Safer agent skills

Multi-LLM orchestration framework

Score basis：Clear source · Risk needs review · Universal

Chat with your data, modify it, visualize it, create and test machine learning models all in plain English.

Score basis：Clear source · Risk needs review · Universal

Full-content web fetcher for AI agents — Chrome TLS fingerprinting, browser impersonation, and multi-strategy article extraction

Score basis：Clear source · Risk needs review · Universal

Coding agent with lossless context management

Score basis：Clear source · Risk needs review · Universal

🌊 Simple, event-driven and stream oriented workflow for TypeScript

Score basis：Clear source · Risk needs review · Universal

Integrate LLM models directly into Ghidra for automated code refactoring and analysis.

Score basis：Clear source · Risk needs review · Universal

[NAACL 2025] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents

Score basis：Clear source · Risk needs review · Universal

[NeurIPS 2025] Thinkless: LLM Learns When to Think

Score basis：Clear source · Risk needs review · Universal

Pose and animate MMD model with LLM and MPL code

Score basis：Clear source · Risk needs review · Universal

Complex Reasoning Rag System, Agentic Rag System

Score basis：Clear source · Risk needs review · Universal

Autonomous experiment loop skill for Claude Code — port of pi-autoresearch

Score basis：Clear source · Risk needs review · Universal

Monitor all your Claude AI usage limits in real-time from your macOS menu bar - supports 5-hour, 7-day, extra usage, 7-day Opus and 7-day Sonnet quotas.

Score basis：Clear source · Risk needs review · Universal

GitHub Copilot in 70 lines of JavaScript

Score basis：Clear source · Risk needs review · Universal

Universal Render Pipeline Shaders for Smoke Lighting (Normal, 6-Way + ASTA Workflows) for VFX Graph and Shuriken

Score basis：Clear source · Risk needs review · Universal

This is a ComfyUI plugin that makes it easier to call and run workflows from RunningHub in your local ComfyUI setup.

Score basis：Clear source · Risk needs review · Universal

Dropbox LLM Security research code and results

Score basis：Clear source · Risk needs review · Universal

19 production-ready Claude Code plugins: git workflows, code review, spec-driven development, architecture patterns, resource optimization, and multi-LLM delegation

Score basis：Clear source · Risk needs review · Universal

Claude Code plugin for Elixir/Phoenix/LiveView — 20 specialist agents, Iron Laws enforcement, and Tidewave MCP integration.

Score basis：Clear source · Risk needs review · Universal