slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
Unlike traditional pipeline-based pentest skills, it uses a state machine with feedback loops, hypothesis-first validation, and disprove-to-generate-new-hypotheses logic, enabling adaptive and evidence-driven testing.
Who it is for
- Penetration testers
- Red team operators
- Security researchers
- Claude Code users interested in offensive security
Use cases
- Web application penetration testing (CDN bypass, API fuzzing, GraphQL, etc.)
- Active Directory and internal network lateral movement with OPSEC
- Cloud environment security assessment (container escape, K8s, IAM)
- EDR evasion and C2 obfuscation testing
Strengths
- State machine with feedback loops allows revisiting earlier phases based on new findings
- Hypothesis-first approach reduces blind tool usage and improves accuracy
- Comprehensive attack surface covering Web, AD, Cloud, Database, Reverse Engineering, and Evasion
- Engagement Tracker with Active/Confirmed/Killed states and evidence per finding
Considerations
- Requires Claude Code environment and the skill's installation procedure
- Dependency on external tools (e.g., nmap, sqlmap) and their proper configuration
- Explicitly requires authorized use only; not suitable for unauthorized testing
README quick start
使用方式
Description
Claude Code RedTeam Skill — Hypothesis-Driven Cognitive Architecture。一个假设-证据驱动的红队skill
Related repositories
Similar projects matched by category, topics, and programming language.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.
makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.