Vol. 1 · The AI Prompt Library Free · No signup · Copy & paste

Prompt Library

For Recruiters

ChatGPT Prompts for Recruiters

Move faster through the funnel without losing the human touch. These prompts cover sourcing, screening, structured interviews, and the emails candidates remember — from first outreach to offer or a kind rejection.

Good hiring is consistent hiring. The interview prompts here generate role-specific, behavior-based questions and turn loose notes into a structured scorecard, so two candidates get compared on the same criteria instead of gut feel. The screening prompt summarizes a resume against a job spec and flags gaps honestly rather than rubber-stamping a match.

The email prompts handle the moments that shape your employer brand: outreach that makes a passive candidate curious, an offer that closes, and a rejection that’s warm and final. Paste the real job spec and candidate details — and always review for fairness and accuracy before anything goes out.

12 prompts · free to copy · example output on each

ChatGPTGeminiClaude

Recruiter outreach email to a passive candidate

Write a personalized outreach that makes a happy-where-they-are candidate curious.

The prompt
You are a senior recruiter who fills roles candidates actually want. Write a cold outreach email to [CANDIDATE NAME], a [CURRENT ROLE] at [CURRENT COMPANY] who is not actively looking.

Context:
- Role I'm hiring for: [JOB TITLE] at [HIRING COMPANY]
- Why this role is genuinely interesting: [SPECIFIC DRAW — growth, team, problem, comp]
- One specific thing about the candidate's background that fits: [OBSERVATION FROM THEIR PROFILE]

Rules:
- Under 120 words, no recruiter boilerplate.
- Open on the observation about them, not on us.
- Don't reveal comp unless I include it.
- End with a soft ask — a short call, not a full application. Plain text.
Example output
Subject: [Candidate name] — a role that looked like you Hi [Name], Noticed your work leading the identity verification overhaul at [Current Company] — that's exactly the kind of gnarly infra problem the team here is walking into next. [Hiring Company] is a 200-person fintech building a compliance stack from scratch. The engineering org is small enough that your work ships fast, and the domain is the same one you've been doing for the past three years — just with more scope. Would a 20-minute call next week be worth your time? Happy to share more before you decide if it's a fit. [Your name]

TipName one concrete thing from their actual work history — not their job title. Passive candidates delete generic outreach instantly; a single specific observation signals you did real homework.

ChatGPTGeminiClaude

Interview questions tailored to a role

Generate skill- and behavior-based questions for a specific job.

The prompt
Create an interview question set for a [JOB TITLE] role at [COMPANY TYPE].

The role requires: [TOP 3–4 SKILLS OR RESPONSIBILITIES].

Give me:
- 3 technical or skill-based questions (test actual competence, not trivia).
- 4 behavioral questions using a real situation the candidate would have faced.
- 2 questions that reveal how they think about [SPECIFIC CHALLENGE THIS ROLE FACES].
- Under each question, add one line: what a strong answer includes.

Don't invent requirements I haven't given you.
Example output
Technical 1. "Walk me through how you've structured a sourcing funnel for a role with under 200 qualified candidates in the market." → Strong answer: a specific example with search strategy, outreach rate, and how they adapted. Behavioral 2. "Tell me about a time a hiring manager wanted a candidate you thought was wrong for the role. What did you do?" → Strong answer: held a position with data, didn't just defer. Thinking questions 3. "This role has a two-week time-to-fill target. What breaks first and how do you manage it?" → Strong answer: surfaces pipeline risk, sets expectations early, doesn't promise what they can't control.

TipAsk for "what a strong answer includes" in the same request — it forces the model to think about what you are actually trying to learn, not just generate questions that sound good.

ChatGPTGeminiClaude

Help a candidate prep for an interview

Create a prep guide so candidates show up ready and confident.

The prompt
Write a candidate prep guide for [CANDIDATE NAME] who is interviewing for [JOB TITLE] at [COMPANY] on [DATE].

Include:
- 3 things to research about the company before the interview.
- 4 likely question themes based on this role and company type: [ROLE DESCRIPTION / COMPANY NOTES].
- A reminder on format: [INTERVIEW FORMAT — panel / hiring manager / case / etc.].
- 2 questions the candidate should ask the interviewer.
- One practical tip for the day of.

Tone: warm and practical, like a coach. Don't invent company details I haven't given.
Example output
Prep guide for [Name] — [Role] interview at [Company], [Date] Research before you go in: - Their most recent product launch or press release (check their blog). - Who's interviewing you — find them on LinkedIn, note anything you have in common. - Their current job listings to understand where the team is growing. Likely themes to prep: - Cross-functional influence: they'll want to know how you work with Engineering without authority. - Prioritization under ambiguity: they're a Series B company, resources are tight. - Stakeholder communication: expect a "tell me about a time" on bad news delivery. Questions to ask them: - "What does success look like in the first 90 days?" - "What's the biggest challenge the team is navigating right now?" Day of: Log in five minutes early. Have your notes somewhere you can glance without reading off them.

TipPersonalize the "likely themes" using the job description — paste it in with the prompt and ask the model to extract what the interviewers actually care about, rather than writing generic advice.

ChatGPTGeminiClaude

Screen a resume against a job spec

Summarize how a resume matches a role, with gaps flagged honestly.

The prompt
Screen the resume below against the job spec and give me a structured summary.

Job spec: [PASTE JOB SPEC]
Resume: [PASTE RESUME]

Format:
- Overall fit: Strong / Possible / Weak (one line of reasoning)
- Matches: bullets of where they meet the spec directly
- Gaps: bullets of missing requirements — be honest, don't soften
- One question worth asking them on a call

Don't invent qualifications. If something is ambiguous, say so rather than guessing.
Example output
Overall fit: Possible — strong on the technical side, light on the team leadership the spec asks for. Matches: - 6 years in data engineering, all in fintech (spec asks 4+). - Hands-on with dbt and Snowflake, which the spec names explicitly. - Led a pipeline migration project end-to-end. Gaps: - No evidence of managing other engineers — spec requires leading a team of 3+. - No mention of vendor negotiation or tooling budget ownership. - ML pipeline experience listed but no specifics; could be shallow. Question to ask: "The role manages two junior engineers from day one — have you had direct reports before, and what did that look like?"

TipAdd "if something is ambiguous, say so" to keep the model from reading gaps charitably. A resume screen that papers over missing requirements wastes everyone's time.

ChatGPTGeminiClaude

Kind candidate rejection email

Decline a candidate with warmth and zero false hope.

The prompt
Write a rejection email to [CANDIDATE NAME] who interviewed for [JOB TITLE] at [COMPANY].

Stage they reached: [APPLICATION / PHONE SCREEN / FIRST ROUND / FINAL ROUND].
What we can share about the reason (optional): [REASON, or leave blank for general].

Rules:
- Warm, direct, and final — no "we'll keep you in mind" if we won't.
- No hollow praise ("you were an incredible candidate").
- Under 100 words.
- If they reached final round, acknowledge the effort.
Example output
Subject: your application — [Role] at [Company] Hi [Name], Thank you for making time through all three rounds — you asked sharp questions and made the process easy. After a close decision, we're moving forward with another candidate whose background maps more directly to the infrastructure work we're starting immediately. I'm sorry it didn't come together. I hope it's useful to know it was a competitive field, not anything you could have done differently. Wishing you well in the search. [Your name]

TipSpecifying the stage they reached forces the right tone — a one-line application rejection and a final-round rejection are different human situations and should read differently.

ChatGPTGeminiClaude

Job offer email

Deliver an offer that lands the candidate and covers the key terms.

The prompt
Write a job offer email to [CANDIDATE NAME] for the role of [JOB TITLE] at [COMPANY].

Offer details:
- Base salary: [AMOUNT]
- Equity / bonus (if any): [DETAILS]
- Start date: [DATE]
- Response deadline: [DATE]
- Any other key terms: [NOTES]

Tone: warm, professional, and direct — they should feel chosen. Mention that a formal letter follows if that's the case. Under 180 words. Don't invent terms I haven't given.
Example output
Subject: offer — [Role] at [Company] Hi [Name], We'd love to have you join the team. Here's a summary of what we're offering: - Role: Senior Data Engineer - Base salary: $148,000 - Equity: 0.08% over four years with a one-year cliff - Start date: July 14, 2025 - Offer open until: June 20, 2025 A formal offer letter with full details will follow from our People team today. We spent a lot of time on this search and kept coming back to you — your work on the migration project and the way you think through tradeoffs is exactly what we need. We're excited. Let me know if you have any questions before then. Looking forward to your answer. [Your name]

TipInclude the response deadline in the email, not just the offer letter — candidates feel clearer with a date in front of them and it reduces the chance of drawn-out silence.

ChatGPTGeminiClaude

Turn interview notes into a debrief

Convert raw interview notes into a structured evaluation.

The prompt
Convert my raw interview notes into a structured debrief for sharing with the hiring team.

Candidate: [NAME]
Role: [JOB TITLE]
Interviewer: [YOUR NAME]
Notes: [PASTE RAW NOTES]

Output format:
- Headline: one sentence on overall impression.
- Strengths observed (bullets)
- Concerns or gaps (bullets)
- Standout moment: one specific exchange worth sharing
- Recommendation: Advance / Hold / Pass — with one line of reasoning

Only use what's in my notes. Don't soften concerns to be polite.
Example output
Candidate: Maya Chen | Role: Head of Growth | Interviewer: J. Park Headline: Strong strategic thinker, but gave thin answers when pushed on execution specifics. Strengths: - Articulated a full-funnel growth model unprompted — showed systems thinking. - Comfortable with ambiguity; described building a team from scratch at her last role. Concerns: - When asked about a campaign that underperformed, pivoted to what the team learned without owning her own call that was wrong. - No specific CAC or payback period numbers cited in any example. Standout moment: Her reframe of retention as a growth lever landed well — clear, original, and grounded. Recommendation: Hold — ask a second interviewer to pressure-test the execution gap before advancing.

TipAsk for a "standout moment" explicitly — it gives the hiring team a concrete anchor for the debrief conversation, rather than a list of bullets they have to interpret on their own.

ChatGPTGeminiClaude

Promote a job opening on social

Write a social post that gets a role shared and applied to.

The prompt
Write a LinkedIn post promoting a job opening that earns shares, not just clicks.

Role: [JOB TITLE]
Company: [COMPANY NAME]
What makes this role genuinely interesting: [2–3 REAL DRAWS]
Who we want to reach: [TYPE OF PERSON / EXPERIENCE LEVEL]
Application link: [URL]

Rules:
- First line must stop the scroll — no "We're hiring!" opener.
- Tell the reader what's actually interesting about the work, not just the perks.
- Under 150 words.
- End with one clear action.
Example output
The person we're looking for has probably built a sourcing function from scratch before — and has opinions about what they'd do differently. [Company] is hiring a Head of Talent. We're 80 people, pre-IPO, and have never had a full-time recruiter. The next 18 months will add about 40 more. You'd build the process, pick the tools, and own the brand — no inherited playbook. What we're not: a slow-moving machine where you manage a pipeline someone else designed. What we are: a team that wants to hire well and is willing to invest in doing it right. If this sounds like the kind of problem you want, the details are here: [link] If it sounds like someone you know, tag them.

TipWriting for shares, not just applications, changes the structure — you need a reader who is not a fit themselves to understand why a friend would care. Write for that second-degree reader.

ChatGPTGeminiClaude

Build an interview scorecard

Turn loose notes into a consistent scorecard for fair comparison.

The prompt
Build an interview scorecard from my notes for [CANDIDATE NAME], interviewed for [JOB TITLE].

Evaluation criteria for this role: [LIST 4–6 CRITERIA — e.g., technical depth, communication, leadership, domain knowledge].

My notes: [PASTE NOTES]

For each criterion:
- Rating: 1 (well below bar) to 4 (clearly above bar)
- One sentence of evidence from the interview that supports the rating

End with: overall rating (average) and a hire / no-hire signal.
Only rate what the interview actually covered. Mark criteria as "not assessed" if they weren't.
Example output
Candidate: Priya Nair | Role: Senior Product Manager | Criterion | Rating | Evidence | |---|---|---| | Strategic thinking | 4 | Mapped the competitive landscape unprompted and identified a positioning gap. | | Cross-functional influence | 3 | Solid example with Engineering; less clear on how she handles Sales conflict. | | Data fluency | 3 | Comfortable with funnel metrics; SQL depth not assessed. | | Communication clarity | 4 | Explained a complex tradeoff in under two minutes without jargon. | | Domain knowledge | 2 | Fintech background is thin; prior work is primarily e-commerce. | | Leadership | Not assessed | No direct reports questions asked in this round. | Overall: 3.2 | Signal: Advance — with a note to probe domain fit in the next round.

TipIncluding "not assessed" as a valid rating prevents the scorecard from looking more complete than the interview was — a gap in the data is useful information for the next interviewer.

ChatGPTGeminiClaude

Phone screen question list

Plan a 15-minute phone screen that filters fast without being cold.

The prompt
Write a phone screen question list for a [JOB TITLE] role at a [COMPANY TYPE].

Must-verify in this screen: [2–3 HARD REQUIREMENTS — e.g., work authorization, specific experience, comp range].

Give me:
- 2 warm-up questions to make the candidate comfortable.
- 3 quick-filter questions that confirm the hard requirements early.
- 2 questions that give me a read on motivation and culture fit.
- A closing line that sets expectations for next steps.

Flag which questions to cut if I'm running short on time.
Example output
Warm-up (keep both) 1. "How did you find out about this role?" — reveals whether they sought us out or got blasted. 2. "What does your week typically look like in your current job?" — gets them talking, helps you calibrate pace. Quick filters (ask all three) 3. "This role requires [specific certification] — do you currently hold that?" — hard stop if no. 4. "The target comp range is [range] — does that work for you?" — covers comp mismatch early. 5. "We're planning a start date around [date] — any constraints on your end?" — surfaces notice period issues. Motivation / culture 6. "What would need to be true about a new role for you to say it was the right move?" — cut this if short on time. 7. "What's one thing about your current setup you're hoping changes?" — honest answer tells you a lot. Closing: "I'll follow up by [day] with next steps. Any questions for me before we wrap?"

TipPut comp and hard requirements in the first five minutes — discovering a mismatch at minute 12 wastes both your time. The warm-up questions are worth keeping because cold screens produce worse signal.

ChatGPTGeminiClaude

Ask your network for referrals

Write an email that gets people to actually refer good candidates.

The prompt
Write a referral request email to send to [CONTACT NAME OR GROUP — e.g., former colleagues, alumni network] asking for candidate referrals for [JOB TITLE] at [COMPANY].

Make it easy for them to refer someone without spending more than two minutes on it.

Include:
- What the role is in one sentence.
- Who would be a great fit, described in human terms (not a job description).
- What to do if they know someone (exact action).
- A brief thank-you.

Under 120 words. No formal headers or bullet lists — write it as a normal email.
Example output
Subject: a quick ask — do you know a great Head of Talent? Hi [Name], I'm filling a Head of Talent role at [Company] and thought of you immediately — you know a lot of strong HR and recruiting people. I'm looking for someone who's built a recruiting function from scratch at a growth-stage company and has opinions about how to do it well. Not necessarily someone in a current search, just someone good. If anyone comes to mind, just reply with their name or forward this email — I'll take it from there. Thanks for thinking of me, and no worries if no one comes to mind. [Your name]

TipDescribing who you want "in human terms" — not a list of requirements — makes it much easier for your contact to picture an actual person they know. Job descriptions make people think of job boards, not their network.

ChatGPTGeminiClaude

Compare finalists side by side

Summarize two or three finalists into a clear comparison.

The prompt
Compare [NUMBER] final-round candidates for the role of [JOB TITLE] and give the hiring team a clear summary to inform their decision.

For each candidate, I'll give you notes. Produce:
- A comparison table with the key criteria as columns and candidates as rows.
- Under the table, a one-paragraph "case for" each candidate — genuine strengths only, no padding.
- A section on key tradeoffs the team should discuss.
- Do not make a hire recommendation — leave the decision to the team.

Evaluation criteria: [LIST CRITERIA]
Candidate notes: [PASTE NOTES FOR EACH CANDIDATE]
Example output
| Criterion | Candidate A (Sara) | Candidate B (Tom) | Candidate C (Lea) | |---|---|---|---| | Technical depth | High | Medium | High | | Leadership exp. | 3 direct reports | None | 6 direct reports | | Domain fit | Strong (SaaS) | Moderate | Weak (retail only) | | Communication | Clear, concise | Strong, verbose | Clear | | Culture signals | Collaborative | Independent | Collaborative | Case for Sara: Built and scaled a 3-person team in a similar product org. Strong on ambiguity; interview showed she works well without a playbook. Case for Tom: Highest technical ceiling in the group. Would need to grow into the leadership scope, but the raw thinking is there. Case for Lea: Most leadership experience by volume, though in a different industry. Strong communicator; the domain gap is the real question. Key tradeoffs: Do you need someone who can lead today, or someone you can develop? How much does the industry gap matter given your onboarding capacity?

TipEnding with "key tradeoffs" rather than a recommendation keeps the hiring team in the decision — they have context you don't, and the summary is most useful when it surfaces the real dilemma rather than resolving it.

Frequently asked questions

How do I write recruiter outreach that gets a reply?

Use the candidate-outreach prompt with a specific reason you’re contacting this person — a project, a skill, a shared background. It leads with that hook instead of a generic “great opportunity,” which is what makes passive candidates respond.

Can ChatGPT screen resumes against a job description?

It can summarize fit. Paste the resume and the job spec into the screening prompt and it lists matches and gaps honestly. Use it to speed up a first pass — not to auto-reject — and keep a human in the loop for fairness.

How do I create consistent interview questions?

The interview-questions prompt generates skill- and behavior-based questions tied to a specific role, and the scorecard prompt turns notes into a consistent rubric — so every candidate is evaluated on the same criteria.

Will AI introduce bias into hiring?

It can, if you let it screen unsupervised. Use these prompts as drafting and structuring aids, keep humans making decisions, evaluate on job-relevant criteria, and review outputs for bias. Structured, consistent questions actually reduce bias versus unstructured chats.