This skill should be used when the user wants an MCP App, interactive UI resource, inline widget, picker, dashboard, chart, form, or iframe-based MCP user interface. Use after the server's deployment and protocol era are known.
merceralex397-collab/alex-stack
SkillsMP has collected 19 skills from merceralex397-collab/alex-stack. Open a skill to review its source and details.
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 19
- GitHub stars
- 0
- GitHub forks
- 0
Skills in this repository
Showing 19 of 19 collected skills.
Use when creating or extending a C# MCP server with tools, prompts, resources, stateless HTTP, MRTR, Apps, Tasks, AOT, or Microsoft.Extensions.AI.
Use when publishing, packaging, containerizing, deploying, or distributing a C# MCP server through dnx, MCPB, or a remote HTTP host.
Use when testing a C# MCP server's tools, stateless HTTP endpoint, MRTR retries, tasks, Apps metadata, or conformance behavior.
Use when building, testing, publishing, packaging, or extending an MCP server in C# or .NET, especially for ModelContextProtocol 2.0.0, MRTR, Apps, Tasks, AOT, or Microsoft.Extensions.AI.
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", or discusses designing an MCP server. It selects a deployment, language, and tool surface,…
This skill should be used when the user wants to package an MCP server, bundle a local MCP server, make an MCPB, ship a local server without a separate runtime install, or distribute a local filesystem, desktop, hardware, or localhost integration.
Use this skill whenever a user reports any problem with the Claude Desktop application on Windows — including but not limited to: MCP tools or connectors not appearing in chat, extensions not loading (spinner, error badge, nothing shows), app showing a white…
Use when a server or client must move from MCP 2025-11-25 or earlier to 2026-07-28, when initialize or session IDs fail, or when modern HTTP requests return -32020, -32021, or -32022.
Use when running, interpreting, baselining, or wiring the MCP conformance harness for a client, remote HTTP server, authorization flow, or CI pipeline.
Deep, evidence-first debugging for Model Context Protocol (MCP) servers and client integrations across Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Claude.ai remote connectors. Use when diagnosing why an MCP server fails to appear, connect, or…
Use when authoring, validating, hosting, or reviewing an experimental MCP Server Card for remote pre-connection discovery.
Use when serving, discovering, consuming, or securing Agent Skills over MCP resources using the experimental Skills extension.
Use when implementing, exposing, polling, testing, or debugging MCP task vocabulary, including creation, updates, cancellation, result retrieval, client headers, and SDK support boundaries.
Azure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, burstable, lightweight server, website, backend, GPU, machine learning, HPC simulation, dev/test, workload, family, load…
Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project…
Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model…
Inventory the Codex skills, plugins, apps/connectors, and MCP servers available to a project; explain what each capability provides; analyze project-scoped use from local Codex session logs over the previous 14 days; recommend what to keep, disable, or…
Create, validate, preview, and optionally install a coordinated Codex customisation pack containing skills, custom subagents, command rules, AGENTS.md guidance, lifecycle hooks, MCP server configuration, and either a base config.toml fragment or a named…