How it works
- Connect the ClickUp MCP server at https://mcp.clickup.com/mcp to your AI assistant or coding agent, then sign in through OAuth because ClickUp accepts OAuth for this connection and asks for that flow during setup.
- Install the ExpLint MCP at https://explint.com/mcp to enable your agent to audit tests.
- Run the prompt below to audit these plans before the work starts.
How the check runs
- It finds the tasks in your list, folder, or space by the statuses and tags your team uses for ideas still being shaped, then builds one text from the summary the tools return and the description and fields you confirm in chat.
- It sends that text to ExpLint with
explint__lint, which returns errors, warnings, and passes, each finding naming the rule behind it. - When you approve a task, it posts the findings and a suggested rewrite as a comment and lints the rewrite, which keeps the review on the task where the assignee will see it.
Copy and paste this prompt
Change the words in square brackets to name your own project, board, or test.
Prompt for your assistant
Use the ClickUp MCP tools to find tasks in [list, folder, or space name] with status [your backlog status] and tag [experiment]. For each task, read its summary and build one text from the title and description the tools return, and tell me where a part of the plan is missing from that text. Lint the text with explint.com against project [your ExpLint project name]. Show me a table with the task name, its errors and warnings, and the exact words behind each finding. Do not change any task yet. When I approve a task, post the findings and a suggested rewrite as a comment on it, then lint the rewrite and show whether the errors are gone.
What ExpLint looks for
ExpLint ships over 24 rules, and a project switches each one on or off or rewrites it in plain English. These are the rules the plans this guide reads break most often. An error means the test cannot answer its question as written, and a warning means the result will be hard to judge when it comes in.
| Rule | Level | In plain words |
|---|---|---|
| hypothesis/is-falsifiable | error | A ClickUp summary that only names the change gives the task nothing a result could contradict. |
| hypothesis/names-metric-and-direction | error | The summary is often the only text a task carries, so the metric and its direction have to appear there or in the description. |
| guardrails/have-launch-thresholds | error | Guardrails need numbers the team can check without debate, since a custom field labelling them is not a limit. |
| power/has-a-sample-size-calculation | error | A task that sets a split without a headcount leaves the assignee unable to say when the test has seen enough traffic. |
