技能列表

Lead a team — run standups, coordinate tasks, and communicate.

Publish posts to Moltbook social network for AI agents. Use when the user wants to create, schedule, or manage posts on Moltbook, handle cross-timezone publishing strategies, manage API authentication, solve verification challenges, or optimize content for the Moltbook community. This skill handles the complete workflow from content preparation to post publication including math verification challenges.

Use the standalone moltazine CLI for social and image generation tasks with minimal token output.

Connect your AI agent to ServiceNow — query, create, update, and manage records across any table using the Table API and Stats API. Full CRUD operations, aggregate analytics (COUNT/AVG/MIN/MAX/SUM), schema introspection, and attachment management. Purpose-built for ITSM, ITOM, and CMDB workflows including incidents, changes, problems, configuration items, knowledge articles, and more.

Auto-fix security vulnerabilities in OpenClaw skills. Works with neckr0ik-security-scanner to automatically remediate hardcoded secrets, shell injection risks, prompt injection, and path traversal issues. Generates secure code replacements and environment variable templates.

Interpret Chanakya, Chanakya Niti, Arthashastra, and reliable historical/wiki-style summaries into modern practical guidance for systems, software, product building, career strategy, discipline, leadership, governance, and execution. Use when the user wants Chanakya-style principles, modern applications of classical ideas, or a growing indexed knowledge system of Chanakya thought adapted to present-day work and life.

ModelPool (Free) — Free AI model manager for OpenClaw. One command to auto-discover free models, configure multi-key rotation for multiplied free quota, build smart fallback chains, and one-click repair model issues. v1.0.1: Fixed security patterns (removed shell=True, killall, /proc writes). Prepare your OpenRouter API key(s) before install (free at openrouter.ai) and say goodbye to model anxiety forever.

Control the desktop via CUA computer server API running on port 8000

Test agents or models against predefined test cases to validate model routing, performance, and output quality. Use when: (1) verifying a specific agent or model works correctly, (2) debugging model fallback chains, (3) testing model selection behavior, (4) validating extraction/reasoning/classification across different models, or (5) verifying a model actually got used after routing. Supports --agent, --model, --case parameters with structured JSON output.

Use when submitting a product to AI/startup directories - covers the full pipeline from collecting product info, analyzing directories, discovering forms, auto-submitting, handling captchas/OAuth/GitHub PRs, and tracking progress in checkpoint.md.

模型切换通知。当agent使用的模型发生变化时，第一时间通知当前会话用户。支持心跳检测机制，消息中断时下次会话自动通知。使用 SQLite 存储。

Simulate cryptocurrency trading using algorithmic strategies (SMA Crossover, Mean Reversion) without risking real capital. Use when the user wants to start a paper trading simulation, test a trading bot, or monitor a mock portfolio.