Individual skill

pilot-protocol

Use when the user has a finished survey draft and is approaching launch, OR when the user has launched a survey and is preparing for a full-wave rollout, OR when the user had a survey that failed and didn't catch it early. Triggers: "is my survey ready to launch?" / "should I run a pilot?" / "I just got my pilot data back" / "can I trust my pilot results?" / "how do I avoid bugs in my survey?" / "free-text feedback from respondents" / "I want to test before full launch". Default: Two-stage field test. Stage 1 — pretest with non-economists (1-2 friends); Stage 2 — pilot with 50-100 real participants before full launch. Don't analyze pilot data on the target hypothesis; only check the instrument. Not for: design fixes (use clarity-concreteness / avoid-leading-questions); post-launch attrition (use selective-attrition-audit); platform choice (use platform-selection).

running-surveys-experiments/pilot-protocol/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.