evaluate-and-improve-agent

SKILLWorkflowcommunity
v0.0.0viktorbezdekMITUpdated 2mo agoSource →

Diagnostic-loop workflow for improving an underperforming AI agent. Starts with baseline measurement using rubrics and LLM-as-judge scoring (agent-evaluation), then diagnoses architectural problems like task-model mismatch and pipeline bottlenecks (agent-project-development), redesigns the agent top

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
10Repo stars
1Clients
1Formats
2mo agoLast update
Skill
Authorviktorbezdek
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Diagnostic-loop workflow for improving an underperforming AI agent. Starts with baseline measurement using rubrics and LLM-as-judge scoring (agent-evaluation), then diagnoses architectural problems like task-model mismatch and pipeline bottlenecks (agent-project-development), redesigns the agent topology — supervisor, swarm, or specialized agents (multi-agent-patterns), adds the right memory frame

Keywords
skillclaude