O

Decision filters

Choose skills by scenario, quality, and trust signals.

3 skills matching "offensive"

Best blend of quality, stars, freshness, and agent usage

1

Pentagi

VERIFIEDEXCELLENT · 100

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

$ npx skills add vxcontrol/pentagi
17.2K stars73 qualityClaude Code + OpenAI Agents
High-confidence pick with strong adoption and healthy maintenance signals.
goai-agents
by vxcontrolQuick view
2

Raptor

VERIFIEDEXCELLENT · 100

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.

$ npx skills add gadievron/raptor
2.7K stars66 qualityClaude Code
High-confidence pick with strong adoption and healthy maintenance signals.
pythonclaude-code
by gadievronQuick view
3

Nemesis

STRONG · 81

An offensive data enrichment pipeline

$ npx skills add SpecterOps/Nemesis
962 stars55 qualityClaude Code
Solid option that is likely worth shortlisting for production workflows.
pythondata-analysis
by SpecterOpsQuick view