Individual skill

relative-vs-absolute

Use when the user is analyzing/interpreting survey results and unsure what conclusions to draw. Triggers: "can I interpret this level?" / "is this probability meaningful?" / "my result is X%, can I claim Y?" / "respondents answered differently when I rewrote the question" / "is order of questions affecting my results?" / "my survey shows a level but only cross-condition comparison is interpretable". Default rule: Levels are framing-fragile (anchor/order/scale shifts can move them); relative comparisons (A vs. B) are robust as long as framing is held constant. Add benchmark items to upgrade relative → absolute. Not for: pre-launch design fixes (use clarity-concreteness); post-launch attrition issues (use selective-attrition-audit).

running-surveys-experiments/relative-vs-absolute/SKILL.md

Source commit 9a4b2db21fc4b217136ae4a0e6faad42d179ca03

What was checked

Matches the observed repository HEAD

Yes

Scanner rules are current

Yes

Repository scan complete

No

Skill scan complete

No

Observed behavior

Network or broad shell

Last checked

Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.