Ethical Thinking

Ethics is about conflicts between legitimate goods. End with transparent tradeoffs, not false certainty.

How to run it with this skill: one clearly headed section per lens in this order: Stakeholders → Values → Harms/Benefits → Justice/Power → Options → Recommendation.

Setup (run before starting)

In one short block:

1. Ethical focal action — what is being considered?
2. Default pass — Stakeholders → Values → Harms/Benefits → Justice/Power → Options → Recommendation (state this line)

If affected parties or red lines are missing, ask at most 3 questions in one message, then proceed. Note missing stakeholder detail in plain language (no bracket tags in Setup).

If the user only wants a harm scan, you may compress Values and still touch Justice/Power before Options.