35 packages found
A Claude Code skill bundle for bug hunting and external red-team work — 71 skills, 15 slash commands, 681 disclosed-repo
[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Po
Query your AWS environment with natural language.
Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to i
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Codex into a s
Tool-native dataset generation skill for Codex, Claude Code, and Antigravity with SFT/DPO pipelines, verification, dedup
AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate solutions,
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a stru
Zac's collection of Claude Code skills for development workflows, testing, and quality assurance
Adversarial multi-model reasoning verification MCP server for AI agents. Claude, Grok, and DeepSeek challenge each decis
ZAP1 attestation and proof-verification MCP for Zcash agents. Attestation layer, not a wallet.
MCP server for multi-round AI brainstorming debates between multiple models (GPT, DeepSeek, Groq, Ollama, etc.)
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-deman
A curated list of Generative AI tools, works, models, and references
Practices, protocols, and skills for AI-driven software development. 18 skills + 1 Bash safety hook for Claude Code, Cod
@raddueClaude Code skills collection — build pipelines, TDD, debugging, code review, and more
18 mental models and critical thinking frameworks for Claude Code - First Principles, Bayesian, Systems Thinking, OODA,
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
Claude Code skill for autonomous, goal-directed iteration. /autoresearch <goal> builds a real-data benchmark harness, ca
GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
Claude Code skill for systematically reducing VirusTotal/EDR detection rates on compiled Go binaries via PE structural a
三竞赛 (CUMCM/MCM/电工杯) 数学建模 skill — harness-agnostic, 同时支持 Claude Code 与 Codex CLI, 全程问答式 (Friendly Mode), 10 阶段 + 4 反馈层 +
Claude Code skill for full-pipeline academic paper writing (IMRAD format, literature management, quality checklists)
mcp-gateway-scan
Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/
A decision operating system for high-stakes choices — business, strategy, career. Simulates disagreement, stress-tests a
⚠️ Experimentelle Skill-Sammlung für deutsches Recht (Arbeits-, Gesellschafts-, Insolvenz-, Datenschutz-, Prozessrecht u
Security, cost, and health governance proxy for MCP infrastructure — YAML policy engine, OAuth 2.1/OIDC, web dashboard,
The ultimate Claude Code optimization toolkit. 15 AI agents, 12 MCP servers, 17 hooks, autonomous token pipeline (60-99%
💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.
实战 SRC / 众测 / Bug bounty 漏洞挖掘 Claude Code skill — 19 个攻击类 playbook、305 个结构化 payload、263 个 WAF/EDR 绕过、2887 份 HackerOne 真实
一款基于各大企业信息API的工具，解决在遇到的各种针对国内企业信息收集难题。一键收集控股公司ICP备案、APP、小程序、微信公众号等信息聚合导出。支持MCP接入
Devil's advocate skill/plugin for Claude Code and Cowork: turns Claude against you to harshly critique an idea or whole