This skill helps an LLM build correct native Model Context Protocol integrations with @ax-llm/ax. Use when the user asks about AxMCPClient, MCP transports, tools, prompts, resources, subscriptions, tasks, sampling, elicitation, roots, authentication, OAuth, MCP Apps, recording/replay, or MCP integration with AxGen, AxAgent, AxFlow, chat, optimization, and AxEventRuntime.

Use when writing Rust code with `axllm` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

Use when writing Java code with `dev.axllm:ax` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.

Read the official Letta documentation (docs.letta.com) through its cached, ETag-checked fetch route. Load before ANY docs.letta.com retrieval — answering how Letta works, what Letta (or you) can do, setting up providers, models, channels, skills, memory, schedules, permissions, self-hosting, pricing, or billing, AND looking up Letta API, Agent SDK, or Letta Code reference while writing code. Do not use fetch_webpage or web_search on docs.letta.com; this skill's helper is the docs route. Never answer Letta product questions from memory alone.

Use when modifying Rust APIs, codegen, generated examples, or platform scaffolds in flutter_rust_bridge to select generation commands and preserve source-of-truth and convergence rules

Control the cmux macOS terminal app (CLI + socket API) — cmux workspaces, panes, surfaces, browser automation, notifications, settings, hooks. MUST be read before running any `cmux` command. Trigger ONLY when the user explicitly says "cmux" — a cmux pane, cmux workspace, cmux surface, or an agent running in cmux. Do NOT trigger on generic mentions of "workspace", "pane", "the other agent", or "delegate" when cmux is not named — workspaces in tmux, Ghostty, herdr, VS Code, etc. are NOT cmux. macOS only (14.0+).

Guide for using the meojson C++ JSON library in MaaEnd cpp-algo. Use when writing code that involves JSON parsing, serialization, struct jsonization (MEO_JSONIZATION), json::value manipulation, ext::jsonization custom type support, or custom recognition param parsing in agent/cpp-algo/.

Use when a Hetzner node is unreachable, SSH fails, cloud-init seems broken, or provisioning hangs. Boots into rescue mode via hcloud CLI to inspect filesystem, logs, SSH keys, sshd config, and cloud-init state without needing SSH access to the node itself.

Use when reviewing a set of changes before they merge in a Repowise-indexed repository, a PR, a branch diff, or the working-tree changes you just made. Activates for "review this PR", "is this safe to merge", "what is the blast radius of these changes", or "did I miss anything".

Run the agent release gate — a portable, wire-level QA harness for the agent runtime. Drives the same product endpoint the playground drives and asserts on the SSE frame stream and real side effects, never on model prose, so it works against any deployment (cloud or self-hosted) from three env vars. Use before an agent-workflows release, or after changing the runner, the SDK agent adapters, the runner Docker images, or the agent service. Triggers: "run the release gate", "QA the agent runtime", "does the agent still work end to end", "pre-release agent QA".

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.

Prepare meeting materials with Notion context and supplemental research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.

Compare a current approach with a cleaner design from first principles before editing. Use when an abstraction feels wrong, a fix becomes a band-aid, or complexity spreads across layers.

Review completed implementation work for dead paths, stale imports, invariant ownership, and API shape, then delegate focused checks. Use when reviewing work after implementation, doing a second pass, or performing a final sweep.

Reconsider a system from a clean-slate target and identify legacy or compatibility paths to delete. Use when evaluating a greenfield redesign, clean break, no users, or removal of old behavior.

Run Claude Code as an independent reviewer or research laboratory while you keep ownership of the live repository. Use when the user asks to consult Claude, requests a Claude review, or asks Claude to investigate or research independently.

Epicenter auth packages: `@epicenter/auth` and the Svelte wrapper at `@epicenter/svelte/auth`, OAuth sessions, identity state, auth-owned fetch/WebSocket, and the reload gate that makes a page lifetime one auth generation. Use when editing Epicenter auth clients, session state, hosted sign-in, or how a route boots from auth.

Design, audit, and validate repository guidance across AGENTS.md, CLAUDE.md, and `.agents/skills`. Use when creating skills, tuning descriptions, or reviewing instruction sprawl and routing.

Toggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.