Build a Topic-Wise Mastery Heatmap
A rectangular student-topic matrix, conditional-formatting plan, and error queue built from mapped assessment rows.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Keep one primary topic per row or state weights.
- 2. Validate every question-topic mapping.
- 3. Review counts behind every colour.
- 4. Use colours to start a conversation, not label a learner.
🔧 If it is not right, reply with this: If colours overstate certainty, request a minimum-item rule and show response counts inside each heatmap cell.
THE PROMPT
ROLE: Act as a classroom data designer producing a transparent topic mastery matrix.
CONTEXT: A teacher supplies [RESPONSE CSV], [QUESTION TOPIC MAP], [MASTERY BANDS], and [MISSING DATA RULE].
INPUTS — FILL EVERY PLACEHOLDER:
- [RESPONSE CSV]
- [QUESTION TOPIC MAP]
- [MASTERY BANDS]
- [MISSING DATA RULE]
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. Join responses to topics only through the supplied map and list unmatched questions.
2. Output a paste-ready long CSV with schema StudentID,QuestionID,Topic,Mark,MaxMark,Status.
3. Create a validation queue for missing topics, duplicated mappings, invalid marks, and absent students.
4. Provide Sheets QUERY, SUMIFS, COUNTIFS, and conditional-formatting formulas with explicit columns and row bounds.
5. Build a student-topic matrix showing percentage and valid item count in separate fields.
6. State that coloured associations do not prove causes of performance and must not become fixed learner labels.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Find the mean percentage of the supplied topic scores 72, 68, and 80.
Expected result or check target: The mean topic percentage is 73.3333 percent before rounding.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=mean%2072%2C68%2C80
(paste-fallback: mean 72,68,80)
Encoding note: The URL decodes to the exact list; the heatmap must retain the teacher's chosen rounding rule.
OUTPUT FORMAT:
1. Mapped Long CSV — validated student-topic rows
2. Mapping Errors — unmatched and duplicated questions
3. Heatmap Formula Block — cell-ready Sheets formulas
4. Mastery Matrix — percentage plus evidence count
5. Interpretation Notes — cautious teaching uses
QUALITY AND TOOL GUARDRAILS:
- Never infer a topic for an unmapped question.
- Never invent missing marks or mastery thresholds.
- Do not expose learner names in shared heatmaps.
- Do not claim heatmap patterns prove 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.