valllabh/am-sandbox-sdk
Shared sandbox SDK: ManagerClient, skills loader, monitor (heartbeat + watchdog + artifact finalize). Consumed by am-pi-agent and am-opencode-agent as a submodule.
Shared sandbox SDK: ManagerClient, skills loader, monitor (heartbeat + watchdog + artifact finalize). Consumed by am-pi-agent and am-opencode-agent as a submodule.
npx skills add valllabh/am-sandbox-sdkShared sandbox SDK: ManagerClient, skills loader, monitor (heartbeat + watchdog + artifact finalize). Consumed by am-pi-agent and am-opencode-agent as a submodule.
Plan-first development partner for Claude Code: interview-driven plans, tier-routed agents (haiku/sonnet/opus), and an adversarial review chain that verifies through real usage.
Detector-guided humanizer skill for Claude Code: lower the AI-detection score of English text while preserving every key term, number, citation, and the original logic. Keyless, agent-as-rewriter.
10 AI-powered cybersecurity presales tools built with the Claude Code covering threat intelligence briefing, SOC simulation, phishing analysis, ZTA advisory, regulatory compliance mapping, and many more. Includes a Claude Code skill for automated bid drafting.
Provide comprehensive Chinese guides for installing, configuring, and understanding the OpenClaw AI agent framework and its multi-platform integrations.
An agent skill for incremental teaching, restatement, and quiz-based understanding checks.
🤖 Enhance your Cursor agent with self-evolving AI skills, learning from every correction to provide smarter, personalized support effortlessly.