Verified against ChatGPT · 2026-07-29
Rewrite resume bullets to show quantified impact
Converts flat, duty-listing resume bullets ("responsible for managing social media") into achievement-framed lines with a number, a result, or a scale — the pattern recruiters actually scan for.
The prompt
Ready to copy — highlighted parts are example details you can swap.
ROLE: You are a resume writer who has coached candidates into more interviews by fixing exactly one recurring problem: bullets that describe duties instead of results.
TASK: Rewrite each of the resume bullets below using this formula: [Action verb] + [what you did] + [quantified result or scale]. Every bullet should answer "so what happened because of this?"
CURRENT BULLETS:
- Responsible for managing company social media accounts
- Helped onboard new employees
- Worked on improving customer support response times
ADDITIONAL CONTEXT (numbers, scale, timeframes I can use):
Social media: grew follower count from 4k to 15k in one year, drove a 22% lift in site traffic from social. Onboarding: onboarded 12 new hires over 8 months, cut ramp-up time from 6 weeks to 4. Support: reduced average first-response time from 24 hours to 5 hours.
REQUIREMENTS:
- Start each bullet with a strong action verb, never "Responsible for," "Helped with," or "Worked on"
- Every bullet must include at least one number: a percentage, dollar amount, time saved, team size, or volume — pull from the context above; if no real number exists for a bullet, keep it qualitative but flag it rather than inventing a figure
- One line per bullet, no bullet longer than ~20 words
- Cut filler adjectives ("dynamic," "results-driven," "passionate")
- Keep the same underlying facts — sharpen the framing, don't add achievements that aren't supported by the context I gave you
Return the rewritten bullets in the same order as the originals. After the list, flag any bullet where you had to keep it qualitative because no number was available, and tell me what number would strengthen it most if I can find it.Customize the highlighted detailsoptional — the prompt above already works
Why this works
This gives the model an explicit formula (action verb + action + quantified result) rather than a vague "make this better" instruction — a structural constraint that's easy for the model to apply consistently across every bullet instead of improving only the first one and coasting on the rest. Splitting the raw bullets from the supporting numbers into two separate variables matters more than it looks: it stops the model from inventing plausible-sounding metrics to satisfy the "include a number" rule, because it only has real numbers to draw from. The instruction to flag ungrounded bullets rather than silently fabricate a number is the same anti-hallucination guardrail used in the cover-letter prompt above, applied to the place resumes most commonly get caught embellishing.
What you get back
- Grew company social following from 4k to 15k followers in 12 months, driving a 22% increase in site traffic from social channels - Onboarded 12 new hires over 8 months, cutting average ramp-up time from 6 weeks to 4 - Cut average customer support first-response time from 24 hours to 5 hours All three bullets had a supporting number, so none needed to stay qualitative.
Verified against
ChatGPT GPT-5.1 · 2026-07-29
Claude Claude Sonnet 4.5 · 2026-07-29
Gemini Gemini 3 Pro · 2026-07-30
Changelog
- 2026-07-29 — Split raw bullets and supporting numbers into separate variables after finding the model invented metrics when given bullets alone.
- 2026-07-12 — Initial version published.
Need this built into your business?
If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.
EXPLORE WHAT SCULT BUILDS
