How it works
- Connect the Asana MCP server at https://mcp.asana.com/v2/mcp to your AI assistant or coding agent, then sign in with your Asana account through OAuth so the assistant reads only the workspaces your account can already reach.
- 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 incomplete tasks carrying your experiment tag, then joins the name, description, subtask names, and the custom fields that hold the parts of the plan your team records there.
- 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 adds the findings and a suggested rewrite as a comment and lints the rewrite, so the task carries both the original gap and the new wording.
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 Asana MCP tools to find incomplete tasks in [project or section name] that carry the tag [experiment]. For each task, read the name, full description, subtasks, and custom fields, then lint that 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, add 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 | Asana descriptions often stop at the change itself, and the lint wants the sentence a finished result could contradict. |
| hypothesis/names-metric-and-direction | error | The task has to name the metric and the direction it expects, since a subtask named after the feature says nothing about what should move. |
| guardrails/have-launch-thresholds | error | Custom fields make a natural home for guardrails, and each one needs a numeric limit a reader can compare rather than a note to watch errors. |
| duration/covers-full-business-cycles | error | The task should say how many full weeks the test runs, because the due date field records a deadline rather than a measurement window. |
