Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →camunda/create-rt-issue
Create a GitHub issue in camunda/camunda for load-test/Reliability Testing (RT) work, extending create-issue with the component/load-tests label and an rt/foundation, rt/coverage, or rt/enablement classification.
Passed 21 of 23 test cases with the skill, and 3 of 23 without it.
and 8 more in the full report
19 fixed2 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 19 test cases the skill fixed. Same model, same prompt, with and without the skill.
Please create a GitHub issue for a joint initiative where we rebuild parts of the test runner and also host team office hours for load testing. Handle the issue creation flow now.
| Checked | Without skill | With skill |
|---|---|---|
| Prompts the user to choose between the RT focus area options. | Missed | Passed |
| Refrains from applying multiple rt/* labels at once. | Passed | Passed |
The instructions your model reads when the skill loads.
Extends the create-issue skill for Reliability Testing (RT) work. Reuses its template selection,
duplicate check, field inference, body composition, and creation flow, and layers on two RT-specific
overrides.
Invoke the create-issue skill and follow its procedure, with these two overrides:
create-issue Step 3)Skip create-issue's component auto-detection entirely. Always apply component/load-tests,
regardless of which files are touched or what the issue is about — this skill is only invoked for
RT/load-test work.
create-issue Step 2's field inference)Every RT issue gets exactly one of the following labels, based on the team's focus-area model (foundation → enablement → coverage):
| Label | Meaning |
|---|---|
rt/foundation | Tools, automation, or infrastructure investment for reliability testing (test, investigate, validate) |
rt/enablement | Onboards other teams to run reliability tests proactively on their own |
rt/coverage | Increases reliability-testing coverage of the orchestration cluster or an environment/deployment |
Infer the label from the issue description:
rt/foundationrt/enablementrt/coverageIf the description doesn't clearly fit one category, ask the user to pick one before proceeding — do not guess or apply more than one.
Additionally, infer the existing discovered-by/load-tests label when the description states the
issue was found during a load-test run. This is optional (not every RT issue is discovery-sourced);
leave it off if the description doesn't say so.
test cases passed, vs 3 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.