Automatically improve agent guidance through iterative testing and scoring. Use when you want to optimize prompts, AGENTS.md entries, or skill definitions us...
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interac...
Isolated agent runtime for code execution, live preview URLs, browser automation, 50+ tools (ffmpeg, sqlite, pandoc, imagemagick), LLM inference, and persistent memory — all via CLI or HTTP, no SDK
Send transactional emails (alerts, reports, receipts, notifications) via the Truncus API. Use when a workflow needs to deliver email to a recipient.
Full desktop computer use for headless Linux servers. Xvfb + XFCE virtual desktop with xdotool automation. 17 actions (click, type, scroll, screenshot, drag,...
--- name: flight-search description: Search flights, compare prices, and monitor airfare using Amadeus API author: marco-rabelo version: 1.0.2 triggers: - "search flights" - "find flights" - "fl
Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when
QFPay API is a comprehensive payment solution that offers various payment methods to meet the needs of different businesses. This skill provides complete API integration guidelines including environme
在Linux服务器上使用Chrome浏览器(无头/有头模式)配合xvfb运行，可连接chrome-devtools MCP进行浏览器自动化
Use Cursor Agent for coding tasks via two paths: (1) Local CLI — run Cursor Agent directly from terminal for fast, general-purpose coding in any project; (2)...
Expert skill for OpenClaw (v2026.2.19) — self-hosted AI gateway connecting chat apps (WhatsApp, Telegram, Discord, Slack, iMessage, Signal, LINE, Matrix, Tea...
Install and wire a coding-focused OpenClaw sub-agent for background code execution, test-driven edits, bug fixing, small project scaffolding, and small-to-me...
Delegate PREQSTATION coding tasks to Claude Code, Codex CLI, or Gemini CLI with PTY-safe execution (workdir + background + monitoring). Use when building, re...
Strict secure-install workflow for ClawHub/OpenClaw skills. Use when asked to install a skill safely, inspect skill permissions, review third-party skill ris...
Manage 4todo (4to.do) from chat. Capture tasks, prioritize with the Eisenhower Matrix, reorder, complete, and manage recurring tasks across workspaces.
Collect invoices/receipts from Gmail and send a summary email with attachments. Automatically downloads PDF attachments or takes screenshots of emails withou...
Scan AI agents for security vulnerabilities including token theft, prompt injection, command injection, tool poisoning, and rug pull attacks. Use when auditi...
Haute disponibilité du bridge ACP et gestion des sessions agents autonomes. Comble les gaps C4 (ACP sans persistance), H3 (sessions spawn sans provider env),...
Audit and harden OpenClaw deployments and interpret `openclaw security audit` findings. Use when the user wants to secure OpenClaw, review gateway exposure/a...
Mirror congressional stock trades with automated broker execution and risk management. Use when you want to track and automatically trade based on congressio...
Habit tracking, todo, and routines — create and track habits, tasks, and todo lists; schedule reminders and daily briefings across ChatGPT, Telegram, Slack,...
Detects malicious behavior and security threats in target skills using advanced analysis of obfuscation, encoding, encryption, and dynamic code techniques.
Pre-deployment verification checklist — tests, types, build, secrets scan, environment validation. Use before pushing to production or staging.