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.
217 prompts
Prompts written for Claude, Anthropic's assistant. Claude handles long inputs well, so many of these prompts ask you to paste a whole document, transcript or code excerpt and then structure the answer around it.
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.
Put the documents first and the prompt after them. Anthropic's prompting guide suggests wrapping each document in tags such as <document> so Claude keeps the sources apart.
Yes. Paste it into the project instructions and every chat in that project starts from it. Fill its blanks with the details that stay the same from chat to chat.
No. These are for the Claude apps and the API. For work inside a code repository, where the agent reads files and runs commands, use the Claude Code prompts.