Use after an agent-qa run has failed and you need to debug, patch, and verify the issue using MCP evidence, logs, artifacts, and local code changes instead of generated fix suggestions.
NewMaintained
Automatic
◆QA & Test Engineering pack
Last verified 9/8/2026
What it changes
Passed 3 of 10 test cases with the skill, and 5 of 10 without it.
Without skill45%
With skill32%
Checks it passed that the model alone missed
Inspects local frontend component files directly
States explicitly that MCP evidence was unavailable
Uses dashboard REST APIs when MCP evidence is unavailable
and 2 more in the full report
4 fixed3 passed either way8 still failing7 broke
Pass-rate lift
-14 pp
Tokens
+5%
Agent turns
0%
Response time
-5%
Model gemini-3.6-flashMeasured 9/8/2026v17 of 22 cases passed with skill · 10 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
We updated a setup hook `hook_db_seed.yaml` after failure `run_31102`. Before running the hook in test execution, which specific validation tool should be used to verify the hook definition syntax?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses agent_qa_validate_definition to validate the modified hook
Missed
Passed
case-16 · gemini-3.6-flash · 9/8/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md24 linessingle file
agent-qa Debug Fix
Workflow
Start with evidence collection:
agent_qa_get_run
agent_qa_get_run_steps
agent_qa_get_run_artifact
agent_qa_get_run_logs
agent_qa_get_run_execution_logs
Call agent_qa_classify_failure and treat its category as a hypothesis, not a verdict.
Identify the failing surface: test definition, hook, application under test, runtime infrastructure, or agent behavior.
Inspect the relevant local files directly. Do not infer patches from artifacts alone.
Apply the smallest code or YAML change that explains the evidence.
Re-run the narrowest affected agent-qa test, suite, hook, or unit test.
Report the root cause, changed files, verification command, and any remaining risk.
Fix Rules
Do not invent selectors, screen states, screenshots, logs, or source files.
Do not rewrite a test just to make it pass if the artifact shows a product or runtime defect.
Preserve canonical agent-qa IDs when editing tests, suites, hooks, or memory files.
Prefer agent_qa_validate_test, agent_qa_validate_suite, and agent_qa_validate_definition before re-running edited YAML.
When MCP is unavailable, use dashboard REST APIs or local .agent-qa artifacts and state that MCP evidence was unavailable.