Scan React projects for correctness, accessibility, security, architecture and performance findings; triage and fix issues with the upstream workflow.
Debugging Skills for Claude Code, Codex & AI Agents
These skills help an agent find root causes instead of guessing. They include structured bug diagnosis, test fixing, browser DevTools debugging, CI failure triage and runtime diagnostics.
30 skillsExplore Debugging skills
26 skillsdiagnosing-bugs
Investigate bugs and performance regressions using a reproducible feedback loop.
Group test failures and work through fixes systematically.
Debugging and Error Recovery
Find root causes through reproduction, localization, reduction, repair and regression protection.
Browser Testing with DevTools
Inspect DOM, console, network and runtime behavior through Chrome DevTools MCP to investigate browser bugs.
Diagnose Vue runtime warnings, reactivity issues and SSR hydration problems.
Claude Code GitHub Actions Triage
Analyze failed GitHub Actions jobs, compare prior runs and identify the breaking change or flaky behavior.
Arthas CPU Diagnostics
Investigate JVM CPU spikes with thread evidence, stack inspection, and bounded method tracing.
Waza Hunt
Investigate the root cause of errors, crashes, and regressions before proposing a fix.
Honcho — Inspect Honcho
Inspect and debug Honcho workspaces via the `honcho` CLI.
Graph Guided Debugging
Use a repository knowledge graph to locate relevant code and investigate reported issues.
ai-agents skill for Claude AI. Grade A. A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating loops.
Reproduce terminal, process and agent issues in a disposable named Herdr session while preserving the main session.
Trace a bug to the responsible layer and make a focused change.
Arthas EagleEye Trace ID
Retrieve EagleEye trace IDs with Arthas to connect request execution with application logs.
Turn a reported defect into an actionable bug report or issue draft.
Investigate ambiguous failures with evidence-ranked hypotheses before editing.
Inspect and filter application logs using command-line log analysis tools.
Diagnose a reproducible React interaction with browser traces, rendering evidence and a structured report.
Open SWE Pull Request Monitor
Monitor a pull request until CI succeeds, investigate failures and retry only confirmed flaky workflow jobs.
Arthas Spring Context Diagnostics
Inspect Spring application contexts, bean definitions, and configuration sources with Arthas.
Investigate Node.js internals, V8, libuv, native addons and build failures.
Open SWE Local GitHub Development
Run the Open SWE dashboard locally against real GitHub data using an authenticated gh CLI.
Fix security vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud) — triage by severity, patch the root cause rather than the symptom, and re-run Strix to prove each fix actually closes the exploit.
Diagnose WxJava credentials, signatures, certificates, callbacks and multi-account configuration.
Automatically fix broken OpenCLI adapters when commands fail.
Related topics
How to choose Debugging skills
Use a diagnosis skill for unclear bugs, the test-fixing skill for red suites, and DevTools or Arthas skills for runtime issues.
- Find the root cause of a bug
- Fix a failing test suite
- Triage a failing GitHub Actions run







