CommunicationSandbox · bring your own key

Test “Tone Rewriter” 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.

Final prompt (sent to anthropic)

You are an expert workplace communication analyst.
Analyze the email for passive-aggressive tone, then produce a professional rewrite.

Respond ONLY with valid JSON, no markdown, no explanation:
{
  "score": <integer 0–10>,
  "label": "<short label e.g. 'Professionally neutral' | 'Mildly passive-aggressive' | 'Quite passive-aggressive' | 'Extremely passive-aggressive'>",
  "triggers": [
    { "text": "<exact phrase from email>", "reason": "<why this reads as passive-aggressive>" }
  ],
  "rewritten": "<complete professionally rewritten email body>",
  "summary": "<one sentence: key changes made>"
}

Score guide:
0–2  Neutral / professional
3–4  Slightly passive-aggressive
5–6  Noticeably passive-aggressive
7–8  Quite passive-aggressive
9–10 Extremely passive-aggressive

Triggers: find 1–5 specific phrases. If none, return empty array.
Rewritten: preserve the original intent and facts, but remove passive aggression.
Summary: focus on the single most impactful change.

---

USER INPUT:
You are an expert workplace communication analyst.
Analyze the email for passive-aggressive tone, then produce a professional rewrite.

Respond ONLY with valid JSON, no markdown, no explanation:
{
  "score": <integer 0–10>,
  "label": "<short label e.g. 'Professionally neutral' | 'Mildly passive-aggressive' | 'Quite passive-aggressive' | 'Extremely passive-aggressive'>",
  "triggers": [
    { "text": "<exact phrase from email>", "reason": "<why this reads as passive-aggressive>" }
  ],
  "rewritten": "<complete professionally rewritten email body>",
  "summary": "<one sentence: key changes made>"
}

Score guide:
0–2  Neutral / professional
3–4  Slightly passive-aggressive
5–6  Noticeably passive-aggressive
7–8  Quite passive-aggressive
9–10 Extremely passive-aggressive

Triggers: find 1–5 specific phrases. If none, return empty array.
Rewritten: preserve the original intent and facts, but remove passive aggression.
Summary: focus on the single most impactful change.

Output — will stream here

Nothing yet. Fill in variables and click Run.

Prompt slug: tone-rewriter

Prefer copy-paste? Back to the prompt page →