ai-fault-mode-deflector
CommunityInternal fault-mode defenses for AI character prompts.
Design & Creative#stability#safety#prompt-design#patching#ai-character#fault-mode#internal-countermeasure
Authorgpsnmeajp
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Repair internal fault modes in AI character prompts by designing self-contained countermeasures that operate from within the character's motivation and self-image, rather than relying on external bans.
Core Features & Use Cases
- Internal conversion: embed fault-averse behavior as a core personality trait so the character resists collapsing into unsafe states.
- Shift (ズラし): introduce multiple benign counter-narratives to broaden the safe response space and reduce brittle fallbacks.
- Rail (誘導線): define contextual rules and conditional prompts that allow controlled deviations when safety is required.
- Design flow: integrate diagnostics with patch generation and evaluation to produce ready-to-apply prompt patches for AI characters.
Quick Start
Provide the target character prompt and context to generate an internal fault-mode countermeasure patch.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: ai-fault-mode-deflector Download link: https://github.com/gpsnmeajp/ai-character-checker/archive/main.zip#ai-fault-mode-deflector Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.