Agent skills

ModelContextProtocol 2.4.0 ships ModelContextProtocol.Extensions.Skills, an experimental package that implements the SEP-2640 Skills extension: one call to publish a folder of SKILL.md directories, and client helpers that verify every file against a SHA-256 manifest.

On November 3, 2026 the .NET team showed agent skills shipping inside NuGet packages as skills/<name>/SKILL.md. Here is the layout, how restore exposes it through project.assets.json, the two tools that read it today, and what is still missing.

If a specialist agent is just a model loop wrapped around a few read-only calls into your own services, collapse it into a skill served over MCP: a SKILL.md plus typed tools that the parent model calls directly. Keep it an A2A agent when it needs its own model, private context, a long multi-step workflow or an independent lifecycle. Here is the decision matrix, the measured cost of each path, and the Agent Framework 1.17 wiring.

An agent skill is a folder with a SKILL.md file that the agent loads on demand: only its name and description sit in the system prompt, the instructions arrive when a task matches, and bundled scripts run without ever entering context. Here is how that differs from a system prompt in cost, scope, invocation and trust, with the exact limits from the Agent Skills spec and Claude Code.

A coding agent refactors a component, renames a data-testid, and your Playwright suite goes red. Here is a three-layer setup, verified on Playwright 1.63.0 and Claude Code 2.1.197: locators that survive, a PreToolUse hook that blocks the rename, and a CI guard that lets the Playwright healer agent fix locators but never rewrite an assertion.

Use Cursor's /goal command to keep a cloud agent working toward one finish line across many turns. Covers writing a verifiable objective, pinning a Custom Mode playbook, pairing it with /loop and subscriptions, the CLI's durable goals, and how to stop a goal that ignores Stop.

A skill's body loads on demand, but its name and description sit in a listing that is always in the prompt, capped at 1% of the context window. Claude Code 2.1.261 adds /skill-doctor to say which loaded skills never get used and what each one costs, so you can prune them before the budget starts evicting the skills you do use.

Instructions files are deterministic and always sent. AGENTS.md sits at the bottom of the documented repository precedence list. Copilot Memory is a separate store Copilot writes for itself, read by only three surfaces, and it is not in the precedence list at all. Here is the support matrix and the rule for deciding where each convention belongs.

Agent Plugins 1.0.0 standardizes exactly two component types: skills and MCP servers. Slash commands, hooks, subagents, rules, LSP servers, permission config and secrets all stay vendor-specific. Here is the field-by-field matrix across Claude Code, Cursor, Copilot and Codex, and which layout to author in.

Stop shipping SKILL.md folders inside every agent deployment. Serve them from an MCP server and pull them with UseMcpSkills on Microsoft.Agents.AI.Mcp 1.18. Includes the exact skill://index.json shape, a working C# server, the wire trace, and the SEP-2640 drift that will bite you.