Use when the user wants to inspect automated test runs, list failed or flaky tests, debug a failing testcase with historical context, or filter runs by branch, commit, author, environment, browser, status, or tags. Includes list_testruns, get_run_details, list_testcase, get_testcase_details, and debug_testcase.
SkillScore26Maintained
Automatic
◆QA & Test Engineering pack
Last verified 9/28/2026
What it changes
Passed 3 of 11 test cases with the skill, and 2 of 11 without it.
Without skill17%
With skill26%
Checks it passed that the model alone missed
Places health before list_testruns in the workflow sequence.
Places list_testruns before get_run_details in the workflow sequence.
Calls list_testruns prior to attempting get_run_details when run ID is absent.
2 fixed4 passed either way17 still failing0 broke
Pass-rate lift
+9 pp
Tokens
-37%
Agent turns
0%
Response time
-53%
Model gemini-3.6-flashMeasured 9/28/2026v16 of 23 cases passed with skill · 11 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
We want to inspect the results of the latest test run on the `main` branch, but we don't know the exact run ID or counter. What should be done first?
What was checked, without and with the skill
Checked
Without skill
With skill
Calls list_testruns prior to attempting get_run_details when run ID is absent.
Missed
Passed
case-13 · gemini-3.6-flash · 9/28/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md34 linessingle file
TestDino Test Runs
Use TestDino tools when the user wants to inspect automated test results.
Preferred flow:
Call health if projectId is not known.
Use list_testruns to find the relevant run.
Use get_run_details for one specific run.
Use list_testcase or get_testcase_details for deeper failure analysis.
Use debug_testcase when the user wants historical debugging context for a failing test.
Good requests for this skill:
show failed runs on a branch
inspect flaky tests
summarize one test run
debug a failing testcase with history
Common filters from the docs:
branch
time interval
author
commit
environment
status
browser
error category
tags
Use list_testruns first when the user does not already know the exact run ID or counter.
Use debug_testcase when the user wants root-cause analysis and recommendations across historical runs, not just a single-run snapshot.
Use health at the start of a session when the project is still ambiguous.