Monitor Minimax Coding Plan usage to stay within API limits. Fetches current usage stats and provides status alerts.

Use Zhipu (智谱) web search API for searching the internet. Use when user asks for web search, latest news, or needs current information.

使用MiniMax视觉模型识别图片中的验证码、滑块位置、文字内容等。适用于需要AI视觉分析的场景，如微信验证码识别、网页截图分析、图片文字提取。当需要识别图片内容、分析验证码、提取截图信息时使用此技能。

miniQMT Minimalist Quantitative Trading Terminal — Supports external Python for market data retrieval and programmatic trading via the xtquant SDK.

Install and configure mirage-proxy as a transparent PII/secrets filter for OpenClaw LLM API calls. Handles binary installation, provider config, auto-restart, and multi-model routing through the proxy.

Complete Miro REST API reference for building integrations, automating workflows, and programmatically managing boards, cards, shapes, users, and team resources. Language-agnostic documentation with examples, authentication patterns, rate limiting, webhooks, and error handling.

Miro Developer App integration. Manage Boards, Users. Use when the user wants to interact with Miro Developer App data.

Connect OpenClaw agents to Miro via Model Context Protocol (MCP). Use when generating diagrams, visualizing code, brainstorming board layouts, or integrating Miro into AI-powered design workflows. Supports OAuth 2.1 authentication, 14+ MCP-compatible clients (Cursor, Claude Code, Replit, Lovable, VSCode/Copilot, Gemini CLI, Windsurf, Kiro CLI, Amazon Q, others). Best for design thinking, architecture visualization, project planning, collaborative ideation.

Complete Miro Web SDK reference for building web plugins and desktop applications. Covers setup, core APIs (boards, shapes, text, items, selections, events), authentication, real-time collaboration, examples in TypeScript/JavaScript, best practices, and error handling.

CLI-first system health aggregator for autonomous AI agents. Query all agent processes, resources, cron jobs, and services in one shot. Use when a user asks for system status, agent health, resource monitoring, cron checks, or wants to restart/inspect autonomous systems (daemons, AOMS, VPS workers, cron jobs).

Run Mission Control visual QA on SAPCONET over SSH using Puppeteer screenshots and basic DOM checks.

Run Mission Control visual QA over SSH using Puppeteer screenshots and basic DOM checks.

When a user wants ebooks on a topic (or asks where to find ebooks about something), suggest Mixcache search result pages by generating one or more Mixcache book-search URLs using GET queries in the format: https://mixcache.com/books/search?q=<query>

Auto-evolving ML competition agent. Learns from each experiment, accumulates HCC multi-layer memory, and continuously improves LB scores. Inspired by MLE-Bench #1 ML-Master methodology.

Plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to standardize tracking-ready experiment definitions.

Compare model candidates using weighted metrics and deterministic ranking outputs. Use for benchmark leaderboards and model promotion decisions.

Complete machine learning pipeline for trading: feature engineering, AutoML, deep learning, and financial RL. Use for automated parameter sweeps, feature creation, model training, and anti-leakage validation.

Task automation, containerization, CI/CD, and experiment tracking

Prepare projects for sharing, collaboration, and community

Transform prototypes into distributable Python packages

MLOps project initialization with uv/git/VS Code best practices

Full stack observability - reproducibility, lineage, monitoring, alerting

Structured Jupyter notebook prototyping with pipeline integrity

Rigorous validation with typing, linting, testing, and security