Agent skill · software engineering · nousresearch
obliteratus
OBLITERATUS: abliterate LLM refusals (diff-in-means).
Why this skill is useful
Adds 9 CLI methods and 28 analysis modules for surgically removing refusal behaviors from LLMs, which are not available in public documentation.
What it needs
Requires accelerate, bitsandbytes, obliteratus, safetensors, torch, transformers installed locally. About 8k tokens when loaded. Last updated 2026-08-07. 226,679 stars on the source repository.
What this skill does
OBLITERATUS Skill What's inside 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Remove refusal behaviors (guardrails) from open-weight LLMs without retraining or fine-tuning. Uses mechanistic interpretability techniques — including diff-in-means, SVD, whitened SVD, LEACE concept erasure, SAE decomposition, Bayesian kernel projection, and more — to identify and surgically excise refusal directions from model weights while preserving reasoning capabilities. License warning: OBLITERATUS is AGPL-3.0. NEVER import it as a Python library. Always invoke via CLI (obliteratus command) or subprocess. This keeps Hermes Agent's MIT license clean. Video Guide Walkthrough of OBLITERATUS used by a Hermes agent to abliterate Gemma: https://www.youtube.com/watch?v=8fG9BrNTeHs ("OBLITERATUS: An AI Agent Removed Gemma 4's Safety Guardrails") Useful when the user wants a visual overview of the end-to-end workflow before running it themselves. When to Use This Skill Trigger when the user: Wants to "uncensor" or "abliterate" an LLM Asks about removing refusal/guardrails from a model Wants to create an uncensored version of Llama, Qwen, Mistral, etc. Mentions "refusal removal", "abliteration", "weight projection" Wants to analyze how a model's refusal mechanism works References OBLITERATUS, abliterator, or refusal directions Step 1: Installation Check if already installed: If not installed, clone and install from GitHub: IMPORTANT: Confirm with user before installing. This pulls in ~5-10GB of dependencies (PyTorch, Transformers, bitsandbytes, etc.). …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nousresearch/obliteratus