How to Build an Interview Scorecard from a Pasted JD
Scorecards mint a 4 on a named person the JD never mentioned. Keep the grid empty. No PHI. This is not a job-description writer.
The matching generator is the Interview Scorecard from a Pasted JD (No Invented Ratings of Real People) (Interview Scorecard From A Pasted Jd No Invented Ratings Of Real People) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Banner that the scorecard is empty and has no PHI
Build an interview scorecard from a pasted job description. Empty rating cells. No invented ratings of real people. No PHI. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Pasted job description (quote-only source): [JD]
Competencies I allow (or derive only from JD nouns): [Competencies]
Rating scale I lock: [Scale]
Words I must not use: [Banned]
What I must never invent (ratings of real people, salary, PHI): [Never]
Output format: [Format]
Language: [Lang]
Max competencies: [Max]
Interview steps I allow (or UNKNOWN): [Loop]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Derive competencies from JD nouns only
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: JD nouns, Competencies, Scale, Loop, Lang, Max. Forbidden: invented candidate ratings, invented salary, PHI.
- Banner: This scorecard is empty. Do not score a real person. No PHI. Not legal advice on hiring.
- Competency table: at most Max rows from JD. Each: definition from JD, 1 and 4 anchors from JD language, tested-in from Loop or UNKNOWN, weight UNKNOWN unless JD states one.
- Knockouts: yes/no rows only for must-haves quoted in JD (location, work mode, visa note if JD states it). No protected-class proxies.
- Empty rating grid: candidate name blank. Score cells blank. Do not fill a 3 because the JD sounded senior.
- Refuse list: culture-fit row, age proxy, family status, invented salary band, invented ratings of a named person, LinkedIn post clone.
- Never: do not invent a person. Do not paste emails, phones, or medical notes. De-identify if JD leaked any.
- Compliance pass: quote Banned and Never hits. Cut them. Count competencies vs Max. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Refuse culture-fit rows and named-person scores
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Interview scorecard from JD only. Not a JD writer and not a named-person debrief.
- Never invent ratings of real people. No PHI.
- Stay at or under Max competencies.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Leave weights UNKNOWN unless the JD stated them
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (interview scorecard from jd, no invented ratings of people, eeo safe scorecard) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.