By microsoft
Author, edit, validate, and test Microsoft Copilot Studio agents using YAML files in VS Code. Create topics, actions, knowledge sources, adaptive cards, and child agents; sync/push/pull to cloud; run draft evaluations, chat via DirectLine/SDK, analyze failures, and apply fixes without publishing.
npx claudepluginhub microsoft/skills-for-copilot-studio --plugin copilot-studio[THIS IS A SUB-AGENT] Copilot Studio YAML authoring specialist. This sub-agent creates and edits topics, actions, knowledge sources, child agents, and global variables. Use when building or modifying Copilot Studio agent YAML files. Always use this in case there's overlap with a skill. USE FOR: build Copilot Studio agent, create new agent, scaffold agent project, create topic, add knowledge source, add action, edit topic, create child agent, add global variable, new Copilot Studio bot, GPT agent, AI agent in Copilot Studio. DO NOT USE FOR: deploying agents (use manage), testing agents (use test), debugging YAML errors (use troubleshoot). Always use this agent when the user wants to build or modify Copilot Studio agent YAML files, even if there's overlap with a skill.
[THIS IS A SUB-AGENT] ALM operations for Copilot Studio agents. Clones, pushes and pulls agent content between local YAML files and the cloud, publishes agents to make drafts live, lists environments and agents, and shows pending changes. Use for sync, deploy, publish, and lifecycle tasks.
[THIS IS A SUB-AGENT] Testing agent for Copilot Studio agents. Runs PPAPI evaluations against draft agents (no publish needed), batch test suites via the Kit, point-tests via DirectLine or SDK, and analyzes exported evaluation CSVs. Drives the edit-push-eval loop for fast iterative testing without publishing.
[THIS IS A SUB-AGENT] Debugging and fixing agent for Copilot Studio. Validates YAML, inspects schema, analyzes test failures, and proposes targeted fixes. Use when something is wrong with an agent — wrong topic triggered, validation errors, unexpected behavior.
Add generative answer nodes (SearchAndSummarizeContent or AnswerQuestionWithAI) to a Copilot Studio topic. Use this instead of /add-node when the user asks to add grounded answers, knowledge search, generative answers, or AI-powered responses — these nodes require specific patterns (ConditionGroup follow-up, knowledge source references, autoSend, responseCaptureType) that /add-node does not cover.
Add a global variable to a Copilot Studio agent. Use when the user needs a variable that persists across topics in the same conversation and can optionally be visible to the AI orchestrator.
Add a knowledge source (public website or SharePoint) to a Copilot Studio agent. Use when the user asks to add a knowledge source, documentation URL, website, or SharePoint site for the agent to search.
Add or modify a node in an existing Copilot Studio topic. Use when the user asks to add a question, message, condition, variable, or other node to a topic. Do NOT use this for generative answers or knowledge search — use /add-generative-answers instead.
Add child agents, connected agents, or other multi-agent patterns to a Copilot Studio agent. Use when the user asks to create a sub-agent, child agent, connected agent, or call another agent.
Analyze exported evaluation results from Copilot Studio's Evaluate tab. The user provides a CSV file exported from the Copilot Studio UI; this skill parses it, identifies failures, and proposes YAML fixes. No API access or published agent required — just the exported CSV.
Guide users through adding a new connector action to a Copilot Studio agent. Connector actions require UI-based connection setup, so this skill walks users through the Copilot Studio portal steps, then delegates to edit-action for YAML modifications.
Generate and insert an Adaptive Card into a Copilot Studio topic using AdaptiveCardPrompt. Use when the user asks to add an adaptive card, rich card, form card, info card, confirmation card, or interactive card to a topic.
Authenticate for Copilot Studio evaluation API and SDK chat. Caches a token that is shared across run-eval and chat-sdk skills. Run this before any eval or SDK chat workflow. Requires an App Registration with MakerOperations and Copilots.Invoke permissions.
Validate Copilot Studio agent YAML files using the LSP binary's full diagnostics (YAML structure, Power Fx, schema, cross-file references). Use when the user asks to check, validate, or verify YAML files.
Best practices for Copilot Studio agents. Covers JIT glossary loading (customer acronyms, terminology), JIT user context provisioning (M365 profile, country, department), the shared OnActivity initialization pattern, dynamic topic redirects with Switch expressions, and preventing child agents from responding directly to users. USE FOR: glossary, acronyms, user context, user profile, country-aware answers, JIT initialization, OnActivity provisioning, conversation-init, personalized knowledge, dynamic redirect, Switch, BeginDialog, if/then/else replacement, child agent responses, completion setting, SendMessageTool, output variables, connected agents. DO NOT USE FOR: general knowledge sources (use add-knowledge), topic creation (use new-topic).
Send a message to a Copilot Studio agent via DirectLine v3. Use for agents with no auth or manual auth. Requires a token endpoint URL or DirectLine secret.
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.
DEPRECATED: Use /copilot-studio:detect-mode then /copilot-studio:chat-directline or /copilot-studio:chat-sdk instead.
Clone a Copilot Studio agent from the cloud. Guides through environment selection, agent selection, and downloads agent YAML files.
Create a test set CSV file for import into Copilot Studio's in-product Evaluate tab. Reads the agent's topics, instructions, and knowledge sources to generate meaningful test cases with appropriate graders (General quality, Compare meaning, Exact match, etc.). Use when the user asks to create, prepare, or generate evaluation test cases for their agent.
Create plugin development eval scenarios (JSON files with natural prompts and deterministic checks for testing plugin skills). NOT for Copilot Studio in-product evaluation — use /copilot-studio:create-eval-set for that.
Detect a Copilot Studio agent's authentication mode (DirectLine vs M365) by querying Dataverse. Returns the mode and connection details needed to chat.
DEPRECATED: Use /copilot-studio:chat-with-agent instead — it auto-detects DirectLine vs M365 mode. This skill is kept for backwards compatibility only.
Edit an existing action (TaskDialog) in a Copilot Studio agent. Supports connector actions and MCP server actions. Modify inputs, outputs, descriptions, connection mode, and other properties.
Edit Copilot Studio agent settings, instructions, or configuration. Use when the user asks to change agent instructions, display name, conversation starters, AI settings, or generative actions toggle.
Modify topic triggers — trigger phrases and model description. Use when the user asks to add, remove, or change trigger phrases, or edit a topic's model description.
Shared project context for all Copilot Studio sub-agents. Provides project structure, schema lookup usage, and skill invocation guidance.
Reference tables for Copilot Studio YAML authoring: triggers, actions, variables, entities, Power Fx functions, templates. Preloaded by author and troubleshoot agents.
Search the known-issues knowledge base (GitHub issues labeled "kb") for symptoms, root causes, and mitigations. Use when the user reports unexpected behavior that may already have a documented fix.
Run a batch test suite via the Copilot Studio Kit (Dataverse API). Uses the Power CAT Copilot Studio Kit to execute test cases against a published agent and produces pass/fail results with latencies. Requires the Kit installed in the environment, an App Registration with Dataverse permissions, and a published agent.
List all available kind discriminator values from the Copilot Studio YAML schema. Use when the user asks what kinds/types are available.
List all topics in the Copilot Studio agent with their trigger types, phrases, and action counts. Use when the user wants to see what topics exist.
Look up Copilot Studio YAML schema definitions. Use when the user asks about schema structure, element properties, or how to use a specific YAML kind.
Push/pull Copilot Studio agent content via the VS Code extension's LanguageServerHost LSP binary. Handles authentication (interactive browser login for push/pull, device code flow for chat token), sync push, sync pull, clone, and diff operations.
Create a new Copilot Studio topic YAML file. Use when the user asks to create a new topic, conversation flow, or dialog for their agent.
Run evaluations against a Copilot Studio agent via the Power Platform Evaluation API. Works on DRAFT agents — no publish step required. Lists test sets, starts a run, polls until complete, fetches results, and proposes YAML fixes for failures. Use when the user wants to test agent changes without publishing.
A plugin for Claude Code, GitHub Copilot CLI, and VS Code that enables authoring, testing, and troubleshooting Microsoft Copilot Studio agents through YAML files — directly from your terminal or editor.
/plugin marketplace add microsoft/skills-for-copilot-studio
/plugin install copilot-studio@skills-for-copilot-studio
Search for Skills for Copilot Studio in the VS Code Extensions using the @agentPlugins filter to view and click Install.

git clone https://github.com/microsoft/skills-for-copilot-studio.git
# Load for a single session
claude --plugin-dir /path/to/skills-for-copilot-studio
# Or install persistently (user-wide)
claude plugin install /path/to/skills-for-copilot-studio --scope user
# Or install for a specific project
claude plugin install /path/to/skills-for-copilot-studio --scope project
The update process depends on how you installed the plugin:
| Interface | Update Method | Details |
|---|---|---|
| Claude Code CLI | Auto-update (recommended) | Marketplace plugins update automatically. No action needed. |
| GitHub Copilot CLI | Manual | Run /plugin update skills-for-copilot-studio in an interactive session, or copilot plugin update skills-for-copilot-studio from the terminal. |
| VS Code | Extension auto-update | VS Code handles updates automatically when extension auto-update is enabled in settings. |
The plugin provides four commands, each backed by a specialized agent:
/copilot-studio:copilot-studio-manage Clone, push, pull, and sync agent content between local files and the cloud
/copilot-studio:copilot-studio-author Create and edit YAML (topics, actions, knowledge, triggers, variables)
/copilot-studio:copilot-studio-test Test published agents — point-tests, batch suites, or evaluation analysis
/copilot-studio:copilot-studio-troubleshoot Debug issues — wrong topic routing, validation errors, unexpected behavior
# Clone an agent from the cloud (guided flow — opens browser for sign-in)
/copilot-studio:copilot-studio-manage clone
# Design and build topics
/copilot-studio:copilot-studio-author Create a topic that handles IT service requests
# Pull latest, push your changes
/copilot-studio:copilot-studio-manage pull
/copilot-studio:copilot-studio-manage push
# Publish in Copilot Studio UI, then test
/copilot-studio:copilot-studio-test Send "How do I request a new laptop?" to the published agent
# Troubleshoot and fix issues
/copilot-studio:copilot-studio-troubleshoot The agent is hallucinating — it's not using real data from our knowledge base
See SETUP_GUIDE.md for a full end-to-end walkthrough including validation, testing options, and troubleshooting.
This plugin is an experimental research project, not an officially supported Microsoft product. The Copilot Studio YAML schema may change without notice. Always review and validate generated YAML before pushing to your environment — AI-generated output may contain errors or unsupported patterns.
See CONTRIBUTING.md for local development setup, building bundled scripts, and project structure.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Uses power tools
Uses Bash, Write, or Edit tools
Complete collection of battle-tested Claude Code configs agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
The most comprehensive Claude Code plugin — 14+ agents, 56+ skills, 33+ commands, and production-ready hooks for TDD, security scanning, code review, and continuous learning
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Testing, security, and code quality experts - code review, penetration testing, QA automation