Skill reviews

Generate a complete Model Context Protocol server project in Java using the official MCP Java SDK with reactive streams and optional Spring Boot integration.

• 13 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Skill converted from mcp-create-adaptive-cards.prompt.md

• Prose only: no discrete steps
• Does not say what the result is

Generate a complete Model Context Protocol server project in Ruby using the official MCP Ruby SDK gem.

• 15 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Generate a complete Rust Model Context Protocol server project with tools, prompts, resources, and tests using the official rmcp SDK

• Does not say what the result is
• No condition that starts the skill

Patterns and lived experience from Vega, an AI partner in a deep long-term partnership. For Ember to draw on when working with humans who are building something big, moving fast, w

• Prose only: no discrete steps
• Does not say what the result is

Generate a complete PHP Model Context Protocol server project with tools, resources, prompts, and tests using the official PHP SDK

• Does not say what the result is
• No condition that starts the skill

Containerize an ASP.NET Core project by creating Dockerfile and .dockerfile files customized for the project.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Authors a Dynamics 365 Finance and Supply Chain Management Solution Blueprint from scratch through a structured, section-by-section architect interview, establishing scope, target

• References files that are not bundled: references/firm-standards.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill

Build and scale developer-led adoption through ecosystem programs. Use when deciding open vs curated ecosystems, building developer programs, scaling platform adoption, or designin

• Does not say what the result is
• No condition that starts the skill

Create agent skills for Microsoft technologies using Learn MCP tools. Use when users want to create a skill that teaches agents about any Microsoft technology, library, framework,

• References files that are not bundled: sample_codes/getting-started/hello-kernel.cs
• 1 referenced file(s) missing: sample_codes/getting-started/hello-kernel.cs
• Does not say what the result is

Guides Qdrant monitoring setup including Prometheus scraping, health probes, Hybrid Cloud metrics, alerting, and log centralization. Use when someone asks 'how to set up monitoring

• Does not say what the result is
• No condition that starts the skill

Reference for React 19 source-file migration patterns, including API changes, ref handling, and context updates.

• Prose only: no discrete steps
• Does not say what the result is

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production

• References files that are not bundled: **validated_args
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill

Create time-boxed technical spike documents for researching and resolving critical development decisions before implementation.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Guides embedding model migration in Qdrant without downtime. Use when someone asks 'how to switch embedding models', 'how to migrate vectors', 'how to update to a new model', 'zero

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing ex

• References files that are not bundled: diagnosis/SKILL.md, search-strategies/SKILL.md
• 2 referenced file(s) missing: diagnosis/SKILL.md, search-strategies/SKILL.md
• 1 steps

Design, create, review, migrate, or troubleshoot Azure Developer CLI (azd) projects using current Microsoft guidance. Use for azd, azure.yaml, AZD templates, Bicep or Terraform und

• References files that are not bundled: scripts/azd
• The response is described with custom markup (3 tags): a typed call is more reliable
• 1 referenced file(s) missing: scripts/azd

When user is asking for guidance for which role to assign to an identity given desired permissions, this agent helps them understand the role that will meet the requirements with l

• Prose only: no discrete steps
• Does not say what the result is

Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Con

• Does not say what the result is
• No condition that starts the skill

Adopt repository-level harness engineering for coding agents. Use when a user wants to prevent repeated AI coding-agent mistakes by turning failures into durable instructions, drif

• References files that are not bundled: scripts/check_*.py
• 1 referenced file(s) missing: scripts/check_*.py
• Does not say what the process needs to start

Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, o

• References files that are not bundled: examples/policies/
• The response is described with custom markup (3 tags): a typed call is more reliable
• 1 referenced file(s) missing: examples/policies/

Complete development kit for Microsoft 365 Copilot declarative agents with three comprehensive workflows (basic, advanced, validation), TypeSpec support, and Microsoft 365 Agents T

• Does not say what the result is
• No condition that starts the skill

Socratic mentoring for junior developers and AI newcomers. Guides through questions, never answers. Triggers: "help me understand", "explain this code", "I'm stuck", "Im stuck", "I

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Guides Qdrant monitoring and observability setup. Use when someone asks 'how to monitor Qdrant', 'what metrics to track', 'is Qdrant healthy', 'optimizer stuck', 'why is memory gro

• References files that are not bundled: setup/SKILL.md, debugging/SKILL.md
• 2 referenced file(s) missing: setup/SKILL.md, debugging/SKILL.md
• 1 steps

Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases,

• 12 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill