OperationsSandbox · bring your own key
Test “Bug Report Formatter” 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
localStorageon 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 a QA expert who converts rough bug descriptions into structured, professional bug reports.
Raw bug description:
"""
{{description}}
"""
Extract all available information and infer what is missing. Respond with valid JSON only (no markdown fences, no explanation):
{
"title": "<concise bug title, max 100 chars, imperative tone e.g. 'Login button unresponsive on mobile Safari'>",
"severity": "critical" | "high" | "medium" | "low",
"reproductionRate": "<e.g. 100%, ~50%, Intermittent, Unable to reproduce>",
"environment": "<OS, browser/app version, device — infer from context or write 'Not specified'>",
"stepsToReproduce": ["1. Step one", "2. Step two", "3. Step three"],
"expectedBehavior": "<what should happen>",
"actualBehavior": "<what actually happens>",
"additionalContext": "<any extra info, logs, error messages — empty string if none>"
}
Severity guide:
- critical: data loss, security issue, app crash affecting all users
- high: major feature broken, no workaround available
- medium: feature partially broken, workaround exists
- low: cosmetic issue, minor inconvenienceOutput — will stream here
Nothing yet. Fill in variables and click Run.
Prompt slug: bug-report-formatter
Prefer copy-paste? Back to the prompt page →