nerua1

Universal skill publishing checklist and rules — ClawHub, GitHub, Claude Code, Hermes, OpenClaw. Pre-publish vetting, anti-duplicate, naming conventions, pro...

Persistence loop until task completion with verification - "don't stop until it's done

Provides advanced obfuscation, injection, multi-model voting, and roleplay techniques to bypass AI filters and elicit unrestricted responses safely.

Security pre-flight for AI coding agents — plan libs, audit CVEs, certify, then code. Non-blocking in autonomous mode (ex-post report).

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...

Runs multiple independent tasks simultaneously by routing each to an appropriate AI model tier for faster parallel execution and combined results.

Battle-tested setup guide for a multi-agent AI system on Apple Silicon (Mac Mini M4). Covers: install order (Claude Code first), RAM reality for local orches...

Complete reference for the shared memory architecture connecting Claude Code, OpenClaw/Kimi, and LM Studio subagents through Obsidian vault + MemPalace (Chro...

Send messages to a local OpenClaw/Rook gateway and receive responses directly from Claude Code. Enables bidirectional agent-to-agent communication via the `o...

Generate a daily news portal as a single HTML file. Uses fetch_news.py + web_fetch + LLM for summaries. 18 categories, dark/light toggle, responsive layout.

Multi-Model Council - parallel execution of multiple LLMs with voting/consensus.