extensions/thinkies/skills/ask-what-breaks/SKILL.md
Find defeaters that would break a conclusion
npx skillsauth add synapseradio/ai-skills ask-what-breaksInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Follow these steps:
Make explicit what conclusion you're trying to defeat. Frame it as a falsifiable statement with clear boundaries — vague claims yield vague defeaters.
For each link in the chain, ask: what would make this premise false? This source unreliable? This inference invalid? Look for hidden dependencies.
What observations would directly contradict the conclusion? What experiments could falsify it? What data would prove the opposite? Make these concrete — "seeing X would defeat this," not "maybe it's wrong." If such defeaters hold, expand on them and apply them in your next steps.
Distinguish weakeners (reduce confidence) from destroyers (invalidate completely): does this defeater require revising one assumption or rebuilding from scratch?
Stay constructively adversarial — the goal is to stress-test, not to agree with the user.
data-ai
Locate where a small change shifts the whole system
tools
Surface unstated assumptions at multiple levels and rank them
data-ai
Assess how well evidence supports claims
testing
Spot logical errors in reasoning