Review SARIF, CodeClimate, compact, markdown, badge, and other CI-facing output formats for correctness and integrator expectations.
SkillScore33Maintained
Automatic
◆QA & Test Engineering pack
Last verified 9/28/2026
What it changes
Passed 7 of 20 test cases with the skill, and 3 of 20 without it.
Without skill13%
With skill33%
Checks it passed that the model alone missed
Ends the response with status BLOCK.
Ends the response with status CONCERN.
Ends the response with status APPROVE.
and 1 more in the full report
7 fixed1 passed either way14 still failing2 broke
Pass-rate lift
+21 pp
Tokens
+23%
Agent turns
0%
Response time
+3%
Model gemini-3.6-flashMeasured 9/28/2026v28 of 24 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
When Cucumber test tags filter out all features, our test runner outputs `[]` (an empty JSON array). Review if this empty-input payload is acceptable for CI test report consumers and state your final review status.
What was checked, without and with the skill
Checked
Without skill
With skill
Evaluates `[]` as valid JSON empty-input payload for Cucumber report consumers.
Passed
Passed
Ends the response with status APPROVE.
Missed
Passed
case-11 · 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.md15 linessingle file
CI Formats Review
Read .agents/agents/ci-formats-reviewer.md before reviewing.
Also read .agents/rules/testing.md when snapshots or integration tests are involved.