agent-debugger
Agent Debugger
Overview
Debug AI agent issues systematically using analysis scripts and proven debugging patterns. This skill helps identify root causes of common agent failures: incorrect responses, tool calling errors, conversation loops, performance problems, and more.
When to Use This Skill
Trigger this skill when:
- Agent gives wrong or irrelevant responses
- Tools are not being called or are called incorrectly
- Conversation gets stuck in loops or repeated patterns
- Agent performance is slow or inconsistent
- Tool executions are failing or returning errors
- Need to analyze conversation logs or API traces
Debugging Workflow
Step 1: Gather Diagnostic Data
More from avivk5498/my-claude-code-skills
ceo-companion
Collaborative CEO co-pilot for SaaS strategy sessions. Researches markets, validates ideas, designs UI inspiration boards, and produces a .strategy/ folder that Beads Orchestration consumes for autonomous building. Use as Session 1 before a Beads build session.
17runpod-serverless-builder
Build production-ready RunPod serverless endpoints with optimized cold start times. Use when creating or modifying RunPod serverless workers for (1) vLLM-based LLM inference, (2) ComfyUI image/video generation, or (3) custom Python inference. Supports both baked models (fastest cold starts) and dynamic loading (shared models). Generates complete projects including Dockerfiles, worker handlers, startup scripts, and configuration optimized for minimal cold start latency.
13create-beads-orchestration
Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead.
9agentform
|
5