os-guide
Trigger with "explain agentic os", "how do I set up a persistent agent environment", "what is the CLAUDE.md hierarchy", "explain the context folder…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
os-improvement-loop
Pattern 5: Concurrent Event-Driven Multi-Agent Loop. Coordinates multiple Claude sessions as OS threads sharing a common event bus and memory address space.…
os-improvement-report
Trigger with "show me the improvement chart", "how are we improving", "progress report", "graph the eval scores", "show cycle of improvement", "what's the…
os-init
Trigger: "set up agentic OS", "initialize agent harness", "init my project for AI agents", "where do I put CLAUDE.md", "create my agent environment", "set up…
openspace
Self-evolving skill system - skills that auto-fix, auto-improve, and auto-learn from usage. Provides collective intelligence where agents share improvements,…
runway-workflows
Build, inspect, validate, and run Runway editor workflow graphs via MCP. Use when the user asks to create, edit, list, or run Runway workflows, design…
create-store
Create or modify ryOS Zustand stores following repo conventions — persist middleware, partialize, versioned migrations, the debounced write-behind storage…
handover
Generate a HANDOVER.md shift-change report summarizing the current session for the next Claude. Use when the user types /handover, asks to "create a handover",…
delegation
This skill configures automatic task delegation between agents in Synapse A2A. Configure delegation rules via settings files (.synapse/settings.json and…
ccp
Use and manage ccp — the Claude Code Profile Manager. Use when: switching profiles, creating profiles, installing skills from sources, managing hub items,…
debate
Live multi-agent debate: named teammates argue with each other by message, you moderate and synthesize what survived — not one agent simulating both sides. Use…
meal-prep-efficiency-guru
Expert in batch cooking, meal planning, food storage, and efficient kitchen workflows
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…
MCP Integration
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",…
sap-joule-capability
Use this skill when authoring `.sapdas.yaml` capability bundles to register a code-based agent into Joule. Covers the four bundle files (capability, _da,…
codex-computer-use
`codex exec` Call Codex.app's Computer Use via , to read, click, and input into macOS apps and browsers. Use this when you want another agent that can execute shell commands, such as Claude Code, to perform GUI operations on its behalf. Chrome/Safari/Finder…
scylladb
Overview of ScyllaDB and a map of the ScyllaDB agent skills, with instructions to install or fetch a skill that is missing. Use this skill when starting a…
one-key-prompt
one-key-prompt (Prompt Alchemy): refine lengthy prompts into precise concept activation keys. Triggers: /one-key-prompt, /提示词炼金术, or when the user mentions "alchemy", "prompt optimization", "help me optimize my prompt", "the prompt is too long"
conductor
View what all active Claude Code sessions are doing and optionally send instructions to them via inbox
agent-evaluation
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents…
agent-manager-skill
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
agent-memory-systems
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term…
agent-tool-builder
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently,…