Grok and xAI workflows. This directory includes agent skill packages and prompt templates; each card identifies its type. A prompt template is copied from its source, while a skill package needs the appropriate agent setup. Compatibility may be inferred from the content unless a recorded test is linked.
One-click installation and configuration of Hermes Agent by Nous Research. Handles installing Hermes from scratch, adding LLM providers (OpenRouter, Anthropic, OpenAI, z.ai/GLM, Kimi, DeepSeek, Alibaba Qwen, Ollama, etc.), setting up messaging platforms (Telegram, Discord, Slack, DingTalk, Feishu/Lark, Weixin, WeCom), installing Hermes Workspace web UI, and migrating from OpenClaw. Use when the user asks about installing Hermes, setting up a provider, configuring a messaging platform, adding a bot, or any Hermes setup task.
Install and configure Tokenless (LLM token optimization toolkit) on Linux or macOS. Use when the user asks to install Tokenless, set up token optimization, reduce LLM token usage, or enable Tokenless for an agent framework (cosh, OpenClaw, Hermes, Qoder, Claude Code, Codex, Qwen Code).
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, and looking up Letta API, Agent SDK, or Letta Code reference.
Maintains an agent's core memory, the editable part of its system prompt. Use to modify the agent's core behavior, embed critical knowledge (needed on every turn), or instruct the agent on how to use deferred memory.
Maintains deferred memory, which stores accumulated knowledge, analysis, and observations made by the agent over time. Use when saving knowledge (e.g. about a person, project, repository, system, or event). Do NOT use for managing skills, prompts, or for saving information that is already automatically stored in the message history.
Create and manage shared memory — git-tracked repositories hosted on Letta Cloud that are attached to one or more agents and projected into their filesystems. Use when the user wants to share memory or files across agents, store context outside your own MemFS, attach or detach shared memory, or inspect its file history.
Use this skill whenever the user wants to create a finished video from a topic, title, idea, prompt, or script with MoneyPrinterTurbo. This includes short-form, voice-over, educational, marketing, social-media, and stock-footage videos. Also use it when the user mentions MoneyPrinterTurbo, provides this Skill URL, asks an AI agent to install or configure MoneyPrinterTurbo, needs missing API keys identified, wants a failed generation repaired, or wants a generated MP4 located and delivered. Use this skill when the expected outcome is a final video file, not setup instructions.
Drive PenguinHarness itself from a shell — list and create agents and sessions, send and steer messages mid-flight, and query costs and scheduled tasks via the penguin CLI over the local server.
Turn an external plugin — a Codex or Claude Code plugin, a skills repository, a folder in a GitHub repository — into a PenguinHarness plugin package, its skills and its MCP servers, and install it on the server's plugin market with penguin plugin install <folder>; the package format, the mapping rules and the review duties.
Optimize LLM prompt caching hit rate to reduce API costs and improve latency. Analyzes prompt structure, identifies cacheable vs non-cacheable content, and recommends restructuring to maximize cache reuse. TRIGGER when: user says "prompt cache", "cache hit rate", "reduce LLM cost", "optimize token usage", "cheaper LLM calls", or asks about prompt caching strategies for OpenAI/Anthropic/other providers. DO NOT TRIGGER when: user just wants to optimize a single prompt's quality (use prompt-optimizer instead), or asks about general caching infrastructure.
Research-before-coding workflow: search npm/PyPI, MCP servers, skills, and GitHub for existing tools before writing custom code, then adopt, extend, or build. Launches the researcher agent for non-trivial needs. Use when starting a feature, adding a dependency or integration, or about to write a utility that may already exist.
Inspect or modify Letta Code's own memory, model, context window, system prompt, compaction, permissions, toolsets, mods, skills, channels, schedules, agent secrets, and local runtime settings. Use when the user asks how this agent or conversation is configured, asks about account usage, remaining credits, or model quota, asks you to change how you behave or how the harness runs you, or renames you.
Install skills from external ecosystems into this agent's agentstate/skills/ — resolve Claude Code plugin marketplaces, the Codex plugin repo, skills.sh registry names, GitHub repos, or local folders to their skill directories, review every file, and normalize SKILL.md frontmatter to the Penguin format.
Diagnose and repair MemFS repository setup, remote sync, authentication failures, optional backup remotes, or merge/rebase conflicts. Do not load for routine memory reads or edits.
Measure a set of reference videos into a reusable style pack - colour grade as a 3D LUT, cut rhythm as a shot-length distribution, hero stills, screen-blend overlay plates, and a text spec for a generative model. Use when the user wants to capture the look of reference footage, build a repeatable look, mint assets from references, or reproduce someone's grade and pacing.
Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Grok Build, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only sessionsspawn for thread creation. Codex chat binding defaults to the native Codex app-server plugin unless ACP is explicit or background spawn needs ACP.
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura tool is present, whenever the user refers to past work ("what did we decide", "last time", "earlier"), or whenever any durable fact needs to be stored, recalled, superseded, or shared with the fleet. Do not use it for throwaway within-session scratch state.
Persistent per-project memory for Claude Code (Context Keeper) driven by deterministic Node.js /ck commands: init, save, resume, info, list, forget, and v1-to-v2 migrate, plus a SessionStart hook that injects a compact project brief. Use when context must survive across sessions, saving session state with next steps and decisions, resuming where a previous session left off, or picking up a project without re-explaining it.
Send chat completions, stream responses, and start an interactive REPL session from the CLI. Supports all OmniRoute providers, combo routing, and system prompt configuration.