agentleFS
katalon-labskatalon-labs/true-skills/.cursor/rules/get-started.mdc

true-skills / rules

Cursor rule10 starsChanged 5 months agoMITView on GitHub

First-run onboarding for Katalon True Platform right after the Katalon connection is installed. Use when the user has just connected Katalon, says get me started, set me up, or pick my default project, or when no default project is stored yet. Confirms who is signed in, asks at most two questions to choose the default project and, only when there is a choice, the default repository and Run with AI target, saves them as settings when the client supports it, and ends on the Katalon home view or three starter prompts. Not for installing or configuring an MCP client in a local agent, which belongs to platform-setup, and not for designing or running tests.

The file

We split this get-started.mdc into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run this once after the Katalon connection is installed.

    line 10
  2. Distinctive:

    Never ask for a password, API key or token.

    line 15
  3. Distinctive:

    Never repeat the user's email address back to them.

    line 16
  4. Distinctive:

    No AUT environment: leave the Run with AI target unset and say Run with AI asks for it on first use.

    line 26
  5. Very specific:

    Save: Call settings_update with {"set": {"default_project_id": ..., "default_repository_id": ..., "default_aut_environment_id": ...}}, …

    line 27
  6. Very specific:

    First view: Call katalon_home so the user lands on their runs, uncovered requirements and release status.

    line 28
  7. Distinctive:

    Stop after step 5. Do not start a run, design cases or file anything during onboarding.

    line 35
  8. Distinctive:

    If any read fails with a permission or gate error, report the error line as given, say who can lift it if the error names that, and …

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
get-started.mdc
---
description: First-run onboarding for Katalon True Platform right after the Katalon connection is installed. Use when the user has just connected Katalon, says get me started, set me up, or pick my default project, or when no default project is stored yet. Confirms who is signed in, asks at most two questions to choose the default project and, only when there is a choice, the default repository and Run with AI target, saves them as settings when the client supports it, and ends on the Katalon home view or three starter prompts. Not for installing or configuring an MCP client in a local agent, which belongs to platform-setup, and not for designing or running tests.
alwaysApply: false
---

<!-- GENERATED by scripts/build-adapters.mjs from skills/. Do not edit by hand. -->

# Katalon Get Started

Run this once after the Katalon connection is installed. The goal is a stored default project and a first useful view in under a minute, with **at most two questions**.

## Boundary

- Reads only, plus one settings save. Nothing in the user's workspace changes.
- Never ask for a password, API key or token. Sign-in happens in the client's own Katalon sign-in screen.
- Never repeat the user's email address back to them.
- Some tools below exist only on clients that render Katalon cards and store settings (`katalon_profile`, `settings_update`, `katalon_home`). When a tool is not listed in this session, skip that step as described and carry on.

## Steps

1. **Who is signed in.** Call `katalon_profile`. Greet in one line with the organization and account name from `nickname`, for example "You are connected to Katalon as Katalon Demo / Demo Shop." If `katalon_profile` is not listed, skip the greeting. If the call says the user is not signed in, tell them to sign in to Katalon from the connection prompt and stop.
2. **Default project (question 1).** Call `list_projects`. If there is exactly one project, use it and do not ask. Otherwise ask one question offering the three most recently used projects by name, plus "another project". If the user names another project, match it by name from the same list.
3. **Repository and Run with AI target (question 2, only if needed).** Call `list_repositories` and `read_auts` for the chosen project.
   - One repository and at most one AUT environment: use them and do not ask.
   - More than one of either: ask one combined question, for example "Which repository and which environment should Run with AI use by default?", listing at most three options for each.
   - No AUT environment: leave the Run with AI target unset and say Run with AI asks for it on first use.
4. **Save.** Call `settings_update` with `{"set": {"default_project_id": ..., "default_repository_id": ..., "default_aut_environment_id": ...}}`, leaving out any value that was not chosen. If `settings_update` is not listed, say which project and repository this conversation will use and skip saving.
5. **First view.** Call `katalon_home` so the user lands on their runs, uncovered requirements and release status. Where cards do not render, or `katalon_home` is not listed, end with these three starter prompts instead:
   - "Which requirements in my next release have no tests?"
   - "Why did my latest test run fail?"
   - "Is my next release ready to ship?"

## Stop conditions

- Stop after step 5. Do not start a run, design cases or file anything during onboarding.
- If any read fails with a permission or gate error, report the error line as given, say who can lift it if the error names that, and continue with the steps that still work.

## Output

One greeting line, at most two questions, one confirmation line naming the saved defaults, then the home view or the three starter prompts.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.