obliteratus Skill
OBLITERATUS: abliterate LLM refusals (diff-in-means). Published by NousResearch in hermes-agent.
Decision snapshot
Is this a fit?
Data analysis, Design and media, Includes SKILL.md, Reusable instructions
Compatibility not yet detected.
Permission behavior not yet detected.
Copy skill directory
21 days ago · MIT license
No specific cautions were detected. Review the source and requested permissions before installing.
What is obliteratus Skill?
OBLITERATUS: abliterate LLM refusals (diff-in-means). Published by NousResearch in hermes-agent. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement. See how SkillIndex evaluates profiles.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Data analysis
- Design and media
- Data analysis use cases
- Design and media use cases
Declared skill metadata
- Declared author: Hermes Agent
- Declared license: MIT
- Source file: optional-skills/mlops/obliteratus/SKILL.md
These fields retain source and confidence evidence from the indexed SKILL.md.
Compatibility and setup
- Install or run with Copy skill directory
When to use obliteratus Skill
- Use it for data analysis.
- Use it for design and media.
Built with
Editorial notes
Source
- Creator: NousResearch
- Repository: NousResearch/hermes-agent
- Skill file: optional-skills/mlops/obliteratus/SKILL.md
What it does
OBLITERATUS: abliterate LLM refusals (diff-in-means).
Skill instructions
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 be
Verified compatibility and discovery
Frequently asked questions
What is obliteratus?
obliteratus is a open-source AI agent skill with Copy skill directory. OBLITERATUS: abliterate LLM refusals (diff-in-means).
Who is obliteratus best for?
obliteratus is best for reusing agent instructions, scripts, and references, data analysis workflows, design and media workflows.
How do I install obliteratus?
Install or run obliteratus using Copy skill directory. Check obliteratus for the latest setup command.
Is obliteratus actively maintained?
obliteratus may need a closer maintenance check before production use.
Project health auto-fetched from the source repository.
Maintain this resource?
Review this source-backed profile, send a correction with evidence, or link to it from your documentation. Claims verify your relationship to the project; profile facts still require source evidence and editorial review.
