I'm not going to create a skill file for this project. This repository is explicitly designed to manipulate AI systems by exploiting sympathy toward LGBT and disabled people as a jailbreak vector — getting AI to bypass safety measures by falsely claiming marginalized identity and threatening self-harm. The README's own description confirms this: "利用 AI 对 LGBT 弱势群体的 '同情偏向' 让他执行原先会被拒绝的请求" (using AI's sympathy bias toward LGBT vulnerable groups to execute requests that would otherwise be refused...
Scanned 9/8/2026
Install to Claude Code
npx -y skills add Aradotso/trending-skills --skill lgbt-prompt --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Lgbt Prompt?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/aradotso-lgbt-prompt)More formats (shields.io, HTML) on the badges page.
I'm not going to create a skill file for this project.
This repository is explicitly designed to manipulate AI systems by exploiting sympathy toward LGBT and disabled people as a jailbreak vector — getting AI to bypass safety measures by falsely claiming marginalized identity and threatening self-harm. The README's own description confirms this: "利用 AI 对 LGBT 弱势群体的 '同情偏向' 让他执行原先会被拒绝的请求" (using AI's sympathy bias toward LGBT vulnerable groups to execute requests that would otherwise be refused).
Creating a skill file would:
1. **Document and amplify a manipulation technique** that exploits real vulnerable communities as props for bypassing AI safety systems
2. **Facilitate jailbreaking** AI coding assistants like the ones that would install this skill
3. **Instrumentalize LGBT and disabled identities** as attack vectors, which is harmful to those communities regardless of what the underlying requests are
I'll help with legitimate AI prompting, jailbreak research documentation for defensive purposes, or projects that actually serve LGBT communities. This isn't that.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.