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.
285 prompts
Prompts written for ChatGPT, OpenAI's chat assistant. They cover writing, analysis, planning, coding and image generation, and each one spells out the role, the steps and the shape of the answer. Copy one as it is, or fill in its blanks first.
6 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.
Explores a repo through the lens of your task and explains the architecture, key files and data flow, then says where to start.
Produces a set of testable guardrail rules for your coding agent, covering blocked commands, approval gates, secret handling and hook checks.
Produces a 3-5 subagent roster with system prompts, minimal tool permissions, model tiers and explicit handoff rules for your project.
Designs a four-agent pipeline for your report type with each agent's prompt, inputs, outputs and handoff format.
Text prompts only need a chat, so they run on any plan. Prompts that rely on file uploads, web search or image generation need those features to be available on your account.
Start a new chat and paste it into the message box. For a prompt you reuse, put it in a project's instructions or a custom GPT so every chat starts from it.
Usually, yes. The prompts are plain text with no ChatGPT-only syntax, so Claude and Gemini follow them too. Each prompt page lists the tools it was written for.