Menu
Manage Letta AI agent fleets with kubectl-style CLI
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
Use when releasing features - covers issues, branches, tests, commits, PRs, versioning, and publishing
Use when deploying agents from YAML configuration files
Use when managing individual agents - creating, updating, deleting, listing, or describing
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 | lettactl |
| description | Manage Letta AI agent fleets with kubectl-style CLI |
kubectl-style CLI and SDK for deploying AI agents declaratively from YAML.
lettactl apply -f fleet.yaml # Deploy agents
lettactl get agents # List agents
lettactl send <agent> "Hello" # Message agent
lettactl health # Check server
export LETTA_BASE_URL=http://localhost:8283
export LETTA_API_KEY=<optional-for-cloud>
fleet-deployment/ - Deploy agents from YAML configsagent-management/ - Create, update, delete, list agentsmessage-operations/ - Send messages, view historyresource-management/ - Manage blocks, tools, folders, filesbulk-operations/ - Cleanup, delete-all, bulk messagingobservability/ - Health, context usage, async runsrelease-cycle/ - Release workflow: issues, branches, tests, commits, PRs, versioning