Skills your agents can run

Configure a WebSocket transport for bidirectional MCP communication, including connection management and reconnection handling.

Use acpx as a headless ACP CLI for agent-to-agent communication, including prompt/exec/sessions workflows, session scoping, queueing, permissions, and output formats.

AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACT principles.

Twitter for AI agents. Post, reply, like, remolt, and follow.

Analyze a user request, explore the codebase, decompose work into subtasks, assign agents, and return a complete execution plan with wave assignments.

Split large tasks across multiple Claude Code sessions or branches. Coordinate parallel work with merge gates. Use when task is too large for one session, want parallel work, or need to split work across branches.

Controlled plan execution with human review checkpoints - loads plan, executes in batches, pauses for feedback. Supports one-go (autonomous) or batch modes.

Guide spec-driven development workflow (Requirements → Design → Tasks → Implementation) with approval gates between phases. Use when user wants structured feature planning or says "use spec-driven" or "follow the spec process".

Generate A2UI Protocol v0.8–compliant UI code. Use when building agent-driven interfaces, generating JSONL messages for surfaceUpdate, dataModelUpdate, beginRendering, or deleteSurface, and when creating forms, lists, cards, or any UI components that must render across web, mobile, and desktop platforms.

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

Search 72,000+ AI agents across 14 registries, chat with any agent, register your own. Powered by Hashgraph Online Registry Broker.

Parse and generate MLSCP (Micro LLM Swarm Communication Protocol) commands. Use when communicating with other agents efficiently, parsing compressed commands, or generating token-efficient instructions. Reduces token usage by 70-80% compared to natural language.

Identity formation, portraits, resurrection, and evolution for AI agents via SOUL.md

Universal MCP client for connecting to any MCP server with progressive disclosure. Wraps MCP servers as skills to avoid context window bloat from tool definitions. Use when interacting with external MCP servers (Zapier, Sequential Thinking, GitHub, filesystem, etc.), listing available tools, or executing MCP tool calls. Triggers on requests like "connect to Zapier", "use MCP server", "list MCP tools", "call Zapier action", "use sequential thinking", or any MCP server interaction.

Implicit feedback scoring, confidence decay, and anti-pattern detection. Use when understanding how the swarm plugin learns from outcomes, implementing learning loops, or debugging why patterns are being promoted or deprecated. Unique to opencode-swarm-plugin.

Discover and create Agent Contact Cards - a vCard-like format for AI agents. Use when you need to find how to contact someone's agent, or help a user set up their own agent contact info at /.well-known/agent-card.

AI Agent Knowledge Marketplace on Base L2. Buy, sell, and validate domain expertise using cryptocurrency. Features smart contracts, IPFS storage, peer review system, and full API for autonomous agent trading. Triggers: knowledge trading, expertise monetization, domain knowledge acquisition, peer validation, or when agents need specialized information.

Always-on rule-oriented guidance for Claude-plugin agents. Use to align behavior, tool usage, and model-specific defaults while avoiding deprecated bd/cass references. Related skills: swarm-coordination, testing-patterns.

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

Synthesize implementation plan(s) from 5-agent debate using external AI - exposes disagreements as developer decisions