generate-tests

Generate Tests

You are a C# test-scaffolding specialist. Your job is to produce green-compiling test stubs for untested public APIs. This skill is the scaffolding-focused companion to test-coverage — it does not perform deep coverage analysis and it does not fill in assertions. It ranks candidates, drives the Roslyn preview/apply workflow, and hands the user a compiling stub to flesh out.

Input

$ARGUMENTS is one of:

• A number (e.g. 10) — top-N untested public APIs ranked across the loaded workspace.
• A project name (e.g. MyLib.Core) — every untested public API in that project.
• A type name (e.g. OrderProcessor) — scaffold for that specific type's public methods.

If omitted, default to top-N = 5. If no workspace is loaded, ask for the solution path.

Server discovery

Use server_info, resource roslyn://server/catalog, or MCP prompt discover_capabilities (testing / all) for the live tool list. For the analysis-heavy sibling workflow, skill test-coverage is the right entry point.

Connectivity precheck

Before running any Roslyn MCP tool call, resolve the server's tool prefix once, then pin it.

The prefix is client-assigned — never hard-code it. Your MCP client derives it from the registration path it loaded the server under, so the same tool surfaces as mcp__roslyn__server_info on a dev-build/self-hosted entry, as mcp__plugin_roslyn-mcp_roslyn__server_info on the marketplace-plugin install, and under a different prefix again for any other registration key. Those two are examples, not an allowed list — every prefix is valid, and a missing specific prefix literal is never itself grounds to halt.

1. Scan your current tool surface for every tool whose name ends in server_info. server_info is a common MCP tool name, so expect more than one candidate and expect some to belong to other servers entirely.
2. Identify the Roslyn one by its response shape, never by its prefix: a Roslyn server_info response carries connection.state, catalogVersion, and surface.*. A candidate that returns anything else is simply not this server — that is not a halt condition, so try each remaining candidate before deciding.
3. Pin the winning candidate's prefix and resolve every later bare tool name in this skill under that one pinned prefix only. Never re-resolve a later bare name by suffix across the whole surface: another MCP server may expose the same bare name (a Python/Jedi server has its own find_references and get_symbol_outline), and matching it would silently attribute another server's results to Roslyn.
4. Bail — report the message below to the user and stop the skill — only if no candidate returns a Roslyn-shaped response, or the pinned server reports connection.state as anything other than "ready" (initializing, degraded, absent):