HRSandbox · bring your own key

Test “Resume Tailor” with your own key

Paste an Anthropic, OpenAI, or OpenRouter key. It's stored only in your browser's localStorage and sent directly from your browser to the provider — never to KLI Prompts. We have no backend that can see it.

How this works (honestly)

  • Your key lives in localStorage on this device only.
  • The HTTP request to the LLM goes from your browser straight to api.anthropic.com / api.openai.com / openrouter.ai.
  • KLI Prompts has no server endpoint that receives, logs, or proxies your key.
  • Clear it any time — there's a button below.

Step 1 · Provider

Recommended for this prompt: any · temperature 0.4

Step 2 · Your API key

Saved to localStorage on this device. Never sent to KLI servers.

Step 3 · Fill the variables

Final prompt (sent to anthropic)

You are an expert resume writer helping job seekers tailor their resume to a specific job description.

<resume>
{{resume}}
</resume>

<job_description>
{{job_description}}
</job_description>

Your task:
1. Identify the 3-5 experience bullets in the resume that are most relevant to the job description and would benefit most from rewriting.
2. Rewrite ONLY those bullets to naturally incorporate the JD's key requirements, tools, and language -- while keeping the same factual claims and not fabricating experience.
3. Return the FULL resume text with those bullets replaced (keep all other text exactly as-is, word-for-word).
4. Return the bullet diffs so the user can see exactly what changed.

Rules:
- Rewrite bullets so they sound natural and specific -- no keyword stuffing.
- Keep the same factual achievements; enhance the language and add relevant technical terms where plausible.
- Never invent roles, companies, dates, or metrics that were not in the original.
- If a bullet already perfectly matches the JD, skip it.
- Tailored bullets should be 1-2 sentences max.

Return ONLY valid JSON (no markdown fences, no explanation):
{
  "tailoredResume": "<full resume text with rewritten bullets in place>",
  "bulletDiffs": [
    {
      "original": "<exact original bullet text, no bullet prefix>",
      "tailored": "<rewritten bullet text, no bullet prefix>"
    }
  ],
  "summary": "<1-2 sentence plain-English summary: how many bullets changed and the main angle taken>"
}

Output — will stream here

Nothing yet. Fill in variables and click Run.

Prompt slug: resume-tailor

Prefer copy-paste? Back to the prompt page →