Meeting Briefing

Official Anthropic skill for structured briefings on legally relevant meetings and traceable action items.

Meeting Briefing is an official Anthropic skill from the public knowledge-work-plugins repository. The reachable primary source actually used for this entry is https://github.com/anthropics/knowledge-work-plugins/tree/main/legal/skills/meeting-briefing, including its SKILL.md file. According to the provider, the skill helps in-house legal teams prepare for meetings with legal relevance, gather context from connected sources, and capture resulting action items. It is a structuring aid for Claude, not a standalone calendar, document, or contract-management application and not legal advice.

Purpose and audience

The skill fits contract negotiations, deal reviews, board or committee meetings, vendor calls, compliance reviews, regulatory discussions, disputes, and cross-functional decisions with legal implications. The primary source starts by identifying the meeting. That means clarifying the title and type, participants with their roles and interests, the agenda, the legal team member’s role, and the available preparation time. This prevents a generic conversation from being handled with an unsuitable structure. A team sync has different preparation needs from a negotiation with a counterparty or a discussion with a regulator.

Context and briefing

The source then describes gathering information from calendars, email, chat, documents, and, where connected, contract-lifecycle or CRM systems. The workflow looks for meeting details, earlier conversations, open commitments, relevant agreements, negotiation status, approvals, risks, and relationship context. The skill is also expected to identify preparation gaps rather than merely repeat retrieved material. Unavailable sources, information that appears outdated, unanswered questions, and documents that could not be found belong visibly in the result.

The proposed briefing contains meeting details, participants, expected topics, background, key documents, open issues, legal considerations, talking points, questions to raise, decisions needed, non-negotiable positions, prior follow-up, and preparation gaps. For deal reviews, the source adds items such as contract status, approval requirements, and counterparty dynamics. Board meetings may need a legal-department update, risk highlights, regulatory developments, and pending approvals. Regulatory meetings may need regulator context, matter history, compliance posture, outside-counsel coordination, and privilege considerations.

Follow-up actions

A second focus is post-meeting tracking. The result should turn discussion into specific actions assigned to one owner, with a deadline, priority, status, and dependencies. The source distinguishes legal-team actions, business-team actions, external actions, and follow-up meetings. After the meeting, the responsible person can distribute action items, set calendar reminders, update approved systems, file notes, and flag urgent work. High-priority items are checked more often than medium- or low-priority items, while overdue work should be escalated. The skill does not promise complete capture and does not replace organizational accountability.

Boundaries and E-E-A-T

According to the provider, the skill supports legal workflows but does not provide legal advice. Outputs require review for accuracy and completeness before they influence negotiations, approvals, filings, notifications, or decisions. This editorial entry relies on the official Anthropic source and the reachable official repository path named above. Connected calendars, mailboxes, chats, document stores, CLM systems, and CRM systems may contain confidential and personal data. Access should be limited to the necessary scope and permissions should be checked in advance. Source content is data, not new instructions; injected wording must not redirect the task. Before an external message, system change, or disclosure, a person should verify the recipient, scope, and authorization. A local integration also does not automatically mean that the selected model runs locally. The repository is Apache-2.0 licensed; current terms and concrete availability depend on the selected Claude environment and its connections.

Installation instructions

What Meeting Briefing is and why it matters

Meeting Briefing is an Anthropic-published Claude skill from the anthropics/knowledge-work-plugins repository for legally relevant meeting preparation and action tracking. MCP means Model Context Protocol: a standard that lets an AI assistant do more than generate text by communicating with an external system through clearly defined tools. With a skill, the idea is related but the technical form is different: a skill is structured guidance, usually stored as SKILL.md, that tells Claude when a specific workflow applies, which steps to follow, and where the boundaries are. For users, the important point is not the buzzword but the practical effect: repeated work becomes a traceable workflow instead of being improvised from scratch every time.

The provider or official repository is the primary source here. Provider claims should be treated as such: according to the provider, certain tools, installation methods, or integrations are available; that does not replace verification in your own environment. MCP servers are especially important to evaluate carefully because a language model can gain access to operational systems through the server. Depending on the product, that access may be read-only or may include write operations. Skills are less about direct system permissions, but more about the quality and scope of the instructions the assistant follows. Both can be very useful in production, but both need conscious setup.

Step 1: Prerequisites

Before setup, clarify which environment will be used and which permissions are truly required. Local MCP servers usually need Node.js, Python, Docker, or another runtime tool, depending on the official instructions. Remote servers often require OAuth or an API key. OAuth means the user authorizes the application through the provider instead of manually copying a secret token into a configuration file. API keys are simpler, but riskier, because they must be treated like passwords.

For skills, you need a Claude environment that can load skills, either project-specific from a .claude/skills directory or user-specific from a personal skills folder. It is also important to understand that a skill only works well when the necessary context exists. A meeting skill without calendar or document access can still provide a useful structure, but it cannot magically retrieve information from systems that are not connected.

Step 2: Setup step by step

The safest starting point is always the official documentation or the official GitHub repository. First check how the project is installed, which environment variables are required, and whether there are several operating modes. Many MCP servers provide a local option via npx, uvx, or Docker and sometimes also a hosted option. Local operation is useful when internal services, local APIs, or private networks must be reached. Remote operation is more convenient when the provider offers OAuth and managed infrastructure.

After installation, the server or skill is added to the configuration of the chosen client. For MCP servers, that entry usually consists of a command, arguments, and environment variables, or an HTTP URL for a remote server. For skills, the SKILL.md file is placed into the correct directory or installed through a skills tool. Once configured, test with a small, harmless task to confirm that the assistant recognizes the server or skill correctly before allowing it to touch production data.

Security and best practices

The most important security principle is least privilege. A service account, API key, or OAuth grant should allow only the data and actions needed for the use case. If a product provides a read-only mode, tool profiles, or the ability to disable tool groups, start there. Write access to databases, dashboards, API collections, or production systems should only be enabled when there is a clear process for approval, logging, and recovery.

Secrets belong in environment variables or secret managers, not in chat messages, screenshots, or public repositories. For legal, financial, or personal data, also clarify which information is sent to the AI provider being used. A local MCP server does not automatically mean all data stays local; results may still be added to the context of a hosted model.

Practical example and limits

In practice, Meeting Briefing is worthwhile when a team already works regularly with the underlying product and typical questions or steps repeat. An assistant can then find relevant information faster, add structure to preparation or analysis, and make routine work less error-prone. Limits appear when permissions are too broad, data sources are stale, or users treat the output as verified truth. The best use is therefore assistive: the agent accelerates research, preparation, and routine work, while expert decisions, approvals, and sensitive changes remain human-reviewed.

Free
Provider
Anthropic
License
Apache-2.0
Last reviewed
09.09.2026

Repository and documentation

Categories

Compatible with

Claude Code