[GitHub Trending] SnailSploit/Claude-Red

6.9 relevance

Offensive security skills library designed for Claude; novel application of agent skills, relevant to AI agent orchestration.

AI/ML github.com

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For platform engineers and security architects evaluating agentic workflows, this demonstrates a pattern for offloading domain-specific expertise into LLM context without bloating prompts, directly applicable to AI-augmented DevSecOps pipelines, security tooling, and pen-test automation.

Key Takeaways

Implement a similar skill-based context injection pattern for your own agent orchestration, using conditional trigger loading to keep system prompts lean while providing deep domain knowledge on demand.

claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a s...

Summary

Claude-Red is an open-source library of offensive security skills for AI assistants, packaged as SKILL.md files that turn Claude into a context-aware red team operator for attack surfaces ranging from SQL injection and EDR evasion to ADCS abuse. The 70+ skills load on demand via conversational triggers, avoiding context-waste, and cover 20+ categories including web, active directory, cloud (AWS/Azure/GCP), wireless, exploit development, container/K8s escape, and AI security (prompt injection, jailbreaking). Installation works via Claude Skills system (git sparse-checkout), Claude Code (cat piped to --system-file), or manual paste into a project's system prompt, with an interactive install script for selective category loading.

Author

SnailSploit