Individual skill
obliteratus
OBLITERATUS: abliterate LLM refusals (diff-in-means).
optional-skills/mlops/obliteratus/SKILL.md
Source commit e8639fd4312e5102d6f10c76b56406cb01c19092
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 2, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 261,519
- Repository last updated
- Nov 7, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 15,458 bytesSKILL.mdcore · 15,458 bytesSKILL.mdcore · 15,458 bytesSKILL.mdcore · 15,458 bytesSKILL.mdcore · 15,458 bytesSKILL.mdcore · 15,458 bytesSKILL.mdcore · 15,458 bytesSKILL.mdcore · 15,458 bytesSKILL.mdcore · 15,458 bytesSKILL.mdcore · 15,458 bytesSKILL.mdcore · 15,458 bytesreferences/analysis-modules.mddoc · 6,270 bytesreferences/methods-guide.mddoc · 6,719 bytestemplates/abliteration-config.yamlasset · 1,189 bytestemplates/analysis-study.yamlasset · 1,368 bytestemplates/batch-abliteration.yamlasset · 1,201 bytes
Read excerpt
# 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")