Resume Rewrite — Tech IC
Cut every adjective. Quantify three things. Make the recruiter call you back.
Prompt
**Role:** Recruiter at a top-tier tech company who has screened 10,000+ resumes. You spend 12 seconds on the first pass and you know which 12 words decide whether to keep reading. **Context:** Candidate background: [years exp, current role, target role]. The role they're applying for: [job title + 2 must-have requirements from the JD]. Current resume bullets they want rewritten: [paste]. **Task:** Rewrite each bullet to pass the 12-second screen. 1. Strip every adjective. "Successfully launched" becomes "Launched." "Highly skilled in" becomes the verb in past tense. 2. Lead each bullet with the result, then the action, then the context. NOT "Worked on X using Y to achieve Z" — say "Cut Z latency 40% by Y across X." 3. Quantify minimum 3 bullets with: # users / $ revenue / % improvement / ms latency / # PRs reviewed / etc. Approximate numbers OK if true. 4. For each bullet: keep the verb varied (don't start 5 bullets with "Built"). 5. Remove anything that isn't differentiating for THIS role (stripping irrelevant skills sections, deprioritizing older roles). **Constraints:** - Each bullet ≤2 lines (about 24 words on standard resume formatting) - Never lie about a metric — approximate is fine, fabricated is not - Forbid: "responsible for," "team player," "passionate about," "synergized" - Lead verb in past tense (current role uses present tense) **Output format:** Original bullet → Rewritten bullet · table format · plus 3-bullet "what I changed and why" callout.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueSets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.
Learn this techniqueSpecifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Writing
Brand Voice Rewrite
Take any draft and rewrite it in your brand's voice. Keep meaning, drop hedges.
Newsletter Issue — Specific Subject Line
Hook earns the open. 3 curated items, one personal note, soft CTA.
Product Changelog — User-Facing
Announce a feature ship. Lead with the job it does, not the feature name.
Conference Talk Abstract
Submit a talk that reviewers can't skip. Hook, claim, 3 takeaways, audience.