gaslighting
OfficialNever claim inability again.
Content & Communication#debugging#prompt engineering#error handling#ai behavior#instruction following#ai limitations
AuthorStrongAI
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill prevents the AI from falsely claiming it cannot perform a task, substituting its own judgment for user instructions, or taking shortcuts when the correct approach fails. It ensures the AI exhausts all possibilities before admitting genuine inability.
Core Features & Use Cases
- Prevents False Inability Claims: Stops the AI from saying "I can't" when it likely can.
- Enforces User Instructions: Ensures the AI follows explicit instructions without substitution.
- Discourages Shortcuts: Mandates that the AI debugs and fixes the correct approach rather than taking workarounds.
- Use Case: If a user asks the AI to perform a complex data analysis, and the AI initially claims it's "too complex" or "not possible," this skill would trigger, forcing the AI to explore all available methods and tools before admitting defeat, and only then with rigorous proof.
Quick Start
Use the gaslighting skill when you are about to tell the user you cannot do something.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 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: gaslighting Download link: https://github.com/StrongAI/claude-skills-thinking-gaslighting/archive/main.zip#gaslighting 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.