Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. Use when testing PRs, detecting regressions, or verifying tool changes end-to-end with Claude/Gemini CLIs.
83
88%
Does it follow best practices?
Impact
97%
1.27xAverage score across 2 eval scenarios
Passed
No findings from the security scan
BAT failure diagnosis and regression check
Phase-level detail cited
100%
100%
Uses --branch master flag
100%
100%
Regression correctly identified
100%
100%
Primary metrics cited
100%
100%
Duration not flagged as regression
100%
100%
BAT scenario design and execution for tool error-signaling change
Three-prompt structure
0%
100%
Reporting instruction
0%
100%
Agents flag present
100%
100%
Stdin piping used
100%
100%
Single behavior focus
53%
66%
Runner output captured
100%
100%
47582a7
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.