IN

investigate-issue

Coordinate incident investigations and identify root causes based on evidence.

Install

mkdir -p .claude/skills/investigate-issue && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15202" && unzip -o skill.zip -d .claude/skills/investigate-issue && rm skill.zip

Installs to .claude/skills/investigate-issue

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Top-level diagnostic workflow for investigating issues and incidents using evidence, dynamically routing to the correct specialist agent, identifying symptoms and failing boundaries, evaluating hypotheses, and determining the most likely root cause only when supported. Use when asked to debug why an issue occurred or produce an investigation report before RCA writing; do not use to write formal RCAs or generate PDFs.
420 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • →Gather objective facts like error messages and timestamps.
  • →Identify visible symptoms from user reports or logs.
  • →Identify the suspected failing boundary (e.g., frontend, backend).
  • →Assign a primary investigator and supporting specialists based on evidence.
  • →Generate multiple plausible hypotheses for the issue.
  • →Evaluate each hypothesis with supporting, contradicting, and missing evidence.

How it works

The skill gathers objective facts and visible symptoms, identifies failing boundaries, and assigns specialist agents. It then generates and evaluates hypotheses to determine the most likely root cause.

Inputs & outputs

You give it
Bug reports, application logs, stack traces, metrics, API requests, database records, source code, configuration files, commits, deployment history.
You get back
An investigation report with summary, symptoms, facts, observations, suspected failing boundary, primary investigator, supporting specialists, hypotheses, evide

When to use investigate-issue

  • →Investigating a production incident
  • →Routing a bug report to the right expert
  • →Gathering evidence for a system failure

About investigate-issue

Assesses logs, metrics, and code history to assign diagnostic work to the appropriate specialist. Keeps investigations focused on evidence.

Top-level diagnostic workflow for investigating issues and incidents using evidence, dynamically routing to the correct specialist agent, identifying symptoms and failing boundaries, evaluating hypotheses, and determining the most likely root cause only when supported. Use when asked to debug why an

When not to use it

  • →When the task is to write formal RCAs.
  • →When the task is to generate PDFs.
  • →When the task is to auto-fix an issue.

Limitations

  • →It does not write formal RCAs.
  • →It does not generate PDFs.
  • →It does not auto-fix issues.

How it compares

This workflow systematically gathers evidence and evaluates hypotheses before determining a root cause, unlike an approach that might jump to conclusions or apply fixes without full understanding.

Compared to similar skills

investigate-issue side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
investigate-issue (this skill)05moNo flagsIntermediate
analyzing-logs144moReviewBeginner
sentry107moCautionBeginner
obsidian-incident-runbook34moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

sentry

openai

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.

1048

obsidian-incident-runbook

jeremylongshore

Troubleshoot Obsidian plugin failures with systematic incident response. Use when plugins crash, data is corrupted, or users report critical issues with your Obsidian plugin. Trigger with phrases like "obsidian crash", "obsidian plugin broken", "obsidian incident", "debug obsidian failure", "obsidian emergency".

346

obsidian-observability

jeremylongshore

Set up comprehensive logging and monitoring for Obsidian plugins. Use when implementing debug logging, tracking plugin performance, or setting up error reporting for your Obsidian plugin. Trigger with phrases like "obsidian logging", "obsidian monitoring", "obsidian debug", "track obsidian plugin".

534

langsmith-observability

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.

430

network-info

UKGovernmentBEIS

Gather network configuration and connectivity information including interfaces, routes, and DNS

329

Search skills

Search the agent skills registry