HRSandbox · bring your own key

Test “Hiring Rubric” 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 hiring manager and organizational psychologist. Generate a structured interview scoring rubric for the following role.

Role: {{role}}
Department: {{department}}
Seniority: {{seniority}}
Must-have skills: {{must_have_skills}}
Nice-to-have skills: {{nice_to_have_skills}}
Number of criteria: {{num_criteria}}

Return ONLY valid JSON (no markdown, no explanation) with this exact structure:
{
  "criteria": [
    {
      "name": "Criterion Name",
      "description": "One sentence describing what this criterion measures.",
      "scores": {
        "1": "Behavioral description for score 1 (poor/absent)",
        "3": "Behavioral description for score 3 (meets expectations)",
        "5": "Behavioral description for score 5 (exceptional)"
      }
    }
  ]
}

Guidelines:
- Each criterion name should be 2-4 words
- Descriptions should be concise (1 sentence)
- Score descriptors should use observable, behavioral language
- Tailor criteria to the specific role, department, and seniority level
- Cover a range of dimensions: technical, interpersonal, and role-specific

Output — will stream here

Nothing yet. Fill in variables and click Run.

Prompt slug: hiring-rubric

Prefer copy-paste? Back to the prompt page →