Skip to content
Get packs

Distributed Tracing

Trace requests across microservices with Jaeger or Tempo to find latency bottlenecks

Source Download skill
Repository
wshobson/agents
Stars
42,095
Licence
MIT
Files
2 files

What it does

This skill gives the agent a playbook for distributed tracing, a way to follow a single user request as it hops between many services so you can see where time is spent and where errors start. When you ask for help with slow or failing microservices, the agent follows its guidance on instrumentation, sampling, adding useful tags, correlating logs with trace IDs, and troubleshooting missing traces. It also points to related skills for metrics, dashboards and latency SLOs.

Great for

  • Backend engineers debugging slow requests across several microservices
  • Platform or SRE teams setting up Jaeger or Tempo based observability
  • Developers who want OpenTelemetry-style trace and log correlation explained

Skip it if

  • Single-process applications with no service boundaries, where ordinary profiling or logs are simpler
  • Non-technical users looking for a finished tracing system, since the skill gives guidance rather than deploying anything
  • Production changes made without review: the advice includes sampling and overhead targets that must be checked against your own system

Try asking

  • “Help me find which service is causing the latency in our checkout request flow using traces”
  • “Set up OpenTelemetry tracing in our Python services and send spans to Jaeger”
  • “Why are no traces appearing in Tempo after I added instrumentation?”
  • “Show me how to add trace IDs to our application logs so I can correlate them”
Step-by-step guide: how to use Distributed TracingInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    distributed-tracing.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip distributed-tracing.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip distributed-tracing.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Name the services, language and whether you use Jaeger or Tempo so the agent can tailor the instrumentation example
  • Share a sample trace or error message so troubleshooting starts from real symptoms rather than the generic checklist
  • Treat the sampling rate and overhead figures as starting points and validate them against your own traffic

What's inside

  • references/details.md
  • SKILL.md

Redistributed unmodified from wshobson/agents under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.