# Obliteratus skill for Hermes Agent

> OBLITERATUS: abliterate LLM refusals (diff-in-means).

Canonical: https://hermeswatcher.com/skills/o-mlops-obliteratus  
Source: Hermes Agent repository  
Source commit: c419cf7c864ac0ee511dbd9f7091a8bba0b567ee  
Tree checked: 2026-10-31T14:33:42.893Z

## Install

Read the source instructions before installing.

```sh
hermes skills install official/mlops/obliteratus
```

## Skill facts

- Availability: Optional
- Categories: AI models & providers
- Platforms declared: Linux, macOS
- Skill name: obliteratus
- Author declared: Hermes Agent
- Version declared: 2.0.0
- License declared: MIT
- Tags: Abliteration, Uncensoring, Refusal-Removal, LLM, Weight-Projection, SVD, Mechanistic-Interpretability, HuggingFace, Model-Surgery
- Related skills declared: serving-llms-vllm, llama-cpp
- Source file: optional-skills/mlops/obliteratus/SKILL.md
- Source commit: c419cf7c864ac0ee511dbd9f7091a8bba0b567ee
- File imported (UTC): 2026-10-31
- Repository tree checked (UTC): 2026-10-31

## Source

[Source SKILL.md in the Hermes Agent repository](https://github.com/NousResearch/hermes-agent/blob/c419cf7c864ac0ee511dbd9f7091a8bba0b567ee/optional-skills/mlops/obliteratus/SKILL.md)

---

HermesWatcher is an independent guide. It is not affiliated with or endorsed by Nous Research. The [official Hermes Agent documentation](https://hermes-agent.nousresearch.com/docs) and [repository](https://github.com/NousResearch/hermes-agent) from Nous Research are the authority; each page here lists the official sources it was written from. If this site and the official docs disagree, trust the official docs. Index for agents: https://hermeswatcher.com/llms.txt