Skip to main content
skill CX Codex

debug-live-issue — Claude Code skill: what it does, how to install

debug-live-issue walks an agent through incident-style debugging: pin down the symptom, isolate the subsystem, reproduce, prove the cause, then apply a minimal fix.

MIT ★ 1,198 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill debug-live-issue -a claude-code
Open on GitHub

What debug-live-issue does

The skill turns debugging into a fixed sequence. First it records the symptom, the expected behavior, and a reproducible path. Then it isolates the subsystem at fault — hook ingestion, an API route, database state, websocket, or UI rendering — before touching any code.

A reference file, references/investigation-template.md, backs the workflow during an investigation. The evidence bar is strict: logs, actual API responses, database state checks, and deterministic repro steps take priority over guesses. When a bug can't be fully reproduced, the agent has to say so and name its strongest hypothesis instead of pretending to certainty.

Nothing here is tied to a particular stack or language; it's a process for reasoning through a failure, not a set of debugging commands.

What it helps with

  • work through a failing workflow step by step instead of guessing
  • pin down which subsystem is actually broken
  • prove a root cause before touching code
  • write down a reproducible path for a regression
  • separate a confirmed cause from a hunch

Example prompts for the agent

  • Debug this failing workflow using debug-live-issue
  • Apply debug-live-issue to the data mismatch between the API and the websocket
  • Isolate the subsystem and find the root cause of this flaky test with debug-live-issue

How to install debug-live-issue

1Skills CLI (Vercel)

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill debug-live-issue -a claude-code

2Manually: put the files in place

~/.claude/skills/debug-live-issue/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/debug-live-issue/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about debug-live-issue

How do I install debug-live-issue in Claude Code?

Run npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill debug-live-issue -a claude-code; the skill then lives at ~/.claude/skills/debug-live-issue/SKILL.md.

What does debug-live-issue do?

It enforces a disciplined incident workflow: capture the symptom, isolate the subsystem (hooks, API, database, websocket, UI), reproduce with minimal surface area, prove the root cause, and only then apply a minimal fix.

What evidence does debug-live-issue require before a fix?

Direct logs, real API responses, database state checks, and deterministic repro steps; if the issue isn't fully reproducible, the agent must state its uncertainty and strongest hypothesis rather than guess.

Source text

SKILL.md · MIT
---
name: debug-live-issue
description: Debug production-like issues in this repository with disciplined evidence gathering. Use when fixing failing workflows, regressions, flaky behavior, or data inconsistencies across hooks, API, DB, websocket, and UI.
---

# 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`

© hoangsonww · MIT · hoangsonww/Claude-Code-Agent-Monitor

Similar skills

All skills for Code review and refactoring →

From the same set155

The whole set →
open-dashboard open-dashboard prints the Agent Monitor address and the commands to start or open it. Use it when you need the local dashboard instructions. CX Codex +1 ★ 1,198repo stars report-analyst report-analyst builds executive, cost, reliability and workflow reports from a local CCAM API, keeping units, scope and data freshness intact. Handy when a stakeholder summary has to hold up to scrutiny. CX Codex ★ 1,198repo stars ping ping is a Claude Code command that checks the local Agent Monitor dashboard API and reports its reachability. CX Codex +1 ★ 1,198repo stars repo-onboarding repo-onboarding maps a repository before coding, helping locate the right module, ownership, and checks for a planned change. CX Codex +1 ★ 1,198repo stars overspend overspend spots the most expensive Claude Code sessions via a local dashboard and displays them in a ranking table. Useful when spending spikes unexpectedly. CX Codex +1 ★ 1,198repo stars top-spenders top-spenders sorts Claude Code sessions by cost and lists the most expensive ones. Use it to inspect session spending and compare the top entries with the total. CX Codex +1 ★ 1,198repo stars runs Pulls recent Workflow-tool fleet runs from the local Agent Monitor and prints a status summary plus a compact table of the latest ones. CX Codex +1 ★ 1,198repo stars recent recent fetches the latest Claude Code sessions from Agent Monitor with costs and run statuses. Useful when you need a quick summary of agent activity and spending. CX Codex +1 ★ 1,198repo stars

Project sponsors

Companies that keep this analytics open