Copilot

verification-before-completion is a final-check skill that blocks unsupported completion claims. Learn when to use it, how to install it from obra/superpowers, and how to match each status claim to fresh verification evidence.

using-superpowers is a session-start skill from obra/superpowers that forces skill lookup before any reply, helping agents discover and activate the right workflow first.

systematic-debugging is a root-cause-first debugging skill for bugs, flaky tests, build failures, and unexpected behavior. Learn the four-phase workflow, companion files, and when to use it before proposing fixes.

executing-plans helps agents follow a written implementation plan: review it first, execute tasks in order, run specified checks, stop on blockers, and hand off to a finishing workflow. Best for Project Management and other plan-led delivery.

webapp-testing is a skill for testing local web apps with Python Playwright. It helps agents start servers with scripts/with_server.py, inspect rendered UI, discover selectors, capture screenshots and console logs, and validate frontend behavior with a reconnaissance-first workflow.

ai-prompt-engineering-safety-review is a prompt audit skill for reviewing LLM prompts for safety, bias, security weaknesses, and output quality before production, evaluation, or customer-facing use.

agentic-eval is a GitHub Copilot skill that shows how to build evaluation loops for AI outputs using reflection, rubric-based critique, and evaluator-optimizer patterns.

agent-governance is a documentation-first skill for designing AI agent guardrails, policy checks, trust rules, tool restrictions, and audit logging for tool-using and multi-agent systems.

The add-educational-comments skill adds teaching-focused comments to a specified code file while preserving structure and behavior. It can ask for a file if missing, adapts to reader level, and follows clear line-growth limits for educational code editing.

vercel-react-best-practices is a Vercel Engineering skill that guides AI agents to optimize React and Next.js performance with prioritized rules for waterfalls, bundle size, and rendering.

mama is a narration-style variant of the pua skill that keeps the same core rules but switches to a Chinese nagging-mom voice. Use it to install a reusable trigger pattern for persistent troubleshooting, debugging, and Prompt Writing workflows, with inherited escalation, checklists, and stronger follow-through.

m365-agents-ts helps you build Microsoft 365 agents in TypeScript/Node.js with the Microsoft 365 Agents SDK, Express hosting, AgentApplication routing, streaming responses, and Copilot Studio client integration. It is a practical guide for deployment-oriented full-stack agent development.

m365-agents-py helps backend developers build Microsoft 365, Teams, and Copilot Studio agents in Python with aiohttp hosting, AgentApplication routing, streaming responses, and MSAL auth. It includes install guidance, usage patterns, and import-change notes from microsoft.agents to microsoft_agents.

m365-agents-dotnet is a Microsoft 365 Agents SDK for .NET skill for building multichannel agents in Teams, Microsoft 365, and Copilot Studio. It helps with ASP.NET Core hosting, AgentApplication routing, MSAL-based auth, package selection, and practical m365-agents-dotnet usage for API Development.

next-best-practices is a practical Next.js skill for App Router work, covering file conventions, RSC boundaries, async APIs, data patterns, route handlers, bundling, and error handling.

running-claude-code-via-litellm-copilot shows how to route Claude Code through a local LiteLLM proxy to GitHub Copilot, align ANTHROPIC_BASE_URL and model names, verify localhost traffic, and troubleshoot 401/403, model-not-found, and proxy compatibility issues.

seo-geo is a practical skill for website SEO and GEO. It helps with audits, keyword research, schema markup, meta tags, indexability, and AI visibility across ChatGPT, Perplexity, Gemini, Copilot, and Claude. Use the seo-geo skill when you need a guide that turns search visibility problems into clear fixes and implementation steps.

The copilot-sdk skill helps you build applications that programmatically use GitHub Copilot through the Copilot SDK. It fits API Development and app integrations in Node.js, Python, Go, and .NET, with session management, streaming, tools, hooks, MCP servers, and reusable agent workflows. Requires the GitHub Copilot CLI, and a subscription unless you use BYOK.

continual-learning is a skill for AI coding agents that need to remember useful lessons across sessions. It supports hooks, two-tier memory, and reflection so agents can reuse project conventions, avoid repeated mistakes, and improve Agent Orchestration over time.

autoresearch is an autonomous experimentation loop for coding tasks with measurable outcomes. It helps developers define a goal, baseline, metric, and scope, then iterate through code changes, tests, and keep-or-revert decisions using git-backed checkpoints.

automate-this turns a screen recording into an automation plan and draft scripts. It uses ffmpeg to extract frames, can transcribe narration with Whisper, reconstructs the workflow, and suggests practical automation options using tools already on your machine.

aspnet-minimal-api-openapi helps create ASP.NET Minimal API endpoints with typed results, DTO validation, MapGroup organization, and stronger OpenAPI metadata. Use it to plan install context, prompt the skill well, and improve endpoint usage for practical API development.

aspire skill for install, AppHost setup, local run, dashboard debugging, and publish workflows for Deployment. Covers CLI usage, references, troubleshooting, and the key publish-vs-deploy boundary.

architecture-blueprint-generator is a prompt-only skill that turns a codebase or project concept into a structured architecture blueprint with stack analysis, patterns, diagrams, implementation notes, and optional decision records.