debugging AI Agent Skills

langsmith-observability

21.8k

davila7

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

trulens-instrumentation

3.1k

truera

Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization

ralph-operations

2.0k

mikeyobrien

Use when managing Ralph orchestration loops, analyzing diagnostic data, debugging hat selection, investigating backpressure, or performing post-mortem analysis

Root Cause Analysis

451

rohitg00

Systematic approach to finding the true source of bugs, not just symptoms

Trace and Isolate

451

rohitg00

Techniques for tracing code execution and isolating problematic components

Hypothesis Testing

451

rohitg00

Scientific approach to debugging with hypothesis formation and testing

memory-leak-detector

376

a5c-ai

Detect memory leaks in desktop applications through heap analysis and object tracking

systematic-debugging

374

vstorm-co

Systematic approach to diagnosing and fixing errors

session-management

196

athola

Manage Claude Code sessions with naming, checkpointing, and resume strategies. Use when organizing long-running work, creating debug checkpoints, managing PR reviews.

fix-issue

97

yonatangross

Fixes GitHub issues with parallel analysis. Use to debug errors, resolve regressions, fix bugs, or triage issues.

errors

97

yonatangross

Error pattern analysis and troubleshooting for Claude Code sessions. Use when handling errors, fixing failures, troubleshooting issues.

systematic-debugging

80

bobmatnyc

Methodical debugging instead of random changes

Root Cause Tracing

80

bobmatnyc

Systematically trace bugs backward through call stack to find original trigger

Debugging Strategies

71

PramodDutta

Advanced debugging patterns for test failures covering root cause analysis, flakiness investigation, performance debugging, and systematic troubleshooting methodologies.

Race Condition Finder

71

PramodDutta

Detect and diagnose race conditions in web applications through concurrent interaction testing, state mutation analysis, and timing-sensitive scenario reproduction.

GitHub CI Fix Debugging

71

PramodDutta

Debug and fix failing GitHub PR checks by inspecting GitHub Actions logs, summarizing failure context, drafting fix plans, and implementing fixes after approval.

fullstack-debugger

43

curiositech

Expert debugger for Next.js + Cloudflare Workers + Supabase stacks. Systematic troubleshooting for auth, caching, workers, RLS, CORS, and build issues. Activate on: 'debug', 'not working', 'error', 'broken', '500', '401', '403', 'cache issue', 'RLS', 'CORS'. NOT for: feature development (use language skills), architecture design (use system-architect).

dag-failure-analyzer

43

curiositech

Performs root cause analysis on DAG execution failures. Traces failure propagation, identifies systemic issues, and generates actionable remediation guidance. Activate on 'failure analysis', 'root cause', 'why did it fail', 'debug failure', 'error investigation'. NOT for execution tracing (use dag-execution-tracer) or performance issues (use dag-performance-profiler).

dag-execution-tracer

43

curiositech

Traces complete execution paths through DAG workflows. Records timing, inputs, outputs, and state transitions for all nodes. Activate on 'execution trace', 'trace execution', 'execution path', 'debug execution', 'execution log'. NOT for performance analysis (use dag-performance-profiler) or failure investigation (use dag-failure-analyzer).

event_driven

39

vuralserhat86

Structure systems around asynchronous, event-based communication to decouple producers and consumers for improved scalability and resilience. Use when building loosely coupled systems with asynchronous message-based communication.

openapi_docs

39

vuralserhat86

Generate comprehensive REST API documentation using SpringDoc OpenAPI 3.0 and Swagger UI in Spring Boot 3.x applications. Use when setting up API documentation, configuring Swagger UI, adding OpenAPI annotations, implementing security documentation, or enhancing REST endpoints with examples and schemas.

cache_patterns

39

vuralserhat86

Instruction set for enabling and operating the Spring Cache abstraction in Spring Boot when implementing application-level caching for performance-sensitive workloads.

debugging

18

LangConfig

Expert guidance for debugging code, analyzing errors, and systematic problem-solving. Use when troubleshooting bugs, understanding error messages, or investigating unexpected behavior.

diagnose-maestro-deployment

17

openshift-online

Diagnoses failed Maestro cluster deployments by analyzing Helm releases, pod status, and resource conflicts

testing-strategy

13

ai-debugger-inc

Comprehensive guide for implementing AIDB tests following E2E-first philosophy, DebugInterface abstraction, and MCP response health standards

DAP Protocol Guide

13

ai-debugger-inc

Comprehensive guide for working with the Debug Adapter Protocol (DAP) in AIDB

Browser Daemon

9

jackspace

Persistent browser automation via Playwright daemon. Keep a browser window open and send it commands (navigate, execute JS, inspect console). Perfect for interactive debugging, development, and testing web applications. Use when you need to interact with a browser repeatedly without opening/closing it.

session-logs

7

openxjarvis

View and analyze session logs

Debugging Strategies

1

KaliBellion

Advanced debugging patterns for test failures covering root cause analysis, flakiness investigation, performance debugging, and systematic troubleshooting methodologies.

hive-debugger

1

mattmre

Interactive debugging companion for Hive agents - identifies runtime issues and proposes solutions

Log Analyzer

novas10

Parse log files to find errors, detect patterns, analyze trends, and alert on anomalies

apex-os-bad-boy

fratilanico

The ultimate agent productivity system - 45+ skills with intelligent recommendations, risk-based planning levels, and systematic workflows for maximum efficiency.

hook-master

gabrielgadea

Meta-skill for creating, validating, testing, and debugging Claude Code hooks. Comprehensive reference for all 18 hook events, exit code contracts, JSON schemas, and templates for both Python and shell hooks.

supreme-problem-solver

gabrielgadea

Last-resort problem solver with H0/H1/H2 escalation horizons. Forces scope amplification before giving up. Use when standard debugging has failed 3+ times.