20-Case Agent Eval Set with Pass/Fail Rubric for Normal, Edge and Unsafe Requests
Builds 20 test cases for your agent's task, with expected behavior, failure signals and a pass/fail rubric covering normal, edge and unsafe requests.
271 prompts
Prompts whose answer is written text: emails, plans, analyses, code reviews, summaries and more. They work in any capable chat assistant, and each one sets the role, the steps and the format of the answer.
3 results
Builds 20 test cases for your agent's task, with expected behavior, failure signals and a pass/fail rubric covering normal, edge and unsafe requests.
Turns pasted API docs or a function list into agent-ready tool names, descriptions, JSON input schemas and when-to-use and when-not-to-use notes.
Produces a set of testable guardrail rules for your coding agent, covering blocked commands, approval gates, secret handling and hook checks.
Any prompt whose answer is writing rather than an image or a video. That covers writing, strategy, research, code and reusable templates.
Any capable chat assistant. ChatGPT, Claude and Gemini all follow the same structure; each prompt page lists the tools it was written for.
Keep the prompt's output format section as it is. It names the headings, lists or tables to return, so repeated runs come back in the same shape.