#149149th of 455 in Skills, plugins and prompts
claude-red
Offensive security SKILL.md library for Claude
- Stars
- 9.8k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Aug 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
claude-red is a collection of 78 SKILL.md files that prime Claude with expert methodology for specific attack surfaces, from SQL injection and XSS to ADCS abuse, EDR evasion and wireless protocol attacks. Skills load on demand based on conversational triggers, so Claude only consumes context for the domain actually being discussed. Intended for authorized red team engagements, bug bounty work, CTF prep and security research rather than general-purpose coding.
Who it is for: Authorized red teamers, bug bounty hunters and security researchers using Claude
Strengths
- 78 skills across 23 categories covering web, AD, wireless, cloud, mobile and exploit dev
- Skills load on demand by trigger, avoiding permanent context overhead
- Sparse-checkout and install script let you pull only the categories you need
- MIT licensed and actively maintained with a stated roadmap toward ~130 skills
Weaknesses
- No code or tooling of its own, only prompt/methodology files for an LLM
- No Docker or compose setup, install is manual git clone or shell script
- Effectiveness depends entirely on Claude's own capability, not tested automation
- Content is purely instructional text with no verification of accuracy claims
What it needs
- no GPU
- Needs Claude (Claude.ai, Claude Code, or Claude Skills system)
- Models: Claude
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |