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 int-referencegit 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/int-reference)<a href="https://agentmods.dev/skills/microsoft/skills-for-copilot-studio/int-reference"><img src="https://agentmods.dev/badge/skills/microsoft/skills-for-copilot-studio/int-reference.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00035 | $0.03241 |
| Opus 5 | $0.00017 | $0.01621 |
| Sonnet 5 | $0.00007 | $0.00648 |
| Haiku 4.5 | $0.00003 | $0.00324 |
Grade A, and why
int-reference 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 7d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Studio YAML Reference
Core File Types
| File | Purpose |
|---|---|
agent.mcs.yml |
Main agent metadata (kind: GptComponentMetadata) |
settings.mcs.yml |
Agent settings and configuration |
connectionreferences.mcs.yml |
Connector references |
topics/*.mcs.yml |
Conversation topics (kind: AdaptiveDialog) |
actions/*.mcs.yml |
Connector-based actions (kind: TaskDialog) |
knowledge/*.mcs.yml |
Knowledge sources (kind: KnowledgeSourceConfiguration) |
variables/*.mcs.yml |
Global variables (kind: GlobalVariableComponent) |
agents/*.mcs.yml |
Child agents (kind: AgentDialog) |
Trigger Types
Topics with OnRecognizedIntent have two routing mechanisms — which one matters depends on the orchestration mode:
modelDescription— used by generative orchestration (GenerativeActionsEnabled: true). The AI orchestrator reads this to decide routing. Primary mechanism for generative agents.- Trigger phrases (
triggerQueries) — used by classic orchestration. Pattern-matched against the user's utterance. Secondary hints when generative orchestration is enabled.
System triggers (OnConversationStart, OnUnknownIntent, OnError, etc.) fire automatically and don't use either mechanism.
| Kind | Purpose |
|---|---|
OnRecognizedIntent |
Trigger phrases matched |
OnConversationStart |
Conversation begins |
OnUnknownIntent |
No topic matched (fallback) |
OnEscalate |
User requests human agent |
OnError |
Error handling |
OnSystemRedirect |
Triggered by redirect only |
OnSelectIntent |
Multiple topics matched (disambiguation) |
OnSignIn |
Authentication required |
OnToolSelected |
Child agent invocation |
OnKnowledgeRequested |
Custom knowledge source search triggered (YAML-only, no UI) |
OnGeneratedResponse |
Intercept AI-generated response before sending |
OnOutgoingMessage |
Non-functional (2026-03-15) — exists in schema but does not fire at runtime. Do not use. |
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.
- 7d ago First seen · 244 lines · 35 tokens per session scan A 81f7d955f2f5
int-reference is a skill published in the GitHub repository microsoft/skills-for-copilot-studio (432 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 3,241 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…