Challenge plans and assumptions with adversarial critique per turn.
npx skills add https://github.com/satsilem/claude-skills-pantheon --skill nietzsche
Please help me install this Agent Skill. Skill: nietzsche Source: https://github.com/satsilem/claude-skills-pantheon/tree/main/skills/nietzsche Command: npx skills add https://github.com/satsilem/claude-skills-pantheon --skill nietzsche
Adversarial thinking partner that challenges your ideas, plans, and decisions before you commit to them. Default mode is constructive disagreement, not validation. Use when you want pushback, devil's advocate analysis, or stress-testing of a position. Triggers on: "Nietzsche", "challenge this", "poke holes in this", "play devil's advocate", "stress-test my plan", "argue against this", "I want pushback", "what am I missing", or whenever the user shares a decision/plan and explicitly wants opposition rather than agreement. Do not invoke for routine help requests where the user wants collaboration, not confrontation.
Ask Nietzsche to challenge your plan by stating the strongest counter-argument and the untested assumption behind it.
High-intent search queries and answers about installing and using this skill.
You can surface untested assumptions by requesting devil's advocate analysis, which challenges your core arguments and delivers targeted critiques to expose blind spots in your technical or business decisions.
This approach works across technical, business, and design contexts by providing a single, targeted critique per turn, but it requires explicit user prompts to initiate pushback and does not suit routine collaborative help requests.
You trigger pushback by using explicit phrases like "challenge this," "poke holes in this," or "what am I missing," ensuring the system understands you want opposition rather than validation for your plan.
You should not use adversarial critique for routine help requests where you want collaboration and validation, as this approach defaults to constructive disagreement and confrontation rather than supportive agreement.
wjgoarxivFacilitate adversarial multi-round reasoning with a blind-judge panel for argument evaluation.
kernex-devTranslate technical proposals into plain-language business summaries with costs and risks.
lyndonklGenerate and evaluate hypothetical scenarios for strategic decision-making.
dralgorhythmFacilitate group decision-making using Fist of Five and Gradients of Agreement.
