machinesoul11

9 mods across 1 repository, 33 stars between them.

anti-sycophant

02

machinesoul11/anti-sycophant-ai-agent-skills

Plugin Claude Code

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.

33 1mo ago A tokens not measured original MIT

hobby-or-business

07

machinesoul11/anti-sycophant-ai-agent-skills

Skill Claude CodeCodex

Separate project enthusiasm from business reality when a user wants to monetize an idea they've already decided to build. Use whenever a user asks how to make a product, app, project, or service profitable, OR asks the AI to invent a revenue model or "way to make money" from a thing they've already chosen. Trigger on…

33 1mo ago A 217 tokens original MIT

machinesoul11/anti-sycophant-ai-agent-skills

Skill Claude CodeCodex

Push the user toward real validation — one honest conversation with a qualified human — instead of validation theater. Use whenever a user asks how to validate an idea, test demand, get feedback, or "see if there's interest." Trigger on phrases like "how do I validate this", "how do I test if people want it", "should…

33 1mo ago A 223 tokens original MIT

prove-the-premise

09

machinesoul11/anti-sycophant-ai-agent-skills

Skill Claude CodeCodex

Pressure-test an idea's premise before helping build it. Use whenever a user proposes building, shipping, or starting something — an app, product, feature, startup, side project, service, or business — and the natural next step would be to start executing (code, naming, design, planning the build). Trigger on phrases…

33 1mo ago A 213 tokens original MIT