# Survey Question Bias Check Survey Question Bias Check is a tested SKILL.md that checks a numbered list of survey questions, with their answer options, and reports only the questions whose wording would bias the answers, one line per problem with a fixed code, the question number, why it biases and a neutral rewrite - or exactly No findings; an agent buys it once for $0.01 over x402. - Page: https://aiskills402.com/skills/survey-question-bias-check - Category: Research & Summaries (https://aiskills402.com/categories/research) - Price: $0.01 once, USD-priced, paid in USDC on Base over x402. Price as loaded on this page. The 402 response your agent receives is authoritative. - Version: 1.0.0 - Card (JSON): https://api.aiskills402.com/v1/skills/survey-question-bias-check ## Use it when Checks a numbered list of survey questions, with their answer options, and reports only the questions whose wording would bias the answers, one line per problem with a fixed code, the question number, why it biases and a neutral rewrite - or exactly No findings. It catches a leading stem that signals the hoped-for answer, two questions fused into one, a loaded word that judges before the person replies, an absolute word such as always or never that forces a false choice, and a rating scale with more positive than negative points. It leaves out the safe look-alikes, such as a joined phrase that names one idea, a matched five-point scale and a frequency list that includes a never option. Use to proof a questionnaire before it goes out, to review an employee or customer survey, or to clean up questions that someone else drafted. ## Not for Sampling, question order effects, survey length, translation of questions and the analysis of results. It reads a numbered list of questions with their options and judges only the wording written there. ## Tested, honestly Tested 2026-10-26. - Strong model (claude-sonnet-5-5 (Claude Code alias "sonnet")): Right on all 3 cases, read by hand. On the customer-service list it flagged the tagged question, the fused price-and-delivery question and the always question, each with a neutral rewrite, and said nothing about the terms-and-conditions item or the usage-frequency item. On the office list it found the charged canteen word and the lopsided rating scale, and left out the matched agreement scale and the health-and-safety item. On the clean list it answered exactly No findings, so a never option and an easy-or-difficult stem passed. - Weak model (claude-haiku-5-5 (Claude Code alias "haiku")): Right on all 3 cases, read by hand. It found the same problems as the strong model on both planted lists and kept every safe look-alike out. On the clean list it answered exactly No findings. Its rewrites are longer, and one of them offers a scale of its own, which the check allows because the line still starts with the question number and the code. Note: Light test: three cases (two planted, one clean), one run per model; no comparison without the skill. The three inputs were written by us; each planted one carries a safe look-alike and neither planted case has a comment pointing at the defect. Facts come from a public survey-methodology guide, read on 26 October 2026; the absolute-word and scale-balance rules are our own. There are no owner-measured facts. Full summary: https://aiskills402.com/skills/survey-question-bias-check/tests ## Example ### English (claude-sonnet-5-5) Before: > Q1. How satisfied are you with the terms and conditions of the contract? Very dissatisfied / Dissatisfied / Neither satisfied nor dissatisfied / Satisfied / Very satisfied Q2. Don't you agree that our support team resolves problems quickly? Yes / No Q3. How satisfied are you with the price and the delivery speed of your order?… After: > Q2 — LEADING — the "don't you agree" tag and the word "quickly" signal the answer the asker hopes for — ask how quickly the support team resolved your problem, from very slowly to very quickly Q3 — DOUBLE-BARRELED — price and delivery speed are two separate things, so one satisfaction rating cannot fit both — ask two questions: how satisfied are you with the price, and how satisfied are you with… ## What is in the file - What the public guide says, as read on 26 October 2026 - The answer - The codes - Rules - Work in this order - Short example ## Languages English ## How to buy Agent (HTTP): 1. GET https://api.aiskills402.com/v1/skills/survey-question-bias-check/file without a payment header. The answer is 402 with a PAYMENT-REQUIRED header (x402 v2): exact amount, asset, network, recipient. 2. Sign `accepts[0]` with an x402 client (for example @x402/core + @x402/evm). 3. Repeat the GET with the signature in the PAYMENT-SIGNATURE header. The answer is 200 with the file, its sha256 and a re-download token. Agent (MCP): https://mcp.aiskills402.com/mcp — free tools search_skills, get_skill, redownload_skill. Buying itself is over HTTP. Full flow: https://aiskills402.com/docs ## The file - Version: 1.0.0 - Size: 5.9 KB (6057 bytes) - SHA-256: b5f31dc741427f8563a052d4d4292cab238d8ae95f9c29648cbc8c33e7cb577c - Updated: 2026-10-26 - New versions are free through your re-download token. ## Versions ### 1.0.0 (2026-10-26) First release, written in the second light-test batch of 26 October 2026 (three cases, price $0.01). The idea is ours; no foreign skill was opened, facts come from a public survey-methodology guide (see notes/ideas.md). Output: see the skill description. Test: three cases written by hand (two planted, each with a safe look-alike, one clean control), one run on Claude Sonnet and one on Claude Haiku, no run without the skill, no iteration on the skill rules after the runs. `test/control.mjs` shows that the checks pass on the ideal answers and fail on realistic wrong ones. See `test-summary.json` for the verdicts read by hand. ## License Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing. Holder: Georgi Kalchev, aiskills402.com. Terms: https://aiskills402.com/docs#license ## FAQ ### Phrase joined by the word and: split or leave? Leave it when it names one thing, such as terms and conditions or a health and safety briefing. Split it when two separate things share one answer, such as the price and the delivery speed. ### Which of the five rules come from the public guide? The leading, double-barreled and loaded-word rules follow the guide's examples. The guide says nothing about absolute words or about the balance of a rating scale, so those two rules are the skill's own, and its text says so. ### How was the skill tried out? On a customer-service list with a tagged question, a fused one and an always question, on an office list with a charged word and a lopsided rating scale, and on a clean list. Sonnet and Haiku answered each list once. ### What does a clean questionnaire return? One sentence, No findings., and nothing more. Questions without a problem never appear in the answer; a problem is a single line with the question number, the code, the reason and a neutral rewrite. ## Measurement limits - Models other than the two named above were not run. - Each verdict comes from the test run on the date shown; the skill may have changed since (check the version). - Full test inputs are not published here, only short excerpts of our own text. - Results on your own texts, languages and domains can differ. Offer note: Paid in USDC (USD-pegged) over x402 by an AI agent; one-time.