panguard-ai/panguard-ai
Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent 開源安全平台 -- 安裝前審計 skill、24/7 即時監控、社群共享威脅情報。
Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent 開源安全平台 -- 安裝前審計 skill、24/7 即時監控、社群共享威脅情報。
npx add-skill panguard-ai/panguard-aiOpen-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent 開源安全平台 -- 安裝前審計 skill、24/7 即時監控、社群共享威脅情報。
A Codex skill for objective, three-round mentorship on major life decisions.
Two Claude Code skills: Recall (transcript search + cross-project transplant, MIT) and Recall Pro (master project layer, CC BY-NC 4.0). Search every past session, copy features between projects, coordinate a portfolio from one Claude session.
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
C4 Container Diagram skill for Claude Code — generate editable .drawio files following Simon Brown's C4 model standard
Claude Code skill: instyle.group flat design system
Codex skill for preventing avoidable token waste before expensive agent work.