When your production workflow breaks or your tests start flaking, this skill enforces the discipline you know you should follow but often skip under pressure. It walks you through capturing symptoms, isolating the subsystem (hook, API, DB, websocket, UI), reproducing with minimal scope, and proving root cause before you touch code. The evidence standards are the real value here: direct logs and DB checks over guesses, minimal fixes over shotgun debugging. It includes an investigation template reference, which suggests this is meant for teams that want consistent incident response. Good for anyone who's shipped a speculative fix at 2am and regretted it.

GitHub stars
455
last updated
Jun 11, 2026

Install

$ npx -y skills add hoangsonww/claude-code-agent-monitor --skill debug-live-issue --agent claude-code

Installs into .claude/skills of the current project.

Files

Debug Live Issue

Use this workflow for incident-style debugging.

Steps

  • Capture symptom, expected behavior, and reproducible path.
  • Isolate subsystem first: hook ingestion, API route, DB state, websocket, or UI rendering.
  • Reproduce with minimal surface area.
  • Prove root cause before changing code.
  • Apply minimal fix and re-verify.

Evidence standards

  • Prefer direct logs, API responses, DB state checks, and deterministic repro steps.
  • Avoid speculative fixes without root-cause evidence.
  • If not fully reproducible, state uncertainty and strongest hypothesis.

References

  • Investigation template: references/investigation-template.md

Sponsors

Details

Repository
github.com/hoangsonww/claude-code-agent-monitor
Categories
Frontend Development, Backend & APIs, DevOps & CI/CD, Git & Pull Requests, AI & Agent Building, Debugging
License
MIT
First seen
Jun 11, 2026

More from hoangsonww/claude-code-agent-monitor

All 24
1hoangsonww avatarship-featurehoangsonww/claude-code-agent-monitorImplement a feature safely end-to-end in this repository. Use when adding or changing functionality across backend, frontend, or MCP with required verification 0skills.sh installs
2hoodini avatarcinematic-scrub-landinghoodini/ai-agents-skillsBuild a premium cinematic landing page with mouse-scrub video hero and brand-driven narrative-arc sections. Use whenever the user provides a hero video plus a p0skills.sh installs
3hoodini avatarparallax-landing-pagehoodini/ai-agents-skillsBuild a scroll-driven cinematic landing page from a short video. The user provides a 5–15 second video (often AI-generated); this skill extracts every frame at 0skills.sh installs
4hoodini avatarvideo-to-landing-pagehoodini/ai-agents-skillsTurn any video into a cinematic scroll-driven landing page — Apple-style hero where scrolling progresses the visible frame through the video. Use when the user 0skills.sh installs
5hoodini avataryuv-pilothoodini/ai-agents-skillsTop-of-pyramid orchestrator for Yuval Avidani's YUV.AI brand work. Apply when (a) the user wants YUV.AI output and the medium is ambiguous or multi-medium, (b) 0skills.sh installs
6htmlstreamofficial avatarpreline-theme-generatorhtmlstreamofficial/prelineGenerate, preview, save, or validate Preline theme CSS using the bundled local generator in this skill. Use when the user asks to create a new Preline theme, ma0skills.sh installs