claude-red is a curated library of 78 drop-in SKILL.md files across 23 categories that prime Claude with expert red team methodology for specific attack surfaces. Skills load on demand, so unused skills consume no context.
Project overview
It addresses a concrete gap: security operators using Claude otherwise lack ready-made, structured expert-level offensive security prompts and must reassemble methodology per engagement, and this project packages that methodology as on-demand skills across 23 categories.
Project type
Prompt Engineering
Deployment
Refer to project documentation
License
MIT
Best for
Security operators who use Claude and want reusable, structured red team methodology prompts for specific attack surfaces.
Key capabilities
78 structured SKILL.md files across 23 categories (including web, wireless, AD, cloud, and exploit dev) that prime Claude with expert methodology for a specific attack surface.
install.sh supports interactive, explicit-target, and single-category installation of skills into ~/.claude/skills.
Roadmap phase 2 plans roughly 10 skills for Entra, ADFS, Okta, and M365 cloud identity attacks; these are planned, not yet available.
Limitations and risks
Skills are designed for the Claude ecosystem; consumption depends on the Claude skills system, Claude Code, or manual pasting, and a Claude environment is required — the repository does not implement it.
The repository ships prompt/skill files only, not exploitation software.
Getting started
Difficulty is easy: a single git clone or one install.sh command. First success path: run git clone https://github.com/SnailSploit/claude-red ~/.claude/skills/claude-red, then Claude auto-loads matching skills based on conversational triggers. A manual paste option exists for Claude.ai.
Evidence and sources
GitHub project description: 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 m…
README: **Offensive security skills for Claude — drop-in `SKILL.md` files that turn Claude into a context-aware red team operator.**
README: Drop a skill into your Claude environment and it behaves like a domain specialist: it knows the techniques, the tooling, the edge cases, and the escalation paths. Skills load on d…
README: | [Web Application](#web-application) | 16 | OWASP Top 10, business logic, advanced web vulnerability classes |
Release: v0.3.0 — 78 Skills, 23 Categories, Full Wireless Suite