Loading...
Loading...
Found 23 Skills
Inspect Claude Code session logs, tool calls, token usage, subagents, and context window using claude-devtools visual UI
Preserve critical session state when compacting context. Use when context window is filling up and you need to summarize/reduce while keeping essential debugging information.
Instruments Python and TypeScript code with MLflow Tracing for observability. Triggers on questions about adding tracing, instrumenting agents/LLM apps, getting started with MLflow tracing, or tracing specific frameworks (LangGraph, LangChain, OpenAI, DSPy, CrewAI, AutoGen). Examples - "How do I add tracing?", "How to instrument my agent?", "How to trace my LangChain app?", "Getting started with MLflow tracing", "Trace my TypeScript app"
Orchestrate multiple specialized agents working in parallel to debug independent problems. Use when encountering 3+ unrelated bugs or test failures in isolated modules. Matches each problem to the right expert agent and launches them concurrently via the Agent tool with worktree isolation. Supports all available subagent types.
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.
Systematically debug issues, investigating bugs, troubleshooting problems, or tracking down errors with persistent state across context resets. Triggers include "debug", "investigate bug", "troubleshoot", "find the problem", "why isn't this working", and "debug session".
Multi-agent investigation for stubborn bugs. Use when: going in circles debugging, need to investigate browser/API interactions, complex bugs resisting normal debugging, or when symptoms don't match expectations. Launches parallel agents with different perspectives and uses Chrome tools for evidence gathering.
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Debugging toolkit for AI agents. Diagnose symptoms via memory cache -> behavior cache -> codebase search, trace data flow, git-bisect bad commits, and compare output directories.
Read production traces, identify what's failing, and build failure taxonomies using open coding and axial coding methodology. Use when debugging agent or pipeline quality, investigating "why are my outputs bad?", or before building any evaluator — error analysis must come first. Do NOT use when you already have identified failure modes and need evaluators (use build-evaluator) or datasets (use generate-synthetic-dataset).
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. A core context engineering skill — also activates when the user mentions "context engineering" or "context-engineering" in the context of diagnosing and mitigating context failures.