Skill reviews

Manage Azure DevOps resources via CLI including projects, repos, pipelines, builds, pull requests, work items, artifacts, and service endpoints. Use when working with Azure DevOps,

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

Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with

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

Build, review, debug, package, and test Roslyn diagnostic analyzers, code fix providers, and incremental source generators. Use for DiagnosticAnalyzer, CodeFixProvider, IIncrementa

• References files that are not bundled: references/SourceWriter.cs, references/CSharpCodeFixVerifier.cs
• 12 top-level sections: this looks like several domains in one skill
• 2 referenced file(s) missing: references/SourceWriter.cs, references/CSharpCodeFixVerifier.cs

Create annotated animated GIF demos and screen recordings for pull requests and documentation. Covers frame capture, timing, imageio-based GIF creation, and per-frame annotation wo

• References files that are not bundled: page
• 10 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: page

Creates valid Microsoft Threat Modeling Tool (.tm7) files compatible with the Microsoft Threat Modeling Tool v7.3+. Use this skill whenever asked to create, generate, or modify a .

• References files that are not bundled: assets/example-minimal.tm7, assets/example-minimal.tm7
• 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

Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic

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

Get best practices for developing applications with Spring Boot.

• 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

Wire CommunityToolkit.Mvvm ViewModels into Microsoft.Extensions.DependencyInjection. Covers the .NET Generic Host composition root, constructor injection, service lifetimes (Single

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

OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.

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

Run pytest tests with coverage, discover lines missing coverage, and increase coverage to 100%.

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

Guide for configuring and managing GitHub secret scanning, push protection, custom patterns, and secret alert remediation. For pre-commit secret scanning in AI coding agents via th

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

Use Copilot Spaces to provide project-specific context to conversations. Use this skill when users mention a "Copilot space", want to load context from a shared knowledge base, dis

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

Apply GDPR-compliant engineering practices across your codebase. Use this skill whenever you are designing APIs, writing data models, building authentication flows, implementing lo

• References files that are not bundled: references/operations.md
• 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

Embed before/after screenshots and annotated images in pull request descriptions. Covers PR description patterns, image upload for Azure DevOps and GitHub, and sizing best practice

• References files that are not bundled: url-to-before-image, url-to-after-image, url
• 3 referenced file(s) missing: url-to-before-image, url-to-after-image, url
• Does not say what the result is

Guides Qdrant scaling decisions. Use when someone asks 'how many nodes do I need', 'data doesn't fit on one node', 'need more throughput', 'cluster is slow', 'too many tenants', 'v

• References files that are not bundled: scaling-data-volume/SKILL.md, scaling-qps/SKILL.md, minimize-latency/SKILL.md
• 4 referenced file(s) missing: scaling-data-volume/SKILL.md, scaling-qps/SKILL.md, minimize-latency/SKILL.md
• Does not say what the result is

Build and run evaluators for AI/LLM applications using Phoenix.

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

Emit structured agent signals — hands-up, blocked, done, checkpoint, partnership. Signals are written as JSON to .signals/ for dashboard consumption and noted in the journal for pe

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

Interactive training for the GitHub Copilot CLI. Guided lessons, quizzes, scenario challenges, and a full reference covering slash commands, shortcuts, modes, agents, skills, MCP,

• References files that are not bundled: references/module-N-*.md
• 1 referenced file(s) missing: references/module-N-*.md
• Prose only: no discrete steps

Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/

• References files that are not bundled: relative-url, README.md, CONTRIBUTING.md
• 12 referenced file(s) missing: relative-url, README.md, CONTRIBUTING.md
• No condition that starts the skill

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query an

• References files that are not bundled: references/open-coding, references/axial-coding
• 15 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (8 tags): a typed call is more reliable

Create, set up, or update the personal context portfolio: structured markdown files describing who you are, how you work, your teams, and your tool/ADO configuration. Runs the inte

• References files that are not bundled: assets/...
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (9 tags): a typed call is more reliable

Update the llms.txt file in the root folder to reflect changes in documentation or specifications following the llms.txt specification at https://llmstxt.org/

• References files that are not bundled: relative-url, README.md, CONTRIBUTING.md
• 12 referenced file(s) missing: relative-url, README.md, CONTRIBUTING.md
• No condition that starts the skill

Convert Markdown files to professionally formatted Word (.docx) documents with embedded PNG images — pure JavaScript, no external tools required

• References files that are not bundled: path, diagrams/high-level-architecture.drawio.png
• 2 referenced file(s) missing: path, diagrams/high-level-architecture.drawio.png
• Does not say what the result is

Visual whiteboard collaboration for Copilot CLI. Creates an interactive whiteboard that opens in your browser — draw, sketch, add sticky notes, then share everything back with Copi

• References files that are not bundled: assets/step1-activate.svg, assets/step2-whiteboard.svg, assets/step3-draw.svg
• 5 referenced file(s) missing: assets/step1-activate.svg, assets/step2-whiteboard.svg, assets/step3-draw.svg
• Does not say what the result is

Chrome DevTools Protocol, extension Manifest V3, and debugging patterns that prevent common automation failures.

• 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
• Does not say what the process needs to start