Use Caliper to run real agent tasks with and without a skill, MCP server, or rule change so reliability and token cost are measurable.
no risky patterns detected
Type: Agent skill (SKILL.md) · Category: Testing & QA · Source: https://github.com/agentskillexchange/skills/tree/HEAD/skills/ab-test-agent-skil
| Capabilities (fewer powerful permissions = higher) | 50/50 |
| Maintenance | 29/35 |
| Documentation | 15/15 |
Always review files before installing. How scores work. Request a correction