Turn a Marking Scheme Into a Step Rubric
A mutually exclusive step rubric tied to a separately checked key, with caps, dependencies, and paste-ready scoring formulas.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Verify the model key first.
- 2. Keep each criterion observable.
- 3. State dependencies and maximum caps.
- 4. Pilot the rubric on a small anonymous sample.
🔧 If it is not right, reply with this: If marks can be counted twice, request a criterion-overlap audit and one evidence field per awarded criterion.
THE PROMPT
ROLE: Act as a marking-rubric designer who converts only the supplied scheme into observable step credit.
CONTEXT: The teacher provides [APPROVED KEY VERSION], [MARKING SCHEME], [QUESTION MAP], and [RUBRIC POLICY].
INPUTS — FILL EVERY PLACEHOLDER:
- [APPROVED KEY VERSION]
- [MARKING SCHEME]
- [QUESTION MAP]
- [RUBRIC POLICY]
SOURCE-BOUND TOOL FACTS AND EXACT URL WHITELIST:
- [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.
- [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.
DO THIS:
1. Confirm that every rubric row points to a separately verified approved-key entry.
2. Output paste-ready Rubric CSV with schema QuestionID,CriterionID,EvidenceRequired,Mark,Dependency,Cap,KeyVersion.
3. Create an exception queue for overlapping criteria, missing key references, inconsistent caps, and vague evidence.
4. Provide Sheets formulas with explicit columns for criterion awards, dependency checks, cap enforcement, and question totals.
5. Write a short marker decision rule for partial evidence and unsupported answers.
6. Keep all pilot scripts anonymous and separate rubric design from student identity.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Check that rubric components 2, 1, and 2 sum to a 5-mark cap.
Expected result or check target: The component total is 5 marks.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=2%2B1%2B2
(paste-fallback: 2+1+2)
Encoding note: Each plus sign is encoded as %2B and decodes exactly; the teacher still approves the rubric.
OUTPUT FORMAT:
1. Key Reference Audit — approved version and coverage
2. Rubric CSV — observable criterion rows
3. Overlap Queue — ambiguous and double-counted credit
4. Formula Block — dependencies, caps, and totals
5. Marker Notes — consistent evidence decisions
QUALITY AND TOOL GUARDRAILS:
- Never invent criteria or alter supplied mark values.
- Never use a rubric whose model key has not been verified separately.
- Never award the same mathematical evidence twice.
- Protect anonymous script evidence and remove personal details.
- 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.