Skills for Copilot Studio is a plugin for authoring, testing, and troubleshooting standard Microsoft Copilot Studio agents as YAML files from a terminal or editor. It is intended for users of Claude Code, GitHub Copilot CLI, and VS Code who work with Copilot Studio agents. The catalogue add-ons are the plugin's skills, agents, hook, and plugin definition.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/skills-for-copilot-studio --skill add-generative-answersgit clone --depth 1 https://github.com/microsoft/skills-for-copilot-studioWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/skills-for-copilot-studio/add-generative-answers)<a href="https://agentmods.dev/skills/microsoft/skills-for-copilot-studio/add-generative-answers"><img src="https://agentmods.dev/badge/skills/microsoft/skills-for-copilot-studio/add-generative-answers/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/skills-for-copilot-studio/add-generative-answers"><img src="https://agentmods.dev/badge/skills/microsoft/skills-for-copilot-studio/add-generative-answers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.01288 |
| Opus 5 | $0.00042 | $0.00644 |
| Sonnet 5 | $0.00017 | $0.00258 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade A, and why
add-generative-answers scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Generative Answers
Add SearchAndSummarizeContent nodes to generate responses grounded in the agent's knowledge sources.
Important: Do You Even Need a Topic?
When knowledge sources are added to the agent (via /add-knowledge), the AI can directly search them without any topic if it recognizes a QnA-style query. A dedicated topic with SearchAndSummarizeContent is useful when:
- You want to restrict the search to a subset of knowledge sources (not all of them)
- You want to control the flow around the answer (e.g., follow-up questions, formatting, adaptive cards)
- You want to process the response before showing it (e.g., extract content, combine with other data)
- You want to use a specific input other than the user's last message
If the user just wants the agent to answer questions from its knowledge, adding the knowledge source may be enough.
Instructions
-
Auto-discover the agent directory:
Glob: **/agent.mcs.ymlNEVER hardcode an agent name.
-
Determine the approach based on what the user needs:
- Add to existing topic: Read the target topic and insert a SearchAndSummarizeContent node
- Create new search topic: Generate a complete topic with the search pattern
-
Look up the schema for both nodes:
node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js resolve CreateSearchQuery node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js resolve SearchAndSummarizeContent -
Read
settings.mcs.ymlto check ifGenerativeActionsEnabled: true. This determines the best pattern:GenerativeActionsEnabled: true→ prefer Pattern 2 (Orchestrator): use topic inputs/outputs and let the orchestrator handle the response. This is the best approach for generative-orchestrated agents.GenerativeActionsEnabled: false(or not set) → use Pattern 1 (Direct Response):autoSend: false+ manual SendActivity, or Pattern 3 (Fallback Search) for a simple all-knowledge fallback.- Verbatim/exact content needed → use Pattern 4 (Precision Search):
SearchKnowledgeSources+CreateSearchQueryfor raw results without AI summarization (insurance policies, HR docs, legal text).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 83 lines · 83 tokens per session scan A f5c8c061b72f
add-generative-answers is a skill published in the GitHub repository microsoft/skills-for-copilot-studio (437 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 1,288 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.