一键导入
agent-management
Use when managing individual agents - creating, updating, deleting, listing, or describing
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when managing individual agents - creating, updating, deleting, listing, or describing
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Thorough code review covering architecture, code quality, and performance. Use when asked to "review this plan", "review code", "audit architecture", "check code quality", or "review for performance". Walks through issues interactively with tradeoff analysis and opinionated recommendations.
Manage Letta AI agent fleets with kubectl-style CLI
Use when releasing features - covers issues, branches, tests, commits, PRs, versioning, and publishing
Use when deploying agents from YAML configuration files
Use when performing bulk operations like cleanup, delete-all, or bulk messaging
Architecture and design patterns for lettactl. Reference when building new features, displays, or commands.
| name | agent-management |
| description | Use when managing individual agents - creating, updating, deleting, listing, or describing |
src/commands/get.ts - List agentssrc/commands/describe.ts - Agent detailssrc/commands/create.ts - Create agentsrc/commands/update.ts - Update agentsrc/commands/delete.ts - Delete agentsrc/commands/export.ts - Export to JSONsrc/commands/import.ts - Import from JSONsrc/lib/agent-resolver.ts - Name to ID resolution# List
lettactl get agents [-o table|json|yaml] [--wide]
# Describe
lettactl describe agent <name> [-o table|json|yaml]
# Create
lettactl create <name> -d <description> -p <prompt> [-m <model>] [--context-window <n>] [--tools <list>]
# Update
lettactl update <name> [-p <prompt>] [-m <model>] [--add-tools <list>] [--remove-tools <list>]
# Delete
lettactl delete agent <name> [-y]
# Export/Import
lettactl export <name> [-o <file>]
lettactl import <file> [--name <new-name>]
AgentState {
id: string
name: string
description: string
system: string // system prompt
llm_config: { model: string; context_window: number }
tools: Tool[]
memory: { blocks: Block[] }
}
# List all agents
lettactl get agents
# Get agent details as JSON
lettactl describe agent my-agent -o json
# Create agent with tools
lettactl create my-agent -d "Helper" -p "You are helpful" --tools web_search
# Update system prompt
lettactl update my-agent -p "New prompt"
# Export and import
lettactl export my-agent -o backup.json
lettactl import backup.json --name my-agent-copy