Agent Curator Skill

AI agent development standards including frontmatter structure, naming conventions, tool access patterns, model selection, and Bash-only file operations for .opencode/ folders

Discovers all Claude Code agents in the system including built-in, plugin, project, and user-level agents. Use when you need to find which agents are available, understand the agent ecosystem, or prepare agents for Actoris registration.

AI agent development with LangChain, CrewAI, AutoGen, and tool integration patterns.

Implement hooks for permission control and security in custom agents. Use when adding security controls, blocking dangerous operations, implementing audit trails, or designing permission governance.

**Project Name:** NextBlock CMS

TS/JS 程式碼智能重構工具。重命名、移動檔案、清理 dead code、修改函式簽章時自動更新所有引用。

Check and process messages from autonomous AILANG agents. Use when starting a session, after agent handoffs, or when checking for completion notifications.

Quick reference for invoking CasareRPA agents via Task tool. AUTO-CHAIN ENABLED by default. Use when: invoking agents, running agent chains, task routing, choosing the right agent, understanding agent auto-chaining, Task tool usage.

Manage agent fleet through CRUD operations and lifecycle patterns. Use when creating, commanding, monitoring, or deleting agents in multi-agent systems, or implementing proper resource cleanup.

MCP Agent Mail - mail-like coordination layer for coding agents with memorable identities, inbox/outbox, searchable threads, advisory file reservations, pre-commit guards, and human-auditable Git artifacts. The backbone of multi-agent workflows.

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

Guidelines for selecting appropriate AI model (Sonnet vs Haiku) based on task complexity, ensuring cost efficiency while maintaining quality. Use when assigning work.

agent-observability

Create new AgentOps skills via interactive interview. Supports from-scratch and clone modes with tiered complexity.

Interactive workflow guide. Use when user is unsure what to do next, needs help navigating AgentOps, or wants to understand available tools.

Deep topic research with optional issue creation from findings. Use for researching technologies, patterns, libraries, or any topic requiring investigation.

Create, refine, and manage issues. Use for creating new issues from loose ideas, refining ambiguous issues, bulk operations, or JSON export.

Detect available development tools at session start. Saves to .agent/tools.json and warns about missing required tools. Works with or without aoc CLI installed.

**CRITICAL: This skill teaches you how to dispatch tasks to multiple worker agents.**

Automatically applies when designing multi-agent systems. Ensures proper tool schema design with Pydantic, agent state management, error handling for tool execution, and orchestration patterns.

agent-prompt-behavior

The Agent Registry is a database-backed system for managing AI agent configurations. It replaces file-based configuration with a centralized, dynamic approach that supports:

Run section orchestrators to coordinate multi-component workflows. Use when starting work on a section.

Run prompt with OpenAI or Gemini provider via agent CLI

Ensure agent safety - guardrails, content filtering, monitoring, and compliance

Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integration, system prompts (CLAUDE.md, appendSystemPrompt, outputStyle), cost tracking, todo tracking, structured outputs, hosting patterns, plugins, and SDK branding guidelines. Assists with building custom agents, configuring SDK options, and troubleshooting SDK issues. Delegates 100% to docs-management skill for official documentation.

Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks.

Facilitates seamless integration between Claude Skills and the existing Agent framework, enabling skills to invoke agents and vice versa with proper context handoffs.

Automatically evaluate the security, safety, and trustworthiness of agent skills from GitHub repositories, websites, or direct .skill file URLs. This skill performs comprehensive assessments including

Create, use, and manage Agent Skills for Claude. Use when working with Skills, creating custom capabilities, or understanding how Skills extend Claude's functionality. Covers Skill architecture, file structure, and best practices.

Designs multi-agent systems with coordinated agent swarms, task distribution, inter-agent communication, and emergent collective behavior.

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, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa

Define tools for the support agent. Use when adding new capabilities like refund processing, license transfer, knowledge lookup, or any agent action.

Reference for configuring tool permissions when launching Claude Code agents. Use when setting up --allowedTools flags, restricting file access, or configuring agent permissions.

>

Build multi-agent AI workflows with orchestration, tool use, and state management

AI agent workflow patterns including ReAct agents, multi-agent systems, loop control, tool orchestration, and autonomous agent architectures. Use when building AI agents, implementing workflows, creating autonomous systems, or when user mentions agents, workflows, ReAct, multi-step reasoning, loop control, agent orchestration, or autonomous AI.

Build the `agentctl` CLI tool for AgentStack platform interaction. Implements authentication, project management, agent operations, development workflows, and evaluation commands.

AgentDB Reinforcement Learning Training operates on 3 fundamental principles:

---

agentdb-state-manager

AgentDB Vector Search Optimization operates on 3 fundamental principles:

Dependency management guidelines for Jarvy - crate selection criteria, feature flag best practices, version management, security auditing with cargo-audit and cargo-deny.

Security best practices and guidelines for the Jarvy CLI codebase - a cross-platform development environment provisioning tool that executes system commands with elevated privileges

Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for building and managing agent systems.

This skill allows product managers and founders to bypass the traditional "design-to-engineering" bottleneck by acting as a "generative lead" who directs AI agents to build, deploy, and maintain softw

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.

Coinbase AgentKit - Toolkit for enabling AI agents with crypto wallets and onchain capabilities. Use for building autonomous agents that can execute transfers, swaps, DeFi operations, NFT minting, smart contract deployment, and gasless transactions via Smart Wallets.

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.