic 2 (20 min)
3. Topic 3 (15 min)
- **Discussion Topics**:
- Key items to cover
- Questions to answer
- **Decisions Needed**:
- Clear decision points
- **Action Items**:
- (To be filled during meeting)
- **Related Resources**:
- Links to relevant pages
- Link to pre-read document
Audience: All participants (internal + external)
Purpose: Structure the meeting, keep it on track
Tone: Professional, focused, clear
See reference/template-selection-guide.md for full templates.
Step 7: Link documents
1. Link pre-read to agenda:
- Add mention in agenda: "See <mention-page>Pre-Read</mention-page> for background"
2. Link both to project:
- Update project page with meeting links
- Add to "Meetings" section
3. Cross-reference:
- Agenda mentions pre-read for internal attendees
- Pre-read mentions agenda for meeting structure
Document Types
Internal Pre-Read (for team)
More comprehensive, internal context:
- Full background and history
- Internal metrics and data
- Honest assessment of challenges
- Strategic considerations
- What we need to achieve
- Internal discussion points
When to create: Always for important meetings with internal team
External Agenda (for all participants)
Clean, professional, focused:
- Clear objectives
- Structured agenda with times
- Discussion topics
- Decision items
- Professional tone
When to create: Every meeting
Agenda Types by Meeting Purpose
Decision Meeting: Meeting Details → Objective → Options (Pros/Cons) → Recommendation → Discussion → Decision → Action Items
Status Update: Meeting Details → Project Status → Progress → Upcoming Work → Blockers → Discussion → Action Items
Customer/External: Meeting Details → Objective → Agenda Items (timed) → Discussion Topics → Next Steps
Brainstorming: Meeting Details → Objective → Constraints → Ideas → Discussion → Next Steps
See reference/template-selection-guide.md for complete templates.
Research Enrichment Patterns
Beyond Notion content, add value through Claude's capabilities:
Technical Context: Explain technologies, architectures, or approaches. Provide industry standard practices. Compare common solutions. Suggest evaluation criteria.
Business Context: Industry trends affecting topic. Competitive landscape insights. Common challenges in space. ROI considerations.
Decision Support: Decision-making frameworks (e.g., RICE, cost-benefit). Risk assessment patterns. Trade-off analysis approaches. Success criteria suggestions.
Customer Context (for external meetings): Industry-specific challenges. Common pain points. Best practices from similar companies. Value proposition framing.
Process Guidance: Meeting facilitation techniques. Discussion frameworks. Retrospective patterns. Brainstorming structures.
Note: Use general knowledge and analytical capabilities. Don't fabricate specific facts. Clearly distinguish Notion facts from Claude insights.
Meeting Context Sources
Project Pages: Status, goals, team, timelines (most important) Previous Meeting Notes: Historical discussions, action items, decisions (recurring meetings) Task/Issue Database: Current status, blockers, completed/upcoming work (project meetings) Specifications/Designs: Requirements, decisions, approach, open questions (technical meetings) Reports/Dashboards: Metrics, KPIs, performance data, trends (executive meetings)
Linking Meetings to Projects
Forward Link: Add meeting to project page's "Meetings" section Backward Link: Include "Related Project" section in agenda with project mention Maintain bidirectional links for easy navigation
Meeting Series Management
Recurring Meetings: Create series parent page with schedule, meeting notes list, standing agenda, and action items tracker. Link individual meetings to parent.
Meeting Database: For organizations, use database with properties: Meeting Title, Date, Type (Decision/Status/Brainstorm), Project, Attendees, Status (Scheduled/Completed)
Post-Meeting Actions
Update agenda with:
Decisions: List each decision with rationale and owner Action Items: Checkbox list with owner and due date (consider creating tasks in database) Key Outcomes: Bullet list of main outcomes
Meeting Prep Timing
Day-Before (next-day meetings): Gather context → create agenda → share with attendees → allow review time Hour-Before (last-minute): Quick context → brief pre-read → basic agenda → essentials only Week-Before (major meetings): Comprehensive research → detailed pre-read → structured agenda → pre-meeting reviews
Best Practices
- Create both documents: Internal pre-read + external agenda for important meetings
- Distinguish sources: Label what's from Notion vs. Claude research
- Start with search: Cast wide net in Notion, then narrow
- Keep pre-read concise: 2-3 pages maximum, even with research
- Professional external docs: Agenda should be polished and focused
- Enrich thoughtfully: Claude research should add real value, not fluff
- Link documents: Pre-read mentions agenda, agenda mentions pre-read
- Include metrics: Data from Notion helps ground discussions
- Share appropriately: Pre-read to internal team, agenda to all participants
- Share early: Give attendees time to review (24hr+ for important meetings)
- Update post-meeting: Capture decisions and actions in agenda
Advanced Features
Meeting templates: See reference/template-selection-guide.md for comprehensive template library
Common Issues
"Too much context": Split into pre-read (internal, comprehensive) and agenda (external, focused) "Can't find relevant pages": Broaden search, try different terms, ask user for page URLs "Meeting purpose unclear": Ask user to clarify before proceeding "No recent updates": Note that in pre-read, focus on historical context and strategic considerations "External meeting - no internal context": Create simpler structure with just agenda, skip internal pre-read or keep it minimal "Claude research too generic": Focus on specific insights relevant to the actual meeting topic, not general platitudes
Examples
See examples/ for complete workflows:
- examples/project-decision.md - Decision meeting prep with pre-read
- examples/sprint-planning.md - Sprint planning meeting
- examples/executive-review.md - Executive review prep
- examples/customer-meeting.md - External meeting with customer (pre-read + agenda)
FAQ
What does the meeting-record-system skill do?
Record and manage meeting notes with intelligence. Organizes meeting documentation with action items, decisions, and follow-ups.
How do I install meeting-record-system?
Run npx skills add https://github.com/qodex-ai/ai-agent-skills --skill meeting-record-system in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/meeting-record-system/ (personal) or .claude/skills/meeting-record-system/ (project).
Which AI agents can use meeting-record-system?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is meeting-record-system safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains meeting-record-system?
It is published by qodex-ai in qodex-ai/ai-agent-skills. It has 135 recorded installs.
More from qodex-ai/ai-agent-skills
word-document-processor
qodex-ai/ai-agent-skills
Comprehensive word document processing with full format support. Handles creation, editing, formatting preservation, tracked changes, and metadata management.
multi-agent-orchestration
qodex-ai/ai-agent-skills
Design and coordinate multi-agent systems where specialized agents work together to solve complex problems. Covers agent communication, task delegation, workflow orchestration, and result aggregation. Use when building coordinated agent teams, complex workflows, or systems requiring specialized expertise across domains.
financial-analysis-agent
qodex-ai/ai-agent-skills
Create agents for financial analysis, investment research, and portfolio management. Covers financial data processing, risk analysis, and recommendation generation. Use when building investment analysis tools, robo-advisors, portfolio trackers, or financial intelligence systems.
legal-document-analyzer
qodex-ai/ai-agent-skills
Build agents for legal document analysis, contract review, and compliance checking. Handles document parsing, risk identification, and legal research. Use when creating contract analysis tools, legal research assistants, compliance checkers, or document review systems.
ecommerce-platform-specialist
qodex-ai/ai-agent-skills
Provide expert guidance on Shopify e-commerce platform. Advises on store setup, products, customization, and optimization.
spreadsheet-processor
qodex-ai/ai-agent-skills
Process and manipulate spreadsheet documents. Creates, edits, analyzes, and transforms Excel files with formula and formatting support.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。