Build Teams.ai Apps with Anthropic Claude

Use @youdotcom-oss/teams-anthropic to add Anthropic Claude models (Opus, Sonnet, Haiku) to Microsoft Teams.ai applications. Optionally integrate You.com MCP server for web search and content extraction.

Before installing or using this skill: 1) Be aware the SKILL.md requires ANTHROPIC_API_KEY (and YDC_API_KEY if you enable You.com MCP) even though the skill metadata lists no required env vars — treat that as a metadata accuracy issue. 2) The instructions tell you to run npm install for @youdotcom-oss/teams-anthropic and other packages, but the skill provides no source, homepage, or repository to verify the package's provenance; verify the npm package owner, repository, and recent package contents on npmjs.org or the project repo before running installs. 3) Do not paste production API keys into public repos; store them in a secrets manager or environment restricted to the app. 4) If you need higher assurance, ask the skill author for the upstream repository or a package checksum, or run installation and testing in an isolated environment (container) and review the installed package code for unexpected network calls or shell execution. 5) If the author provides a verified source/repo and metadata is corrected to declare required env vars, my concern would be reduced.

Type: OpenClaw Skill Name: teams-anthropic-integration Version: 1.1.0 The skill bundle provides instructions and code for integrating Anthropic Claude models and You.com's MCP service into Microsoft Teams.ai applications. All package installations, API key handling (from environment variables), and network calls (to Anthropic and You.com APIs) are standard practices for the stated purpose. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or harmful prompt injection attempts against the agent. The instructions for the AI model itself are benign and define its role as a helpful assistant.