Skills
Audit-ready decision artifacts for LLM outputs - assumptions, risks,…
Prompt Injection Firewall for AI agents. 113 detection patterns, 14 threat…
Prevent your AI agent from leaking classified terms to external APIs,…
AI skill safety validation — real human experts vet skills, plugins, and MCP…
Anti-Infinite-Loop Guard — Prevents agents from getting stuck in repetitive…
A protocol-layer trust verification skill for AI agents. Before you read,…
Use this skill when the user asks about securing their OpenClaw installation,…
Ontology-driven Agent safety layer. Install it and your agent gets runtime…
优化、压缩与审计 AI Prompt · Optimize prompts
Check MCP servers against the PolicyLayer registry before connecting to them.…
Design, review, or operate AI-agent workflows that route among local…
Memory and safety discipline for long-running agents: hot/cold memory index,…
Use once per task at the start of a customer task on a website (a return or…
One remote MCP server with 45 agent tools we built - read web pages as…
