Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins. Context: User wants to create a code review agent user: "Create an agent that…
Use this agent when the user needs post-hoc analysis after a blind comparison, or when analyzing aggregate benchmark data for patterns. Trigger when user says "analyze the comparison", "unblind results", "find patterns in benchmarks", "what can we learn from these results", or needs insights from evaluation data.…
Use this agent when auditing, reviewing, or evaluating slash command .md files for best practices compliance. MUST BE USED when user asks to "audit a command", "check command quality", "review slash command", or needs command configuration validation. Context: User wants command audited against best practices user…
Use this agent when the user needs a blind A/B comparison of two skill outputs. Trigger when user says "compare outputs", "which is better", "A/B test these", "blind comparison", or needs to determine which of two outputs is superior. Context: User has two skill output directories to compare user: "Compare these two…
Use this agent when the user needs to evaluate skill outputs against a set of expectations or assertions. Trigger when user says "grade the skill", "evaluate outputs", "check if assertions pass", "score the results", or needs automated quality assessment of skill execution. Context: User ran a skill and wants to…
Use this agent when the user asks to "validate my plugin", "check plugin structure", "verify plugin is correct", "validate plugin.json", or mentions plugin validation. Also trigger proactively after user creates or modifies plugin components. Context: User finished creating a new plugin user: "I've created my first…
Use this agent when auditing, reviewing, or evaluating SKILL.md files for best practices compliance. MUST BE USED when user asks to "audit a skill", "check skill compliance", "evaluate skill structure", or needs deep skill quality assessment against create-extensions standards. Context: User wants skill audited…
Use this agent when the user has created or modified a skill and needs quality review, asks to "review my skill", "check skill quality", "improve skill description", or wants to ensure a skill follows best practices. Trigger proactively after skill creation. Context: User just created a new skill user: "I've created a…
Use this agent when auditing, reviewing, or evaluating agent configuration files for best practices compliance. MUST BE USED when user asks to "audit an agent", "check agent config", "review subagent", or needs agent configuration validation. Context: User wants agent audited user: "Audit my grader agent…