Use when the user wants to manage a manual execution run or update case-level results inside a run — listing runs, creating runs for a release, inspecting a run, assigning cases, or marking case results (passed/failed/blocked/skipped/retest/untested). Accepts counter-style IDs like RUN-12 and TC-156.
SkillScore33Maintained
Automatic
◆QA & Test Engineering pack
Last verified 9/28/2026
What it changes
Passed 4 of 11 test cases with the skill, and 2 of 11 without it.
Without skill17%
With skill33%
Checks it passed that the model alone missed
Uses tool update_run_test_case.
Sets updates.result to canonical value skipped.
Uses get_manual_run to inspect metadata for RUN-45.
and 2 more in the full report
4 fixed4 passed either way16 still failing0 broke
Pass-rate lift
+17 pp
Tokens
-20%
Agent turns
0%
Response time
-48%
Model gemini-3.6-flashMeasured 9/28/2026v18 of 24 cases passed with skill · 11 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
Flag test case TC-501 in manual run RUN-77 as skipped. Specify the tool call and status parameter value.
What was checked, without and with the skill
Checked
Without skill
With skill
Uses tool update_run_test_case.
Missed
Passed
Sets updates.result to canonical value skipped.
Missed
Passed
case-14 · 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.md28 linessingle file
TestDino Manual Runs
Use TestDino manual-run tools when the user wants to manage a manual execution run or update case-level results inside a run.
Preferred flow:
Call health if projectId is not known.
Use list_manual_runs to discover runs by name, state, release, environment, or tags.
Use get_manual_run to inspect one run's metadata and rollup stats.
Use create_manual_run or update_manual_run for run-level metadata changes.
Use list_run_test_cases before changing any individual case in a run.
Use update_run_test_case to assign a case, change its result, or update elapsed time.
Important details:
runId accepts an internal ID or a counter-style ID like RUN-12.
rtcRef can be the run test case row ID, case key like TC-156, or the underlying test case ID.
updates.assigneeUserId can be a user ID or email address.
updates.result accepts display form or canonical form, but canonical values like passed, failed, blocked, skipped, retest, and untested are safest.
For create and update payloads, tags and linkedIssues must be JSON arrays.