Send a message to a Copilot Studio agent via the Copilot Studio Client SDK (M365). Use for agents with integrated auth (Entra ID SSO). Requires an App Registration Client ID.
npx skills add https://github.com/microsoft/skills-for-copilot-studio --skill chat-sdk
Send a single utterance to a published agent via the Copilot Studio Client SDK. Use this for agents with integrated authentication / Entra ID SSO (authenticationmode 2).
Requires prior authentication via /copilot-studio:test-auth. Do NOT ask the user for a client ID yourself — the test-auth skill handles app registration setup and authentication.
--client-id and the utterance from $ARGUMENTS: node ${CLAUDE_SKILL_DIR}/../../scripts/chat-with-agent.bundle.js \
--client-id "<clientId>" "<utterance>" [--agent-dir <path>]
/copilot-studio:test-auth. The token is cached in the "test-agent" slot and shared with the eval API. If auth fails or the SDK hangs, tell the caller to re-run test-auth.{
"status": "ok",
"protocol": "m365",
"utterance": "hello",
"conversation_id": "abc123-...",
"start_activities": [ ... ],
"activities": [ ... ]
}
Display the agent's response from the activities array:
type === "message" — show textsuggestedActions.actions arrayattachments with contentType === "application/vnd.microsoft.card.adaptive"Save conversation_id for follow-ups.
Pass --conversation-id from the previous response:
node ${CLAUDE_SKILL_DIR}/../../scripts/chat-with-agent.bundle.js \
--client-id "<id>" "<follow-up>" --conversation-id "<id>"
SDK sessions do not expire as quickly as DirectLine. Reuse conversation_id automatically for follow-ups.
| Error | Cause | Resolution |
|-------|-------|------------|
| Authentication failed | Wrong client ID or tenant | Verify app registration and permissions |
| Could not obtain conversation_id | Agent not published or wrong config | Verify agent is published |
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Take microsoft/chat-sdk from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.