gws-modelarmor-sanitize-prompt

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought…

Local input-hardening scanner for OpenClaw agents. Pattern-based detection across 9 categories of LLM input risks, with combined-signal scoring and caller-su...

Convert public web pages into clean Markdown with markdown.new for AI workflows. Use when tasks require URL-to-Markdown conversion for summarization, RAG ing...

Run Claude Code tasks in headless mode with `claude -p` through the local `cc-task-runner.sh` wrapper, including model switching, JSON output capture, struct...