extensions/openai/thinkies/skills/evaluate-evidence/SKILL.md
Assess how well evidence supports claims
npx skillsauth add synapseradio/ai-skills evaluate-evidenceInstall 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:
State what is being asserted with enough specificity to be testable. Separate bundled claims into distinct assertions.
Catalog what evidence is actually offered:
Actively seek contradicting evidence, alternative explanations for the same observations, and relevant evidence that may have been omitted.
Identify what assumptions must hold for the claim to be valid, and what additional evidence would meaningfully strengthen or weaken it.
data-ai
Locate where a small change shifts the whole system
tools
Surface unstated assumptions at multiple levels and rank them
testing
Spot logical errors in reasoning
data-ai
Detect when further effort yields little gain