Agent tasks

Coding-agent tasks in a real folder, with safety rules. 5 prompts. Search and filter these.

Prompt	Difficulty	Lang	What it tests	Source
Agent task: build a FLUX workflow in a local ComfyUI folder	hard	DE	Coding-agent discipline in a real folder: explore first, follow existing file formats, no downloads, no moving or deleting files, validate the output and report assumptions.	Arnie936 / llm-prompting-tests
Agent task: n8n Gmail workflow with a dry-run switch	hard	DE	Turning business rules into an importable n8n workflow with a classifier, branching, a review label for paid offers, placeholder credentials and a dry-run switch that is on by default.	Arnie936 / llm-prompting-tests
Audited, self-improving trading research agent	very hard	DE	A 54 KB master prompt for a coding agent with binding safety limits, strategy research, backtesting, an external audit, paper-trading deployment and an explicitly locked live phase.	Arnie936 / llm-prompting-tests
Scroll-driven product landing page builder	very hard	EN	An autonomous website-builder prompt: from one product photo to a polished scroll-driven landing page with a fixed section order, OKLCH palette, copy rules, browser QA on three viewports and a ship checklist.	Arnie936 / llm-prompting-tests
Micron quarterly results video with Hyperframes and voice-over	hard	DE	A research-plus-production task: about one minute of 16:9 video on Micron's latest quarterly report with figures, outlook, Hyperframes animation, a German ElevenLabs voice-over and quiet lo-fi music.	Arnie936 / llm-prompting-tests