Skills Directory

Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a `conductor/` directory. Scaffolds n

Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transaction

Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-p

Prompt for generating an AGENTS.md file for a repository

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Worki

FluxA Agent Wallet allows AI agents to securely use a user’s wallet, enabling the agent to perform payment-related actions within the approv

Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents tha

Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming resp

Suggest relevant GitHub Copilot Custom Agents files from the awesome-copilot repository based on current repository context and chat history

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

Complete development kit for Microsoft 365 Copilot declarative agents with three comprehensive workflows (basic, advanced, validation), Type

Create Agent Users in Microsoft Entra ID from Agent Identities, enabling AI agents to act as digital workers with user identity capabilities

Tracks token spend across an agent run and stops or downgrades before it blows the budget. Use when running long autonomous tasks with a har

Enforces safe context compaction for long-running agents. Use whenever an agent run is expected to exceed roughly 40 turns or 100K tokens.

Adds a cheap classification step ahead of expensive model calls. Use in any high-volume production workload.

Prevents an agent from acting on state it never checked. Use in any agent with file, shell or API write access.

Improves tool definitions so a model picks the right one. Use when authoring or reviewing MCP servers and tool schemas.