Obliteratus Abliteration
aradotso/trending-skillsOBLITERATUS is a tool that removes the safety guardrails from large language models. It uses a technique called abliteration to find and remove the specific directions in the model that cause it to refuse requests. You can do this with just one click.
The toolkit looks inside the model's hidden layers. It uses math to find the refusal directions. Then it removes those directions from the model's weights. The model keeps its core language abilities intact.
You can use OBLITERATUS from the command line, from Python code, or with a web interface. It works with models from HuggingFace. This is helpful for developers and researchers who want to experiment with model behavior.
Add Obliteratus Abliteration skill to your workflow
Global
mkdir -p ~/.claude/skills/obliteratus-abliterationProject
mkdir -p .claude/skills/obliteratus-abliterationSource Repository
More AI & Agent Building Claude Code Skills
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Skill Creatoranthropics/skills
Create, test, and improve AI agent skills with easy step-by-step guidance
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly
Openclaw Secure Linux Cloudxixu-me/skills
Secure self-hosting of OpenClaw with private control and SSH tunneling