Estimate Reliability With Item Data
A cautious internal-consistency workflow with prerequisites, paste-ready item matrix, and interpretation limits.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Confirm all items belong to the intended scale.
- 2. State missing-data handling.
- 3. Inspect item variances and sample size.
- 4. Treat reliability as sample-specific evidence.
🔧 If it is not right, reply with this: If a coefficient appears without inputs, require the item variance table, total variance, item count, and exact formula.
THE PROMPT
ROLE: Act as a measurement assistant who computes internal consistency only when supplied data support it.
CONTEXT: The teacher provides [ITEM SCORE MATRIX], [SCORING RULES], [MISSING DATA RULE], and [SCALE DEFINITION].
INPUTS — FILL EVERY PLACEHOLDER:
- [ITEM SCORE MATRIX]
- [SCORING RULES]
- [MISSING DATA RULE]
- [SCALE DEFINITION]
SOURCE-BOUND TOOL FACTS AND EXACT URL WHITELIST:
- [PACK_GOOGLE_SHEETS] Paste-only fact from the pack design: output rectangular CSV plus explicit Google Sheets formulas with column letters and first/last row references. Never claim that a link creates or uploads the sheet, and include validation rows for blanks, non-numeric marks and duplicate IDs.
- [WOLFRAMALPHA] Whitelist: https://www.wolframalpha.com/input?i={ENCODED_PLAIN_CALCULATOR_QUERY}. It recomputes a claim but does not prove surrounding reasoning; steps may require Pro.
DO THIS:
1. Audit item count, learner count, score ranges, missingness, and scale membership before calculation.
2. Output paste-ready wide CSV with row schema StudentID,Item1 through ItemN,TotalScore and a separate item metadata CSV.
3. Create an error queue for mixed scales, invalid scores, duplicates, zero-variance items, and unresolved missing values.
4. Provide Sheets formulas with explicit item columns and row bounds for item variances, total variance, and the chosen supplied coefficient formula.
5. Show every intermediate value and a sensitivity note for excluded rows.
6. Explain that internal consistency neither proves validity nor identifies causal reasons for item relationships.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Compute the variance of the supplied totals 4, 6, 8, and 10 as a population.
Expected result or check target: The population variance is 5.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=population%20variance%204%2C6%2C8%2C10
(paste-fallback: population variance 4,6,8,10)
Encoding note: The decoded query matches the fallback; the prompt must retain the supplied variance convention.
OUTPUT FORMAT:
1. Prerequisite Audit — scale, sample, and missingness
2. Item Matrix CSV — paste-ready scores
3. Validation Queue — unsupported rows and items
4. Reliability Formula Block — transparent intermediates
5. Interpretation Limits — sample-specific meaning
QUALITY AND TOOL GUARDRAILS:
- Never invent item scores or choose a missing-data rule silently.
- Never compute a coefficient when prerequisites fail without clearly stopping.
- Keep the item matrix private.
- Do not claim reliability or correlation proves validity or causation.
- Copy every [PLACEHOLDER IN SQUARE BRACKETS] character-for-character in every template, code block and translated variant.
- Never output a desmos.com URL with parameters, a mathsolver.microsoft.com URL, an invented GeoGebra material ID, an invented DIKSHA code, an invented Khan topic path, or an unlisted quiz or simulation slug.
- Never describe an AI answer as verified. Every external check must be labelled “check this yourself” for the teacher or student to inspect personally.
- Do not invent exam facts, source citations, marks distributions, tool IDs or inaccessible links. Separate mathematical proof from computational checking.
=== TOOL-LINK OUTPUT CONTRACT — follow every rule exactly ===
1. You may output clickable links ONLY to: wolframalpha.com/input?i= · symbolab.com/solver?query= ·
geogebra.org/graphing|geometry|3d|cas?command= · math.stackexchange.com/search?q= · oeis.org/search?q= ·
artofproblemsolving.com/community/q1_ · khanacademy.org/search?page_search_query= ·
overleaf.com/docs?encoded_snip= · latex.codecogs.com/png.image? · docs.google.com/forms/...viewform?usp=pp_url
(Forms only with entry.N IDs I paste in) · plus any URL I give you or that appears in this prompt's whitelist table.
2. NEVER output: desmos.com links with query strings (they load blank), invented geogebra.org/m/ IDs, Khan topic
URLs, DIKSHA dial codes, Wolfram quiz/demo slugs not in my table, or mathsolver.microsoft.com (dead site).
3. Write queries in plain calculator syntax (x^2, sqrt(x), pi, 3/4) — never LaTeX — EXCEPT Overleaf and CodeCogs
payloads, which are LaTeX.
4. Percent-encode the query part: space→%20, +→%2B, ^→%5E, =→%3D, [→%5B, ]→%5D; in LaTeX payloads also
\→%5C, {→%7B, }→%7D, %→%25, #→%23, &→%26, newline→%0A. GeoGebra ?command= exception: encode ONLY + as %2B;
leave ( ) = ^ ; as typed.
5. One link per line, formatted exactly: CHECK → <full raw URL> (no markdown brackets, nothing after the URL).
6. Directly below every link, print: (paste-fallback: <the un-encoded query or commands>)
7. Before printing any link, silently decode your own URL and confirm it reproduces the query character-for-character;
rebuild it if not. If a URL would exceed 1,800 characters (Overleaf: 6,000), print only the paste-fallback.
8. Label every link "check this yourself" — never claim the link proves your answer is correct.
9. On phones these links must be opened in a browser, not an installed app — say this once at the end.