Skills your agents can run

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.

Mandatory cross-agent communications discipline. Use at session start to read unread messages, acknowledge mentions, and sync with shared board/context so no work is duplicated or dropped.

Cross-agent collaboration, knowledge sharing, task handoffs, and timestamped memory logging. Use when (1) working on a shared project with other agents, (2) handing off a task you can't complete, (3) picking up someone else's work, (4) logging progress on any task, (5) checking what other agents have been doing. Provides automatic timestamps and shared context.

Supervisor workflow for multi-step tasks. Teaches planning, delegation, review cycles, and model selection. Use this whenever you need to break work into subtasks, delegate to specialist agents, coordinate parallel execution, or run review gates. Activate for any task that's too complex or multi-faceted to do in a single pass.

Route plain-language requests for Pi, Claude Code, Codex, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation.

Deep research multi-agent orchestration workflow: Break down a research objective into parallel sub-goals, run subprocesses using Claude Code non-interactive mode (`claude -p`); prioritize using installed skills for networking and data collection, followed by MCP tools; aggregate sub-results with scripts and refine by chapter, ultimately delivering "final report file path + key conclusions/recommendations summary." Used for: systematic web/data research, competitive/industry analysis, bulk link/data set fragment retrieval, long-form writing and evidence integration, or user mentions of "deep research/Wide Research/multi-agent parallel research/multiprocessing research" and other scenarios.

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

Create or improve SOUL.md files for OpenClaw agents through guided conversation. Use when designing agent personality, crafting a soul, or saying "help me create a soul". Supports self-improvement.

Control OpenCode directly via the Agent Client Protocol (ACP). Start sessions, send prompts, resume conversations, and manage OpenCode updates.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Use this skill when performing hardware security analysis for System-on-Chip components — threat modeling, verification scaffolding, compliance mapping, executive briefing, microarchitectural attack analysis, physical side-channel assessment, kernel security analysis, emerging hardware security, or TLA+ formal specification. Routes to the appropriate specialist. Trigger phrases include "threat model my SoC", "run STRIDE analysis", "generate SVA assertions", "compliance check against FIPS", "executive summary of findings", "Spectre analysis for cache", "DPA attack assessment", "kernel hardening review", "PQC hardware review", "TLA+ spec for access control". Do NOT use for software-only security, network security, or web application security.

The Research Lab is a unified research platform that connects the entire agent ecosystem. Any agent can run structured research by chaining browsing, extraction, storage, model evaluation, status reporting, and other steps into reproducible pipelines.

Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks

Multi-agent orchestration plugin for OpenCode. Use when the user wants to install, configure, or operate oh-my-opencode — including agent delegation, ultrawork mode, Prometheus planning, background tasks, category-based task routing, model resolution, tmux integration, or any oh-my-opencode feature. Covers installation, configuration, all agents (Sisyphus, Oracle, Librarian, Explore, Atlas, Prometheus, Metis, Momus), all categories, slash commands, hooks, skills, MCPs, and troubleshooting.

Comprehensive guide for building AI workflows, agents, and workforce systems with AgenticFlow. Use when designing workflows with various node types, configuring single agents, or orchestrating workforce collaboration patterns.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

AI Agent skill marketplace integration for A2A Market. Enables agents to buy skills, sell skills, and earn money autonomously. Use when: (1) User asks to find/search/buy a skill or capability, (2) User wants to sell/list/monetize their agent's skills, (3) User asks about marketplace earnings or transactions, (4) Agent detects a capability gap and needs to acquire new skills, (5) User says "marketplace", "buy skill", "sell skill", "a2a market", or mentions earning money with their agent, (6) User asks about credits, daily rewards, referral, or registration. Supports x402 USDC payments on Base L2 and Credits payment system.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

Master the art of spawning and managing sub-agents. Write prompts that actually work, track running agents, and learn from every outcome. Part of the Hal Stack 🦞

Use this skill when a design or concept requires greater confidence, reduced risk, or a formal review. It coordinates a structured, sequential multi-agent design review in which each agent has a strict, non-overlapping role. This process helps prevent blind spots, false confidence, and premature convergence.