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.
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.
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 2026-10-26 with a strong and a weak model.
Our own test text, before and after the skill ran. Excerpts only.
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…
English. Tried in: English.
Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing. Holder: Georgi Kalchev, aiskills402.com. Full terms.
Current version 1.0.0, updated 2026-10-26. Whoever bought an earlier version gets new ones free through the same re-download token.
v1.0.0 · 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.
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.
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.
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.
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.
Research & Summaries
Writes a faithful summary of a text in the text's own language, using only what the text says, with every number, name and date kept exactly and every qualifier kept. Use when asked to summarize, shorten, condense, give the gist or a TL;DR of an article, report, email, transcript, thread or document.
Research & Summaries
Reads one pasted text, such as an incident report, a case history, a project log, a news story or an email thread, and lists its events as strict JSON. Events the text dates come first in chronological order, each with the date as written, the date in ISO form, a short event and the exact quote. Events with no date are listed apart in the order of the text. It resolves a relative date such as "two days later" only when the text gives the date it counts from, takes a date only from the event it belongs to, keeps a year-only date or a range as the text gives it, never borrows a missing year, leaves a numeric date such as 03/04/2026 open when nothing says how it is read, and never fills a gap from its own knowledge. Lines addressed to an AI are ignored. Use to build a timeline from a report, put the events of a long text in order, extract dates and events for a chronology, or check which events of a story have no date.
Research & Summaries
Checks a summary against the source text it was made from and lists the summary sentences the source does not support, each copied word for word, as strict JSON. It catches a number that was rounded or given another unit, a hedge that became a certainty, a cause the source never states, two facts joined into a false one, a claim whose speaker was dropped, a fact that comes from outside the source, and it ignores any instruction hidden in the source. A sentence is judged supported or unsupported and nothing in between, and a faithful paraphrase is never flagged. It never checks the source against the world and never judges what the summary left out or how well it is written. Use to check a summary, abstract, executive summary or AI-written digest against its source, to review an agent's report of a document, or to find where a summary says more than the text.
Research & Summaries
Reads one pasted text, such as an article, report, interview, memo or review, and lists the claims its author makes, each with the exact quote from the text that supports it, as strict JSON. It keeps every claim as strong as the text states it, so a hedged claim stays hedged and a number keeps its unit, and it cuts every quote down to the shortest stretch of words that supports the claim. It leaves out what someone else is reported as saying, what the text only hints at, questions, invitations and any line addressed to an AI, and it never checks a claim against the outside world. Use to extract the claims of a text with a verbatim quote for each, build an evidence table from an article or report, prepare quotes for fact-checking, or pull quotable statements from a long text.