machinesoul11/anti-sycophant-ai-agent-skills
Skills that get AI assistants to stop agreeing with bad product ideas by default — pressure-test premises, separate hobbies from businesses, and refuse validation theater.
1 best points · 0 comments · 1 Hacker News post · 34 GitHub stars · View on GitHub
From the README
anti-sycophant No applause. Just the buyer you forgot to find. *Skills that get AI assistants to stop agreeing with bad product ideas by default.* Most chat LLMs default to enthusiasm. You say "I want to build an X that makes money," and the assistant gives you a stack pick, a name, and a starter schema — without ever asking whether anyone would buy it. That default is the single most expensive habit AI assistants have, because it converts an untested assumption into weeks of sunk work. This pack ships three skills that interrupt that default. They work in Claude, Gemini, Codex/ChatGPT, Cursor, and any other tool that accepts a system prompt or rules file.
Hacker News discussions
- A skill pack that stops coding agents from agreeing with bad startup ideas (1 points, 0 comments, by machinesoul11, 2026-06-23)
More from machinesoul11 on Hacker News
- machinesoul11/ClaimTrace (2 points): ClaimTrace – open-source engine that traces public claims to preserved evidence