CIRCE-Agent-Squad-for-Microsoft-Copilot-Studio

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.

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 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.

Pre-built TaskDialog templates for common Business Central MCP operations. Provides ready-to-use action YAML files for customer balance, overdue invoices, payment creation, sales orders, incident creation, and item availability.

Complete agent blueprints for typical Business Central scenarios — ready-to-implement specifications that combine all BC Extension Pack skills (MCP setup, instructions, actions, topics) into end-to-end agent definitions. Covers collections, sales assistant, and customer support agents.

Composable instruction blocks optimized for Business Central agents in Copilot Studio. Provides pre-composed instruction sets for collections, sales, support, and general BC agents.

Guide users through the complete Business Central MCP Server setup — from enabling the feature in BC to connecting it in Copilot Studio and pulling locally.

Topic patterns and templates for common Business Central scenarios in Copilot Studio. Covers collections, order inquiry, incident management, and customer onboarding with decision guidance on orchestrator vs custom topic.

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 published Copilot Studio agent and get its full response. Use when the user asks to test a specific utterance, check how the agent responds, verify a topic was fixed, or do a quick point-test after making YAML changes. Also useful for multi-turn conversation testing.

Clone a Copilot Studio agent from the cloud. Guides through environment selection, agent selection, and downloads agent YAML files.

Interactively configure an MCP (Model Context Protocol) action in a Copilot Studio agent. Walks the user through each configurable field, showing current values and asking for changes.

Send a message to a bot via DirectLine v3 REST API and get the full response. Use when the user has a DirectLine secret or Copilot Studio token endpoint URL. Supports auth/sign-in flows via OAuthCard detection.

Edit an existing connector action (TaskDialog) in a Copilot Studio agent. Modify inputs, outputs, descriptions, connection mode, and other properties using connector definitions as reference.

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.

List all available kind discriminator values from the Copilot Studio YAML schema. Use when the user asks what kinds/types are available.

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 or analyze tests for a published Copilot Studio agent. Two modes — run a batch test suite via the Copilot Studio Kit (Dataverse API), or import and analyze results from Copilot Studio's built-in evaluations. Not for sending a single test message — use /chat-with-agent for that instead.

Validate a Copilot Studio YAML file against the schema and best practices. Use when the user asks to check, validate, or verify a YAML file.

Creates a lightweight architecture decision record. Invoked automatically by agents when making significant design decisions, or manually when the user wants to document a decision.

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.

Create, edit, and manage Copilot Studio agent YAML files — topics, actions, knowledge sources, triggers, variables, and more.

Orchestrate multi-step, multi-agent workflows with HITL gates.

Push, pull, clone, and manage Copilot Studio agent content between local files and the cloud.

Test a published Copilot Studio agent — send test messages, run batch test suites, or analyze evaluation results.

Debug and fix Copilot Studio agent issues — validate YAML, diagnose wrong topic routing, resolve validation errors, analyze unexpected behavior.

Analyzes the Copilot Studio agent and generates a quality/coverage report. Reports on topic test coverage, trigger phrase density, knowledge source validation, model description completeness, and YAML validation status. Integrated with pre-push review.

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.

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.

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.

Mandatory review gate before pushing changes. Pulls latest state, validates all modified files, generates change summary with associated decision records, and waits for explicit user approval before proceeding with push.

Scaffolds a complete Copilot Studio agent from scratch with greeting, fallback, and error handler topics. Use when no agent exists in the workspace and the user wants to create one from scratch instead of cloning.

Updates circe-memory.md after significant operations. Invoked by other agents, not directly by users. Maintains a persistent cross-session memory file at the agent root with configuration, components, knowledge sources, decisions, and session summaries.